Commit
•
8fe10b5
0
Parent(s):
Update README.md
Browse files- .gitattributes +35 -0
- README.md +142 -0
- config.json +26 -0
- generation_config.json +10 -0
- pytorch_model-00001-of-00029.bin +3 -0
- pytorch_model-00002-of-00029.bin +3 -0
- pytorch_model-00003-of-00029.bin +3 -0
- pytorch_model-00004-of-00029.bin +3 -0
- pytorch_model-00005-of-00029.bin +3 -0
- pytorch_model-00006-of-00029.bin +3 -0
- pytorch_model-00007-of-00029.bin +3 -0
- pytorch_model-00008-of-00029.bin +3 -0
- pytorch_model-00009-of-00029.bin +3 -0
- pytorch_model-00010-of-00029.bin +3 -0
- pytorch_model-00011-of-00029.bin +3 -0
- pytorch_model-00012-of-00029.bin +3 -0
- pytorch_model-00013-of-00029.bin +3 -0
- pytorch_model-00014-of-00029.bin +3 -0
- pytorch_model-00015-of-00029.bin +3 -0
- pytorch_model-00016-of-00029.bin +3 -0
- pytorch_model-00017-of-00029.bin +3 -0
- pytorch_model-00018-of-00029.bin +3 -0
- pytorch_model-00019-of-00029.bin +3 -0
- pytorch_model-00020-of-00029.bin +3 -0
- pytorch_model-00021-of-00029.bin +3 -0
- pytorch_model-00022-of-00029.bin +3 -0
- pytorch_model-00023-of-00029.bin +3 -0
- pytorch_model-00024-of-00029.bin +3 -0
- pytorch_model-00025-of-00029.bin +3 -0
- pytorch_model-00026-of-00029.bin +3 -0
- pytorch_model-00027-of-00029.bin +3 -0
- pytorch_model-00028-of-00029.bin +3 -0
- pytorch_model-00029-of-00029.bin +3 -0
- pytorch_model.bin +3 -0
- pytorch_model.bin.index.json +810 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +35 -0
.gitattributes
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
---
|
| 4 |
+
<h3 align="center">
|
| 5 |
+
Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment
|
| 6 |
+
</h3>
|
| 7 |
+
|
| 8 |
+
<p align="center">
|
| 9 |
+
<a href="https://huggingface.co/Xwin-LM">
|
| 10 |
+
<img src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue">
|
| 11 |
+
</a>
|
| 12 |
+
</p>
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
**Step up your LLM alignment with Xwin-LM!**
|
| 17 |
+
|
| 18 |
+
Xwin-LM aims to develop and open-source alignment technologies for large language models, including supervised fine-tuning (SFT), reward models, reject sampling, reinforcement learning, etc. Our first release, built-upon on the Llama2 base models, ranked **TOP-1** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Notably, it's **the first to surpass GPT-4** on this benchmark. The project will be continuously updated.
|
| 19 |
+
|
| 20 |
+
## News
|
| 21 |
+
|
| 22 |
+
- :boom: [Sep, 2023] We released [Xwin-LM-70B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1), which has achieved a win-rate against Davinci-003 of **95.57%** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmark, ranking as **TOP-1** on AlpacaEval. **It was the FIRST model surpassing GPT-4** on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/). Also note its winrate v.s. GPT-4 is **60.61**.
|
| 23 |
+
- :boom: [Sep, 2023] We released [Xwin-LM-13B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1), which has achieved **91.76%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 13B models.
|
| 24 |
+
- :boom: [Sep, 2023] We released [Xwin-LM-7B-V0.1](https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1), which has achieved **87.82%** win-rate on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), ranking as **top-1** among all 7B models.
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
## Model Card
|
| 28 |
+
| Model | Checkpoint | Report | License |
|
| 29 |
+
|------------|------------|-------------|------------------|
|
| 30 |
+
|Xwin-LM-7B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-7B-V0.1" target="_blank">HF Link</a> | 📃**Coming soon (Stay tuned)** | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|
| 31 |
+
|Xwin-LM-13B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-13B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|
| 32 |
+
|Xwin-LM-70B-V0.1| 🤗 <a href="https://huggingface.co/Xwin-LM/Xwin-LM-70B-V0.1" target="_blank">HF Link</a> | | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License|
|
| 33 |
+
## Benchmarks
|
| 34 |
+
|
| 35 |
+
### Xwin-LM performance on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/).
|
| 36 |
+
|
| 37 |
+
The table below displays the performance of Xwin-LM on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/), where evaluates its win-rate against Text-Davinci-003 across 805 questions. To provide a comprehensive evaluation, we present, for the first time, the win-rate against ChatGPT and GPT-4 as well. Our Xwin-LM model family establish a new state-of-the-art performance across all metrics. Notably, Xwin-LM-70B-V0.1 has eclipsed GPT-4 for the first time, achieving an impressive win-rate of **95.57%** to Text-Davinci-003 and **60.61%** to GPT-4.
