Upload folder using huggingface_hub
Browse files- README.md +119 -0
- config.json +33 -0
- mergekit_moe_config.yml +65 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- frankenmoe
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
10 |
+
- vihangd/DopeyTinyLlama-1.1B-v1
|
11 |
+
- cognitivecomputations/TinyDolphin-2.8.1-1.1b
|
12 |
+
- Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
|
13 |
+
base_model:
|
14 |
+
- TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
15 |
+
- vihangd/DopeyTinyLlama-1.1B-v1
|
16 |
+
- cognitivecomputations/TinyDolphin-2.8.1-1.1b
|
17 |
+
- Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
|
18 |
+
---
|
19 |
+
|
20 |
+
# UltraCompute-7B-Base
|
21 |
+
|
22 |
+
UltraCompute-7B-Base is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
23 |
+
* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
|
24 |
+
* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
|
25 |
+
* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
|
26 |
+
* [Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test](https://huggingface.co/Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test)
|
27 |
+
|
28 |
+
## 🧩 Configuration
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
32 |
+
gate_mode: hidden
|
33 |
+
dtype: float16
|
34 |
+
experts:
|
35 |
+
- source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
36 |
+
positive_prompts:
|
37 |
+
- "Help me debug this code."
|
38 |
+
- "Rewrite this function in Python."
|
39 |
+
- "Optimize this C# script."
|
40 |
+
- "Implement this feature using JavaScript."
|
41 |
+
- "Convert this HTML structure into a more efficient design."
|
42 |
+
- "Assist me with writing a program that"
|
43 |
+
- source_model: vihangd/DopeyTinyLlama-1.1B-v1
|
44 |
+
positive_prompts:
|
45 |
+
- "How do you"
|
46 |
+
- "Explain the concept of"
|
47 |
+
- "Give an overview of"
|
48 |
+
- "Compare and contrast between"
|
49 |
+
- "Provide information about"
|
50 |
+
- "Help me understand"
|
51 |
+
- "Summarize"
|
52 |
+
- "Make a recommendation on"
|
53 |
+
- "Answer this question"
|
54 |
+
- source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
|
55 |
+
positive_prompts:
|
56 |
+
- "Write a program to solve this problem"
|
57 |
+
- "Modify this function to improve its performance"
|
58 |
+
- "Refactor this code to enhance readability"
|
59 |
+
- "Create a custom function for this specific use case"
|
60 |
+
- "Optimize this algorithm to reduce computational complexity"
|
61 |
+
- "Implement this feature by extending existing codebase"
|
62 |
+
- "Integrate this API call into the application"
|
63 |
+
- "Help me troubleshoot and fix this bug"
|
64 |
+
- "Review and test this code snippet before deployment"
|
65 |
+
- "Analyze this error log to identify potential issues"
|
66 |
+
- "Generate a set of unit tests for this module"
|
67 |
+
- "Evaluate different approaches to solving this problem"
|
68 |
+
- "Do a web search for"
|
69 |
+
- "Use the plugin to"
|
70 |
+
- source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
|
71 |
+
positive_prompts:
|
72 |
+
- "add these numbers"
|
73 |
+
- "whats 2+2"
|
74 |
+
- "subtraction"
|
75 |
+
- "division"
|
76 |
+
- "multiplication"
|
77 |
+
- "addition"
|
78 |
+
- "I need help with a math problem"
|
79 |
+
- "Solve for x"
|
80 |
+
- "Add these two numbers together: 4 + 3 = 7"
|
81 |
+
- "Multiply 5 by 6: 5 * 6 = 30"
|
82 |
+
- "Divide 8 by 2: 8 / 2 = 4"
|
83 |
+
- "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
|
84 |
+
- "Calculate the square root of 16: sqrt(16) = 4"
|
85 |
+
- "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
|
86 |
+
- "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
|
87 |
+
- "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
|
88 |
+
- "Graph the line y = 2x + 3"
|
89 |
+
- "Approximate pi to three decimal places: 3.142"
|
90 |
+
- "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
|
91 |
+
- "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
|
92 |
+
- "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
|
93 |
+
- "Solve the system of equations Ax = b: x = [-5, 10]"
|
94 |
+
- "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
|
95 |
+
```
|
96 |
+
|
97 |
+
## 💻 Usage
|
98 |
+
|
99 |
+
```python
|
100 |
+
!pip install -qU transformers bitsandbytes accelerate
|
101 |
+
|
102 |
+
from transformers import AutoTokenizer
|
103 |
+
import transformers
|
104 |
+
import torch
|
105 |
+
|
106 |
+
model = "gmonsoon/UltraCompute-7B-Base"
|
107 |
+
|
108 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
109 |
+
pipeline = transformers.pipeline(
|
110 |
+
"text-generation",
|
111 |
+
model=model,
|
112 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
113 |
+
)
|
114 |
+
|
115 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
116 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
117 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
118 |
+
print(outputs[0]["generated_text"])
|
119 |
+
```
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 22,
|
19 |
+
"num_key_value_heads": 4,
|
20 |
+
"num_local_experts": 4,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"router_aux_loss_coef": 0.001,
|
27 |
+
"sliding_window": null,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float16",
|
30 |
+
"transformers_version": "4.37.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 32000
|
33 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
3 |
+
gate_mode: hidden
|
4 |
+
dtype: float16
|
5 |
+
experts:
|
6 |
+
- source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
|
7 |
+
positive_prompts:
|
8 |
+
- "Help me debug this code."
