LoneStriker commited on
Commit
8c2f438
1 Parent(s): 8decbf4

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ model_type: llama
4
+ tags:
5
+ - facebook
6
+ - meta
7
+ - pytorch
8
+ - llama
9
+ - llama-2
10
+ - Storywriter
11
+ ---
12
+
13
+ ![GOAT-70B-Storytelling](https://assets.adapt.ws/files/20231117_ehznrqludevtapck.png)
14
+ # GOAT-70B-Storytelling model
15
+ GOAT-70B-Storytelling model trained by GOAT.AI lab as a core model for an autonomous story-writing agent.
16
+
17
+ # GOAT-Storytelling-Agent
18
+ This agent facilitates the generation of high-quality, cohesive, and captivating narratives, including stories and books. It achieves this by utilizing inputs such as plot outlines, character profiles, their interrelationships, and other relevant details. Examples are provided below.
19
+
20
+ # Model description
21
+ - **Base Architecture:** LLaMA 2 70B
22
+ - **License:** llama2
23
+ - **Context window length:** 4096 tokens
24
+
25
+ ### Training details
26
+ Training was performed on a GPU cluster of 64xH100s. FSDP ZeRO-3 sharding is employed for efficient training. We instruction finetune on a dataset of 18K examples for one epoch with batch size of 336, AdamW optimizer with learning rate 1e-5.
27
+
28
+ ### Learn more
29
+ - **Blogpost:** [GOAT-Storytelling: Arbitrarily Long Story Writing Agent](https://www.blog.goat.ai/goat-st/)
30
+ - **GitHub:** [here](https://github.com/GOAT-AI-lab/GOAT-Storytelling-Agent)
31
+ - **Generated examples:** [here](https://huggingface.co/datasets/GOAT-AI/generated-novels/tree/main/generated-books)
32
+
33
+ ## Uses
34
+ The main purpose of GOAT-70B-Storytelling is to generate books, novels, movie scripts and etc. as an agent in coping with our GOAT-Storytelling-Agent. It is specifically designed for storywriters.
35
+
36
+ ## Usage
37
+ Usage can be either self-hosted via `transformers` or used with Spaces
38
+
39
+ ```python
40
+ import torch
41
+
42
+ from transformers import AutoTokenizer, AutoModelForCausalLM
43
+
44
+ model_name = "GOAT-AI/GOAT-70B-Storytelling"
45
+
46
+ tokenizer = AutoTokenizer.from_pretrained(model_name)
47
+ model = AutoModelForCausalLM.from_pretrained(
48
+ model_name,
49
+ torch_dtype=torch.bfloat16
50
+ )
51
+ ```
52
+ Currently, we support LLM endpoint generation, where you need to send a post request to the generation endpoint (we recommend using Text Generation Inference by HuggingFace)
53
+
54
+ First, modify `config.py` and add your generation endpoint.
55
+
56
+ Then you can use it inside via GOAT-Storytelling-Agent:
57
+
58
+ ```python
59
+ from goat_storytelling_agent import storytelling_agent as goat
60
+
61
+ novel_scenes = goat.generate_story('treasure hunt in a jungle', form='novel')
62
+ ```
63
+
64
+ ## License
65
+ GOAT-70B-Storytelling model is based on [Meta's LLaMA-2-70b-hf](https://huggingface.co/meta-llama/Llama-2-70b-hf), and using own datasets.
66
+
67
+ GOAT-70B-Storytelling model weights are available under LLAMA-2 license.
68
+
69
+ ### Risks and Biases
70
+ GOAT-70B-Storytelling model can produce factually incorrect output and should not be relied on to deliver factually accurate information. Therefore, the GOAT-70B-Storytelling model could possibly generate wrong, biased, or otherwise offensive outputs.