|
| 38 |
+
|
| 39 |
+
| **Model** | **AlpacaEval (winrate %)** | **AlpacaEval (winrate %)** |**AlpacaEval (winrate %)** |
|
| 40 |
+
|----------------------------------|------------|----------|-------------|
|
| 41 |
+
| | **v.s. Text-Davinci-003** | **v.s. ChatGPT** | **v.s. GPT4**|
|
| 42 |
+
| **Xwin-LM-70B-V0.1** | **95.57** | **87.50** | **60.61** |
|
| 43 |
+
| GPT-4 | 95.28 | 84.66 | 50.00 |
|
| 44 |
+
| WizardLM-70B-V1.0 | 92.91 | 80.19 | 46.70 |
|
| 45 |
+
| Llama-2-70B-Chat | 92.66 | 81.97 | 51.19 |
|
| 46 |
+
| **Xwin-LM-13B-V0.1** | **91.76** | **81.79** | **55.30** |
|
| 47 |
+
| ChatGPT | 89.37 | 50.00 | 16.60 |
|
| 48 |
+
| WizardLM-13B-V1.2 | 89.17 | 75.75 | 41.91 |
|
| 49 |
+
| **Xwin-LM-7B-V0.1** | **87.35** | **76.40** | **47.57** |
|
| 50 |
+
| Llama-2-13B-Chat | 81.09 | 64.22 | 30.92 |
|
| 51 |
+
|
| 52 |
+
### Case study on [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/)
|
| 53 |
+
|
| 54 |
+
| Prompts | GTP4 response | Xwin-LM response |
|
| 55 |
+
|----------------|------------|--------|
|
| 56 |
+
|I've put a plate on top of an apple, and take the plate from kitchen to dinning room. Where is the apple now|The apple is now in the dining room, as it was underneath the plate when you moved the plate from the kitchen to the dining room.|The apple is still in the kitchen, as you have only moved the plate. The apple is under the plate, so if you want to bring the apple to the dining room, you should either move the apple directly or put the apple on the plate and then move the plate to the dining room.|
|
| 57 |
+
| Answer the following question.<br> How do you say "good evening" in French. | In French, "good evening" is said as "bonsoir." | In French, "good evening" is translated to "bonsoir." This greeting is used in the evening and nighttime hours, typically after 6 p.m. It is a combination of "bon," which means "good," and "soir," which means "evening." To pronounce it, say "bone-swahr." |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Xwin-LM performance on NLP foundation tasks.
|
| 61 |
+
|
| 62 |
+
The following table provides a comparison of Xwin-LMs with other LLMs on NLP foundation tasks.
|
| 63 |
+
|
| 64 |
+
| Model | MMLU 5-shot | ARC 25-shot | TruthfulQA 0-shot | HellaSwag 10-shot | Average |
|
| 65 |
+
|------------------|-------------|-------------|-------------------|-------------------|------------|
|
| 66 |
+
| Text-davinci-003 | <u>56.9<u/> | **85.2** | **59.3** | <u>82.2<u/> | **70.9** |
|
| 67 |
+
|Vicuna-13b 1.1 | 51.3 | 53.0 | 51.8 | 80.1 | 59.1 |
|
| 68 |
+
|Guanaco 30B | 57.6 | 63.7 | 50.7 | **85.1** | 64.3 |
|
| 69 |
+
| WizardLM-7B 1.0 | 42.7 | 51.6 | 44.7 | 77.7 | 54.2 |
|
| 70 |
+
| WizardLM-13B 1.0 | 52.3 | 57.2 | 50.5 | 81.0 | 60.2 |
|
| 71 |
+
| WizardLM-30B 1.0 | **58.8** | <u>62.5<u/> | <u>52.4<u/> | 83.3 | <u>64.2<u/>|
|
| 72 |
+
| **Xwin-LM-7B-V0.1** | 49.7 | 56.2 | 48.1 | 79.5 | 58.4 |
|
| 73 |
+
| **Xwin-LM-13B-V0.1** | - | - | - | - | - |
|
| 74 |
+
| **Xwin-LM-70B-V0.1** | - | - | - | - | - |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
## Inference
|
| 78 |
+
|
| 79 |
+
### Conversation templates
|
| 80 |
+
To obtain desired results, please strictly follow the conversation templates when utilizing our model for inference. Our model adopts the prompt format established by [Vicuna](https://github.com/lm-sys/FastChat) and is equipped to support **multi-turn** conversations.