|
9 |
+
- "Rewrite this function in Python."
|
10 |
+
- "Optimize this C# script."
|
11 |
+
- "Implement this feature using JavaScript."
|
12 |
+
- "Convert this HTML structure into a more efficient design."
|
13 |
+
- "Assist me with writing a program that"
|
14 |
+
- source_model: vihangd/DopeyTinyLlama-1.1B-v1
|
15 |
+
positive_prompts:
|
16 |
+
- "How do you"
|
17 |
+
- "Explain the concept of"
|
18 |
+
- "Give an overview of"
|
19 |
+
- "Compare and contrast between"
|
20 |
+
- "Provide information about"
|
21 |
+
- "Help me understand"
|
22 |
+
- "Summarize"
|
23 |
+
- "Make a recommendation on"
|
24 |
+
- "Answer this question"
|
25 |
+
- source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
|
26 |
+
positive_prompts:
|
27 |
+
- "Write a program to solve this problem"
|
28 |
+
- "Modify this function to improve its performance"
|
29 |
+
- "Refactor this code to enhance readability"
|
30 |
+
- "Create a custom function for this specific use case"
|
31 |
+
- "Optimize this algorithm to reduce computational complexity"
|
32 |
+
- "Implement this feature by extending existing codebase"
|
33 |
+
- "Integrate this API call into the application"
|
34 |
+
- "Help me troubleshoot and fix this bug"
|
35 |
+
- "Review and test this code snippet before deployment"
|
36 |
+
- "Analyze this error log to identify potential issues"
|
37 |
+
- "Generate a set of unit tests for this module"
|
38 |
+
- "Evaluate different approaches to solving this problem"
|
39 |
+
- "Do a web search for"
|
40 |
+
- "Use the plugin to"
|
41 |
+
- source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
|
42 |
+
positive_prompts:
|
43 |
+
- "add these numbers"
|
44 |
+
- "whats 2+2"
|
45 |
+
- "subtraction"
|
46 |
+
- "division"
|
47 |
+
- "multiplication"
|
48 |
+
- "addition"
|
49 |
+
- "I need help with a math problem"
|
50 |
+
- "Solve for x"
|
51 |
+
- "Add these two numbers together: 4 + 3 = 7"
|
52 |
+
- "Multiply 5 by 6: 5 * 6 = 30"
|
53 |
+
- "Divide 8 by 2: 8 / 2 = 4"
|
54 |
+
- "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
|
55 |
+
- "Calculate the square root of 16: sqrt(16) = 4"
|
56 |
+
- "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
|
57 |
+
- "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
|
58 |
+
- "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
|
59 |
+
- "Graph the line y = 2x + 3"
|
60 |
+
- "Approximate pi to three decimal places: 3.142"
|
61 |
+
- "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
|
62 |
+
- "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
|
63 |
+
- "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
|
64 |
+
- "Solve the system of equations Ax = b: x = [-5, 10]"
|
65 |
+
- "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d38f31ef61bf68f90303925662e940e7aaa1c0fd144c96c7549865c9790d1c1
|
3 |
+
size 1992400992
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2045a530438abd30ab4c899bca713086bc48e5e66b28e81f1533826b68e6da8
|
3 |
+
size 1983916872
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a3e4dbec96346b449a29529514bda3ba68c6c1988ef0a56d1018a44cd77eca4
|
3 |
+
size 1983916872
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd9b26580bb02a40ab88a2d3ca7d4a58c4b2225a47db42246d31e4e58c7248e6
|
3 |
+
size 807871392
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.norm.weight": "model-00001-of-00004.safetensors", "lm_head.weight": "model-00001-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00004.safetensors", "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00004-of-00004.safetensors"}}
|
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": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 2048,
|
36 |
+
"pad_token": "<s>",
|
37 |
+
"padding_side": "left",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|