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/data1/models/tolkien/v0_0_5",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.34.1",
25
+ "use_cache": true,
26
+ "vocab_size": 32000
27
+ }
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": "4.34.1"
10
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/GOAT-AI/GOAT-70B-Storytelling
2
+ branch: main
3
+ download date: 2023-11-19 14:04:35
4
+ sha256sum:
5
+ cff84a14ff786f2c79269a7d46c062cd2006f608f8a4e8a6dd643a6609425d5a pytorch_model-00001-of-00015.bin
6
+ 0bff6a7714e539971818b882ca28fc4e69f60cede78739ecad476f4b773c0422 pytorch_model-00002-of-00015.bin
7
+ 897b9454e30a7f6cd1f4388781063e046e74c9e908af127fbb0140a604d48382 pytorch_model-00003-of-00015.bin
8
+ b720d8745cf66c2c4b3df39b50162a982ec32d96f6bf29be770c31a40a0fdba6 pytorch_model-00004-of-00015.bin
9
+ 232b871c353ec429bc33ca3173b007340233768aa139d318c9ee1b13b3a13a7a pytorch_model-00005-of-00015.bin
10
+ 6c924ccaaf46debdd89b97026b9f5d864ed381c7e3f34b37ed4d20c700a7498e pytorch_model-00006-of-00015.bin
11
+ 467171f02f26e51bdce98c342b533155b646bde1bad3b17c811c804d260b4ea3 pytorch_model-00007-of-00015.bin
12
+ 230d32f9b5464ae919a8b319a25ba22c5580998250cdb6b2df589508d7ca45c3 pytorch_model-00008-of-00015.bin
13
+ 3132cf8f97a39c190b5ee3896fb17eebe5b0828293431249377bd0db5ac341e9 pytorch_model-00009-of-00015.bin
14
+ dc5b095277185a6b2159843a5cb2da83daf8abbefb33b8bbb83ea821939ed5a0 pytorch_model-00010-of-00015.bin
15
+ 1184c60c93fee2653129565b51aae09dbc898ff3bee96c5755f217d4e57d3601 pytorch_model-00011-of-00015.bin
16
+ 98e3be7c2b172aeab89990ed21e6e5e9452f1a0bc8a7f196119aa9cb5847c54b pytorch_model-00012-of-00015.bin
17
+ 562e25c93f4cdb86920fe45c096a3f606ef1ce811fad2ad18aa5e0cc3ce81c6c pytorch_model-00013-of-00015.bin
18
+ 9c0f9674c7708f8e6eb43578087f5aca3471604fb7944ba3da86ba60b69540dc pytorch_model-00014-of-00015.bin
19
+ b188ed0447c698e53942e85d031909fad27e1496d825ebf05ddeca3587680c80 pytorch_model-00015-of-00015.bin
20
+ 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
output-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f462241bf577fd65fc08d9bfc0b774ab353bf9a2d35ec37d87ef9ed846c6924c
3
+ size 8588117472
output-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d00cfaa76558837ac3220feb9317b94b7d4f0d9c95e083166e91191c1c8e920
3
+ size 8551303744
output-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:580a7a1328ca2ae165a1b8ee3e6108f4cddabc5e9ec9862286bcd1f785a3a9a3
3
+ size 8546144280
output-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54fdadef890316f8f7283396c0bd0bf05f47099a30eb0a34e11e94beea6a3d26
3
+ size 8589898576
output-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c4c71a00e3481f9b546c819036ac6e812f6b86b8d1a85da4478f11a3825ec17
3
+ size 8575809104
output-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df316d73cfcf937d907558b3d7ec34f90f4674262f08de526353208fa874e30
3
+ size 8579564320
output-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ca87e1a877e84b923c41eb37f7d8e036192c4cab3bc919a80d7558571cb3826
3
+ size 670476264
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 137953296384
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00015-of-00015.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
323
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
324
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
325
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
326
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
327
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
328
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
329
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
330
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
331
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
332
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
333
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
334
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
335
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
336
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
337
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
338
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
339
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
340
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
341
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
342
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
343
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
344
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
345
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
346
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
347
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
348
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
349
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
350
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
351
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
352
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
353
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
354
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
355
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
356
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
357
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
358
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
359
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
360
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
361
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
362
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
363
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
364
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
365
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
366
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
367
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
368
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
369
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
370
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
371
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
372
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
373
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
374
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
375
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
376
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
377
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
378
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
379
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
380
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
381
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
382
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
383
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
384
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
385
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
386
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
387
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
388
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
389
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
390
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
391
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
392
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
393
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
394
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
395
+ "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
396
+ "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
397
+ "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
398
+ "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
399
+ "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
400
+ "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
401
+ "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
402
+ "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
403
+ "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
404
+ "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
405
+ "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
406
+ "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
407
+ "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
408
+ "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
409
+ "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
410
+ "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
411
+ "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
412
+ "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
413
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
414
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
415
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
416
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
417
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
418
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
419
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
420
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
421
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
422
+ "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
423
+ "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
424
+ "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
425
+ "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
426
+ "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
427
+ "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
428
+ "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
429
+ "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
430
+ "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
431
+ "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
432
+ "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
433
+ "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
434
+ "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
435
+ "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
436
+ "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
437
+ "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
438
+ "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
439
+ "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
440
+ "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
441
+ "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
442
+ "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
443
+ "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
444
+ "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
445
+ "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
446
+ "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
447
+ "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
448
+ "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
449
+ "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
450
+ "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
451
+ "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
452
+ "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
453
+ "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
454
+ "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
455
+ "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
456
+ "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
457
+ "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
458
+ "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
459
+ "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
460
+ "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
461
+ "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
462
+ "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
463
+ "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
464
+ "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
465
+ "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
466
+ "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
467
+ "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
468
+ "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
469
+ "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
470
+ "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
471
+ "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
472
+ "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
473
+ "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
474
+ "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
475
+ "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
476
+ "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
477
+ "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
478
+ "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
479
+ "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
480
+ "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
481
+ "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
482
+ "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
483
+ "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
484
+ "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
485
+ "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
486
+ "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
487
+ "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
488
+ "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
489
+ "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
490
+ "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
491
+ "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
492
+ "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
493
+ "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
494
+ "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
495
+ "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
496
+ "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
497
+ "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
498
+ "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
499
+ "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
500
+ "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
501
+ "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
502
+ "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
503