|
| 81 |
+
```
|
| 82 |
+
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi! ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am Xwin-LM.</s>......
|
| 83 |
+
```
|
| 84 |
+
|
| 85 |
+
### HuggingFace Example
|
| 86 |
+
|
| 87 |
+
```
|
| 88 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 89 |
+
|
| 90 |
+
model = AutoModelForCausalLM.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
|
| 91 |
+
tokenizer = AutoTokenizer.from_pretrained("Xwin-LM/Xwin-LM-7B-V0.1")
|
| 92 |
+
(
|
| 93 |
+
prompt := "A chat between a curious user and an artificial intelligence assistant. "
|
| 94 |
+
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
|
| 95 |
+
"USER: Hello, can you help me? "
|
| 96 |
+
"ASSISTANT:"
|
| 97 |
+
)
|
| 98 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
| 99 |
+
samples = model.generate(**inputs, max_new_tokens=4096, temperature=0.7)
|
| 100 |
+
output = tokenizer.decode(samples[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
|
| 101 |
+
print(output)
|
| 102 |
+
# Of course! I'm here to help. Please feel free to ask your question or describe the issue you're having, and I'll do my best to assist you.
|
| 103 |
+
```
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### vllm Example
|
| 107 |
+
Because Xwin-LM is based on Llama2, it also offers support for rapid inference using [vllm](https://github.com/vllm-project/vllm). Please refer to [vllm](https://github.com/vllm-project/vllm) for detailed installation instructions.
|
| 108 |
+
```
|
| 109 |
+
from vllm import LLM, SamplingParams
|
| 110 |
+
(
|
| 111 |
+
prompt := "A chat between a curious user and an artificial intelligence assistant. "
|
| 112 |
+
"The assistant gives helpful, detailed, and polite answers to the user's questions. "
|
| 113 |
+
"USER: Hello, can you help me? "
|
| 114 |
+
"ASSISTANT:"
|
| 115 |
+
)
|
| 116 |
+
sampling_params = SamplingParams(temperature=0.7, max_tokens=4096)
|
| 117 |
+
llm = LLM(model="Xwin-LM/Xwin-LM-7B-V0.1")
|
| 118 |
+
outputs = llm.generate([prompt,], sampling_params)
|
| 119 |
+
|
| 120 |
+
for output in outputs:
|
| 121 |
+
prompt = output.prompt
|
| 122 |
+
generated_text = output.outputs[0].text
|
| 123 |
+
print(generated_text)
|
| 124 |
+
```
|
| 125 |
+
|
| 126 |
+
|
| 127 |
+
## Citation
|
| 128 |
+
Please consider citing our work if you use the data or code in this repo.
|
| 129 |
+
```
|
| 130 |
+
@software{xwin-lm,
|
| 131 |
+
title = {Xwin-LM},
|
| 132 |
+
author = {Xwin-LM Team},
|
| 133 |
+
url = {https://github.com/Xwin-LM/Xwin-LM},
|
| 134 |
+
version = {pre-release},
|
| 135 |
+
year = {2023},
|
| 136 |
+
month = {9},
|
| 137 |
+
}
|
| 138 |
+
```
|
| 139 |
+
|
| 140 |
+
## Acknowledgements
|
| 141 |
+
|
| 142 |
+
Thanks to [Llama 2](https://ai.meta.com/llama/), [FastChat](https://github.com/lm-sys/FastChat), [AlpacaFarm](https://github.com/tatsu-lab/alpaca_farm), and [vllm](https://github.com/vllm-project/vllm).
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "meta-llama/Llama-2-70b-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 8192,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 28672,
|
| 12 |
+
"max_position_embeddings": 4096,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 64,
|
| 15 |
+
"num_hidden_layers": 80,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.28.1",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"max_length": 4096,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"temperature": 0.6,
|
| 8 |
+
"top_p": 0.9,
|
| 9 |
+
"transformers_version": "4.28.1"
|
| 10 |
+
}
|
pytorch_model-00001-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38e9248eb12e833c740b59e9e2109fbc7ce684437e3fa8d7382848e15e0a2447
|
| 3 |
+
size 9437325577
|
pytorch_model-00002-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92a2a6f48dc81efa76477670709a7a74bac456f0d1b86bee82149417ccd0e418
|
| 3 |
+
size 9328339985
|
pytorch_model-00003-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:624362cafd28d30c9f5ec286388767e9219e55cca89024cca530b282d26d453e
|
| 3 |
+
size 9999428079
|
pytorch_model-00004-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac5cb7c7d2474beaa0ac021e762773d70c90cf18e5d2d0764e11fbec2a443179
|
| 3 |
+
size 9932318961
|
pytorch_model-00005-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72df5f6fdeb912992488415428ef9f7856c597c4dc0ba700bb1c2d9ce1b14a60
|
| 3 |
+
size 9328273665
|
pytorch_model-00006-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb5a6056e86bb9f0cfa458bb5a56360f9186813c32291dbda2de6ec8b8799bda
|
| 3 |
+
size 9328339961
|
pytorch_model-00007-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0594b09b7984b605b18ec08bd16873afd4409301aaf2ac1d42aeafc2095d6ca8
|
| 3 |
+
size 9328339985
|
pytorch_model-00008-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc9e9a6099f5901b95a372c974deb12048ba642f0ebfaa2d0a7bc9a381d8dc30
|
| 3 |
+
size 9999428079
|
pytorch_model-00009-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:751a60db8476d6e25d60d62748636448efa0f2c8fea4d0ecbb3f64bab84249e8
|
| 3 |
+
size 9932318961
|
pytorch_model-00010-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b120fd5cbf31fd3a24bde70b0bd4b6b1c2901cbcd46794842b8c6afc39d07c76
|
| 3 |
+
size 9328273665
|
pytorch_model-00011-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59266e46e3120c592ab80b25ec99174ef26f041051697a662069cf671f31c90a
|
| 3 |
+
size 9328339961
|
pytorch_model-00012-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71b10ae7d557978f8c77fb46dc77b7aacc6f65a281052079fe54727effb0dad1
|
| 3 |
+
size 9328339985
|
pytorch_model-00013-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b346607b4a411d2f99f4138ad62cecb296d515012871a35bc20a5534822e5a8
|
| 3 |
+
size 9999428079
|
pytorch_model-00014-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2027de8d9fc33e84578da68c9821eb5866e7b687795246a74b42507fb579a4e
|
| 3 |
+
size 9932318961
|
pytorch_model-00015-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47dcfeb7fe205bac9db96ce105326f17f4346e7342bbb65470cacf15d60e2385
|
| 3 |
+
size 9328273665
|
pytorch_model-00016-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d170687924d00540f4b1aa63e5d713a57f0ca45efcd7c3fe9fd7eaab7f6c1fd
|
| 3 |
+
size 9328339961
|
pytorch_model-00017-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccf2209b72a83cbc8aa37559f42e0cc77abe78a2c5cd1f71bb4816bd351c4296
|
| 3 |
+
size 9328339985
|
pytorch_model-00018-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc31dae362ac0196d42b8ce76cbb0e5459dc65adb4d463cb5112212fe5a6cee0
|
| 3 |
+
size 9999428079
|
pytorch_model-00019-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f601c50c9eadd622078e08f69c5eb82944922f7dfed50866ef452c7c93ef655
|
| 3 |
+
size 9932318961
|
pytorch_model-00020-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9516953cc4c0ed918535dde46b37c6121e093a1469511a81e64af1bbdd90819
|
| 3 |
+
size 9328273665
|
pytorch_model-00021-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a193e4f4d028ca102132f92a3dc3921b5987ded20eab06b76bc54ee94b8ea5bd
|
| 3 |
+
size 9328339961
|
pytorch_model-00022-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc1c8ece55c90091c70221ae29fbe3a2bdf1dfa3854827e61f90fc68985ec273
|
| 3 |
+
size 9328339985
|
pytorch_model-00023-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:13079863208922b734ae95d4804f5463c59b82a8eb147c45129550b4737fb5e6
|
| 3 |
+
size 9999428079
|
pytorch_model-00024-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70028e8e32e5aec46db6291c514155a6c3ee6e7e14314b935c229b501c772f2e
|
| 3 |
+
size 9932318961
|
pytorch_model-00025-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:01b3fe2a50c3bfccf5a527f77b7a844d649dfad79df8a5bf7252edf422e1c7c7
|
| 3 |
+
size 9328273665
|
pytorch_model-00026-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f026c8c6a2ceb4e0a0ac9c7159368829bd65df66708c3c1de35b405892e111e
|
| 3 |
+
size 9328339961
|
pytorch_model-00027-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ceff689d8ddd4dbbc698503ae267fc284c1df42ca9a13d256af582470ff5d63
|
| 3 |
+
size 9328339985
|
pytorch_model-00028-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:231de1e9bf5a52ea4dafc052e1faee0ae5e657b4d537349c9ba9b0ac1bc23586
|
| 3 |
+
size 9999428079
|
pytorch_model-00029-of-00029.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55f10750d204d211f82b8c43aac89206704a65a8388faee5f8dbd43ab57cbf1f
|
| 3 |
+
size 7558307097
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
| 3 |
+
size 443
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,810 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 275906613248
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00029-of-00029.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00029.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00029.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00029.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00029.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00029.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00029.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00029.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00029.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00029.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00029.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00029.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00029.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00029.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00029.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00029.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00029.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00029.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00029.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00029.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00029.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00029.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00029.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00029.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00029.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00029.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00029.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00029.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00029.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00029.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00029.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00029.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00029.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00029.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00029.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00029.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00029.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00029.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00029.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00029.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00029.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00029.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00029.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00029.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00029.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00029.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00029.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00029.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00029.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00029.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00029.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00029.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00029.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00029.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-of-00029.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00029.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00014-of-00029.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00029.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00029.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00029.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 358 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 359 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 360 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 361 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 362 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00015-of-00029.bin",
|
| 363 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 364 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 365 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 366 |
+
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00029.bin",
|
| 367 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 368 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 369 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 370 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 371 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 372 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 373 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 374 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 375 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 376 |
+
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00029.bin",
|
| 377 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00015-of-00029.bin",
|
| 378 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 379 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 380 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 381 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 382 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 383 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 384 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 385 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 386 |
+
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00029.bin",
|
| 387 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 388 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 389 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 390 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 391 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 392 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00016-of-00029.bin",
|
| 393 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 394 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 395 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 396 |
+
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00029.bin",
|
| 397 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 398 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 399 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 400 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 401 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 402 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 403 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 404 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 405 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 406 |
+
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00016-of-00029.bin",
|
| 407 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00016-of-00029.bin",
|
| 408 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 409 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 410 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 411 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 412 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 413 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 414 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 415 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 416 |
+
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00029.bin",
|
| 417 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 418 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 419 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 420 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 421 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 422 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00017-of-00029.bin",
|
| 423 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 424 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 425 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 426 |
+
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00029.bin",
|
| 427 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 428 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 429 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 430 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 431 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 432 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 433 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 434 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 435 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 436 |
+
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00029.bin",
|
| 437 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00017-of-00029.bin",
|
| 438 |
+
"model.layers.48.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 439 |
+
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 440 |
+
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 441 |
+
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 442 |
+
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 443 |
+
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 444 |
+
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 445 |
+
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 446 |
+
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00029.bin",
|
| 447 |
+
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 448 |
+
"model.layers.49.input_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 449 |
+
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 450 |
+
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 451 |
+
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 452 |
+
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00018-of-00029.bin",
|
| 453 |
+
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 454 |
+
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 455 |
+
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 456 |
+
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00029.bin",
|
| 457 |
+
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 458 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 459 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 460 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 461 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 462 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 463 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 464 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 465 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 466 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00029.bin",
|
| 467 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00029.bin",
|
| 468 |
+
"model.layers.50.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 469 |
+
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 470 |
+
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 471 |
+
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 472 |
+
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 473 |
+
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 474 |
+
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 475 |
+
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 476 |
+
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00029.bin",
|
| 477 |
+
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00018-of-00029.bin",
|
| 478 |
+
"model.layers.51.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 479 |
+
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 480 |
+
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 481 |
+
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 482 |
+
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 483 |
+
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 484 |
+
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 485 |
+
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 486 |
+
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00029.bin",
|
| 487 |
+
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 488 |
+
"model.layers.52.input_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 489 |
+
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 490 |
+
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 491 |
+
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 492 |
+
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00019-of-00029.bin",
|
| 493 |
+
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 494 |
+
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 495 |
+
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 496 |
+
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00029.bin",
|
| 497 |
+
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00019-of-00029.bin",
|
| 498 |
+
"model.layers.53.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 499 |
+
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 500 |
+
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 501 |
+
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 502 |
+
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 503 |
+
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 504 |
+
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 505 |
+
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 506 |
+
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00029.bin",
|
| 507 |
+
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 508 |
+
"model.layers.54.input_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 509 |
+
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 510 |
+
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 511 |
+
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 512 |
+
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00020-of-00029.bin",
|
| 513 |
+
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 514 |
+
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 515 |
+
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 516 |
+
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00029.bin",
|
| 517 |
+
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 518 |
+
"model.layers.55.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 519 |
+
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 520 |
+
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 521 |
+
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 522 |
+
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 523 |
+
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 524 |
+
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 525 |
+
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 526 |
+
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00029.bin",
|
| 527 |
+
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00020-of-00029.bin",
|
| 528 |
+
"model.layers.56.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 529 |
+
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 530 |
+
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 531 |
+
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 532 |
+
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 533 |
+
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 534 |
+
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 535 |
+
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 536 |
+
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00029.bin",
|
| 537 |
+
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 538 |
+
"model.layers.57.input_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 539 |
+
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 540 |
+
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 541 |
+
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 542 |
+
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00021-of-00029.bin",
|
| 543 |
+
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 544 |
+
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 545 |
+
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 546 |
+
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00029.bin",
|
| 547 |
+
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 548 |
+
"model.layers.58.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 549 |
+
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 550 |
+
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 551 |
+
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 552 |
+
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 553 |
+
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 554 |
+
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 555 |
+
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 556 |
+
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00029.bin",
|
| 557 |
+
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00021-of-00029.bin",
|
| 558 |
+
"model.layers.59.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 559 |
+
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 560 |
+
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 561 |
+
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 562 |
+
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 563 |
+
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 564 |
+
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 565 |
+
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 566 |
+
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00029.bin",
|
| 567 |
+
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 568 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 569 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 570 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 571 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 572 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 573 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 574 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 575 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 576 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00029.bin",
|
| 577 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 578 |
+
"model.layers.60.input_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 579 |
+
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 580 |
+
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 581 |
+
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 582 |
+
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00022-of-00029.bin",
|
| 583 |
+
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 584 |
+
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 585 |
+
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 586 |
+
"model.layers.60.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00029.bin",
|
| 587 |
+
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 588 |
+
"model.layers.61.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 589 |
+
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 590 |
+
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 591 |
+
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 592 |
+
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 593 |
+
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 594 |
+
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 595 |
+
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 596 |
+
"model.layers.61.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00029.bin",
|
| 597 |
+
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00022-of-00029.bin",
|
| 598 |
+
"model.layers.62.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 599 |
+
"model.layers.62.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 600 |
+
"model.layers.62.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 601 |
+
"model.layers.62.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 602 |
+
"model.layers.62.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 603 |
+
"model.layers.62.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 604 |
+
"model.layers.62.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 605 |
+
"model.layers.62.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 606 |
+
"model.layers.62.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00029.bin",
|
| 607 |
+
"model.layers.62.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 608 |
+
"model.layers.63.input_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 609 |
+
"model.layers.63.mlp.down_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 610 |
+
"model.layers.63.mlp.gate_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 611 |
+
"model.layers.63.mlp.up_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 612 |
+
"model.layers.63.post_attention_layernorm.weight": "pytorch_model-00023-of-00029.bin",
|
| 613 |
+
"model.layers.63.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 614 |
+
"model.layers.63.self_attn.o_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 615 |
+
"model.layers.63.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 616 |
+
"model.layers.63.self_attn.rotary_emb.inv_freq": "pytorch_model-00023-of-00029.bin",
|
| 617 |
+
"model.layers.63.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 618 |
+
"model.layers.64.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 619 |
+
"model.layers.64.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 620 |
+
"model.layers.64.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 621 |
+
"model.layers.64.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 622 |
+
"model.layers.64.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 623 |
+
"model.layers.64.self_attn.k_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 624 |
+
"model.layers.64.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 625 |
+
"model.layers.64.self_attn.q_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 626 |
+
"model.layers.64.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00029.bin",
|
| 627 |
+
"model.layers.64.self_attn.v_proj.weight": "pytorch_model-00023-of-00029.bin",
|
| 628 |
+
"model.layers.65.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 629 |
+
"model.layers.65.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 630 |
+
"model.layers.65.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 631 |
+
"model.layers.65.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 632 |
+
"model.layers.65.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 633 |
+
"model.layers.65.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 634 |
+
"model.layers.65.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 635 |
+
"model.layers.65.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 636 |
+
"model.layers.65.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00029.bin",
|
| 637 |
+
"model.layers.65.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 638 |
+
"model.layers.66.input_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 639 |
+
"model.layers.66.mlp.down_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 640 |
+
"model.layers.66.mlp.gate_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 641 |
+
"model.layers.66.mlp.up_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 642 |
+
"model.layers.66.post_attention_layernorm.weight": "pytorch_model-00024-of-00029.bin",
|
| 643 |
+
"model.layers.66.self_attn.k_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 644 |
+
"model.layers.66.self_attn.o_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 645 |
+
"model.layers.66.self_attn.q_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 646 |
+
"model.layers.66.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00029.bin",
|
| 647 |
+
"model.layers.66.self_attn.v_proj.weight": "pytorch_model-00024-of-00029.bin",
|
| 648 |
+
"model.layers.67.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 649 |
+
"model.layers.67.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 650 |
+
"model.layers.67.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 651 |
+
"model.layers.67.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 652 |
+
"model.layers.67.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 653 |
+
"model.layers.67.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 654 |
+
"model.layers.67.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 655 |
+
"model.layers.67.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 656 |
+
"model.layers.67.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00029.bin",
|
| 657 |
+
"model.layers.67.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 658 |
+
"model.layers.68.input_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 659 |
+
"model.layers.68.mlp.down_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 660 |
+
"model.layers.68.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 661 |
+
"model.layers.68.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 662 |
+
"model.layers.68.post_attention_layernorm.weight": "pytorch_model-00025-of-00029.bin",
|
| 663 |
+
"model.layers.68.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 664 |
+
"model.layers.68.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 665 |
+
"model.layers.68.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 666 |
+
"model.layers.68.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00029.bin",
|
| 667 |
+
"model.layers.68.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 668 |
+
"model.layers.69.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 669 |
+
"model.layers.69.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 670 |
+
"model.layers.69.mlp.gate_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 671 |
+
"model.layers.69.mlp.up_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 672 |
+
"model.layers.69.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 673 |
+
"model.layers.69.self_attn.k_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 674 |
+
"model.layers.69.self_attn.o_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 675 |
+
"model.layers.69.self_attn.q_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 676 |
+
"model.layers.69.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00029.bin",
|
| 677 |
+
"model.layers.69.self_attn.v_proj.weight": "pytorch_model-00025-of-00029.bin",
|
| 678 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 679 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 680 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 681 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 682 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00029.bin",
|
| 683 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 684 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 685 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 686 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00029.bin",
|
| 687 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 688 |
+
"model.layers.70.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 689 |
+
"model.layers.70.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 690 |
+
"model.layers.70.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 691 |
+
"model.layers.70.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 692 |
+
"model.layers.70.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 693 |
+
"model.layers.70.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 694 |
+
"model.layers.70.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 695 |
+
"model.layers.70.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 696 |
+
"model.layers.70.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00029.bin",
|
| 697 |
+
"model.layers.70.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 698 |
+
"model.layers.71.input_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 699 |
+
"model.layers.71.mlp.down_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 700 |
+
"model.layers.71.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 701 |
+
"model.layers.71.mlp.up_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 702 |
+
"model.layers.71.post_attention_layernorm.weight": "pytorch_model-00026-of-00029.bin",
|
| 703 |
+
"model.layers.71.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 704 |
+
"model.layers.71.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 705 |
+
"model.layers.71.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 706 |
+
"model.layers.71.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00029.bin",
|
| 707 |
+
"model.layers.71.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 708 |
+
"model.layers.72.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 709 |
+
"model.layers.72.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 710 |
+
"model.layers.72.mlp.gate_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 711 |
+
"model.layers.72.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 712 |
+
"model.layers.72.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 713 |
+
"model.layers.72.self_attn.k_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 714 |
+
"model.layers.72.self_attn.o_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 715 |
+
"model.layers.72.self_attn.q_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 716 |
+
"model.layers.72.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00029.bin",
|
| 717 |
+
"model.layers.72.self_attn.v_proj.weight": "pytorch_model-00026-of-00029.bin",
|
| 718 |
+
"model.layers.73.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 719 |
+
"model.layers.73.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 720 |
+
"model.layers.73.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 721 |
+
"model.layers.73.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 722 |
+
"model.layers.73.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 723 |
+
"model.layers.73.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 724 |
+
"model.layers.73.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 725 |
+
"model.layers.73.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 726 |
+
"model.layers.73.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00029.bin",
|
| 727 |
+
"model.layers.73.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 728 |
+
"model.layers.74.input_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 729 |
+
"model.layers.74.mlp.down_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 730 |
+
"model.layers.74.mlp.gate_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 731 |
+
"model.layers.74.mlp.up_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 732 |
+
"model.layers.74.post_attention_layernorm.weight": "pytorch_model-00027-of-00029.bin",
|
| 733 |
+
"model.layers.74.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 734 |
+
"model.layers.74.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 735 |
+
"model.layers.74.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 736 |
+
"model.layers.74.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00029.bin",
|
| 737 |
+
"model.layers.74.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 738 |
+
"model.layers.75.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 739 |
+
"model.layers.75.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 740 |
+
"model.layers.75.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 741 |
+
"model.layers.75.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 742 |
+
"model.layers.75.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 743 |
+
"model.layers.75.self_attn.k_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 744 |
+
"model.layers.75.self_attn.o_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 745 |
+
"model.layers.75.self_attn.q_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 746 |
+
"model.layers.75.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00029.bin",
|
| 747 |
+
"model.layers.75.self_attn.v_proj.weight": "pytorch_model-00027-of-00029.bin",
|
| 748 |
+
"model.layers.76.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 749 |
+
"model.layers.76.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 750 |
+
"model.layers.76.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 751 |
+
"model.layers.76.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 752 |
+
"model.layers.76.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 753 |
+
"model.layers.76.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 754 |
+
"model.layers.76.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 755 |
+
"model.layers.76.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 756 |
+
"model.layers.76.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00029.bin",
|
| 757 |
+
"model.layers.76.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 758 |
+
"model.layers.77.input_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 759 |
+
"model.layers.77.mlp.down_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 760 |
+
"model.layers.77.mlp.gate_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 761 |
+
"model.layers.77.mlp.up_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 762 |
+
"model.layers.77.post_attention_layernorm.weight": "pytorch_model-00028-of-00029.bin",
|
| 763 |
+
"model.layers.77.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 764 |
+
"model.layers.77.self_attn.o_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 765 |
+
"model.layers.77.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 766 |
+
"model.layers.77.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00029.bin",
|
| 767 |
+
"model.layers.77.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 768 |
+
"model.layers.78.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
| 769 |
+
"model.layers.78.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 770 |
+
"model.layers.78.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 771 |
+
"model.layers.78.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 772 |
+
"model.layers.78.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
| 773 |
+
"model.layers.78.self_attn.k_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 774 |
+
"model.layers.78.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 775 |
+
"model.layers.78.self_attn.q_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 776 |
+
"model.layers.78.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00029.bin",
|
| 777 |
+
"model.layers.78.self_attn.v_proj.weight": "pytorch_model-00028-of-00029.bin",
|
| 778 |
+
"model.layers.79.input_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
| 779 |
+
"model.layers.79.mlp.down_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 780 |
+
"model.layers.79.mlp.gate_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 781 |
+
"model.layers.79.mlp.up_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 782 |
+
"model.layers.79.post_attention_layernorm.weight": "pytorch_model-00029-of-00029.bin",
|
| 783 |
+
"model.layers.79.self_attn.k_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 784 |
+
"model.layers.79.self_attn.o_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 785 |
+
"model.layers.79.self_attn.q_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 786 |
+
"model.layers.79.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00029.bin",
|
| 787 |
+
"model.layers.79.self_attn.v_proj.weight": "pytorch_model-00029-of-00029.bin",
|
| 788 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 789 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 790 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 791 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 792 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 793 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 794 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 795 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 796 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00029.bin",
|
| 797 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00029.bin",
|
| 798 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 799 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 800 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 801 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 802 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00029.bin",
|
| 803 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 804 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 805 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 806 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00029.bin",
|
| 807 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00029.bin",
|
| 808 |
+
"model.norm.weight": "pytorch_model-00029-of-00029.bin"
|
| 809 |
+
}
|
| 810 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": false,
|
| 22 |
+
"model_max_length": 4096,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
}
|
| 35 |
+
}
|