+ "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
504
+ "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
505
+ "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
506
+ "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
507
+ "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
508
+ "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
509
+ "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
510
+ "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
511
+ "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
512
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
513
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
514
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
515
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
516
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
517
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
518
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
519
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
520
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
521
+ "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
522
+ "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
523
+ "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
524
+ "model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
525
+ "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
526
+ "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
527
+ "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
528
+ "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
529
+ "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
530
+ "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
531
+ "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
532
+ "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
533
+ "model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
534
+ "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
535
+ "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
536
+ "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
537
+ "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
538
+ "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
539
+ "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
540
+ "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
541
+ "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
542
+ "model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
543
+ "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
544
+ "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
545
+ "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
546
+ "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
547
+ "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
548
+ "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
549
+ "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
550
+ "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
551
+ "model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
552
+ "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
553
+ "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
554
+ "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
555
+ "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
556
+ "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
557
+ "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
558
+ "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
559
+ "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
560
+ "model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
561
+ "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
562
+ "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
563
+ "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
564
+ "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
565
+ "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
566
+ "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
567
+ "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
568
+ "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
569
+ "model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
570
+ "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
571
+ "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
572
+ "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
573
+ "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
574
+ "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
575
+ "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
576
+ "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
577
+ "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
578
+ "model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
579
+ "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
580
+ "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
581
+ "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
582
+ "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
583
+ "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
584
+ "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
585
+ "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
586
+ "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
587
+ "model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
588
+ "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
589
+ "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
590
+ "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
591
+ "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
592
+ "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
593
+ "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
594
+ "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
595
+ "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
596
+ "model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
597
+ "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
598
+ "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
599
+ "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
600
+ "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
601
+ "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
602
+ "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
603
+ "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
604
+ "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
605
+ "model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
606
+ "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
607
+ "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
608
+ "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
609
+ "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
610
+ "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
611
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
612
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
613
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
614
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
615
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
616
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
617
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
618
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
619
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
620
+ "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
621
+ "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
622
+ "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
623
+ "model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
624
+ "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
625
+ "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
626
+ "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
627
+ "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
628
+ "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
629
+ "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
630
+ "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
631
+ "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
632
+ "model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
633
+ "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
634
+ "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
635
+ "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
636
+ "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
637
+ "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
638
+ "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
639
+ "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
640
+ "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
641
+ "model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
642
+ "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
643
+ "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
644
+ "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
645
+ "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
646
+ "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
647
+ "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
648
+ "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
649
+ "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
650
+ "model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
651
+ "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
652
+ "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
653
+ "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
654
+ "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
655
+ "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
656
+ "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
657
+ "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
658
+ "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
659
+ "model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
660
+ "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
661
+ "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
662
+ "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
663
+ "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
664
+ "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
665
+ "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
666
+ "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
667
+ "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
668
+ "model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
669
+ "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
670
+ "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
671
+ "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
672
+ "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
673
+ "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
674
+ "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
675
+ "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
676
+ "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
677
+ "model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
678
+ "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
679
+ "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
680
+ "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
681
+ "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
682
+ "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
683
+ "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
684
+ "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
685
+ "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
686
+ "model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
687
+ "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
688
+ "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
689
+ "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
690
+ "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
691
+ "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
692
+ "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
693
+ "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
694
+ "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
695
+ "model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
696
+ "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
697
+ "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
698
+ "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
699
+ "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
700
+ "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
701
+ "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
702
+ "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
703
+ "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
704
+ "model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
705
+ "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
706
+ "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
707
+ "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
708
+ "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
709
+ "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
710
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
711
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
712
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
713
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
714
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
715
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
716
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
717
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
718
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
719
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
720
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
721
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
722
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
723
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
724
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
725
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
726
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
727
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
728
+ "model.norm.weight": "pytorch_model-00014-of-00015.bin"
729
+ }
730
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "legacy": false,
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": null,
34
+ "padding_side": "right",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }