beratcmn commited on
Commit
e6b8e7b
1 Parent(s): 307ad0a

Trained with Unsloth

Browse files
README.md CHANGED
@@ -3,65 +3,14 @@ language:
3
  - en
4
  license: apache-2.0
5
  tags:
6
- - merge
7
- - mergekit
8
- - lazymergekit
9
- - meta-llama/Meta-Llama-3-8B
10
- - beratcmn/Llama-3-11.5B
11
  - text-generation-inference
12
  - transformers
13
  - unsloth
14
  - llama
15
  - trl
 
16
  base_model: beratcmn/Llama-3-11.5B
17
  ---
18
- # Llama-3-11.5B
19
-
20
- This model is a Proof of Concept. First 2 Llama-3-8B models has been merged using `Mergekit` and pre-training continued using `QLora` and `Unsloth` for 1000 samples from `roneneldan/TinyStories`.
21
- Loss still decreases each epoch so I believe this is a successful experiment where there is a lot of room to experiment.
22
-
23
- Llama-3-11.5B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
24
- * [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
25
- * [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
26
-
27
- ## 🧩 Configuration
28
-
29
- ```yaml
30
- slices:
31
- - sources:
32
- - model: meta-llama/Meta-Llama-3-8B
33
- layer_range: [0, 24]
34
- - sources:
35
- - model: meta-llama/Meta-Llama-3-8B
36
- layer_range: [8, 32]
37
- merge_method: passthrough
38
- dtype: bfloat16
39
- ```
40
-
41
- ## 💻 Usage
42
-
43
- ```python
44
- !pip install -qU transformers accelerate
45
-
46
- from transformers import AutoTokenizer
47
- import transformers
48
- import torch
49
-
50
- model = "beratcmn/Llama-3-11.5B"
51
- messages = [{"role": "user", "content": "What is a large language model?"}]
52
-
53
- tokenizer = AutoTokenizer.from_pretrained(model)
54
- prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
55
- pipeline = transformers.pipeline(
56
- "text-generation",
57
- model=model,
58
- torch_dtype=torch.float16,
59
- device_map="auto",
60
- )
61
-
62
- outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
63
- print(outputs[0]["generated_text"])
64
- ```
65
 
66
  # Uploaded model
67
 
 
3
  - en
4
  license: apache-2.0
5
  tags:
 
 
 
 
 
6
  - text-generation-inference
7
  - transformers
8
  - unsloth
9
  - llama
10
  - trl
11
+ - sft
12
  base_model: beratcmn/Llama-3-11.5B
13
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
 
15
  # Uploaded model
16
 
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "beratcmn/Llama-3-11.5B",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 8192,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 48,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 128001,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 500000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.40.0",
27
+ "unsloth_version": "2024.4",
28
+ "use_cache": true,
29
+ "vocab_size": 128256
30
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "eos_token_id": 128001,
5
+ "transformers_version": "4.40.0"
6
+ }
pytorch_model-00001-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eabdf98b46ed2e246a5d84875545ad7b88ec9ddd6ed3e60c9a1a1ebf08cf0f70
3
+ size 4976718466
pytorch_model-00002-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec2ea519a6f8d7925089542b186366a41f4724f90cdaa755704505e288a9d501
3
+ size 4999827206
pytorch_model-00003-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fbdf0495d48e220ee879089bed887eb63cdd11a94829370a95db60a1227261
3
+ size 4915939082
pytorch_model-00004-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64bb57b125808c694af95806f63769166ab50132f08838e1f8fc05365733c881
3
+ size 4999843656
pytorch_model-00005-of-00005.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6978434f5954774b95009c1a2fb6d1dab8c8af9216d9efe1fafac56e7e4f4c0a
3
+ size 3147930224
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 23040106496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00005-of-00005.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
242
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
243
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
244
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
245
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
246
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
247
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
248
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
249
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
250
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
251
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
252
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
253
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
254
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
255
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
256
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
257
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
258
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
259
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
260
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
261
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
262
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
263
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
264
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
265
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
266
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
267
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
268
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
269
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
270
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
271
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
272
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
273
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
274
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
275
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
276
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
277
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
278
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
279
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
280
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
281
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
282
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
283
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
284
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
285
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
286
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
287
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
288
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
289
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
290
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
291
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
292
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
293
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
294
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
295
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
296
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
297
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
298
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
299
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
300
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
301
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
302
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
303
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
304
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
305
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
306
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
307
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
308
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
309
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
310
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
311
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
312
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
313
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
314
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
315
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
316
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
317
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
318
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
319
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
320
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
321
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
322
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
323
+ "model.layers.40.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
324
+ "model.layers.40.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
325
+ "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
326
+ "model.layers.40.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
327
+ "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
328
+ "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
329
+ "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
330
+ "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
331
+ "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
332
+ "model.layers.41.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
333
+ "model.layers.41.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
334
+ "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
335
+ "model.layers.41.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
336
+ "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
337
+ "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
338
+ "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
339
+ "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
340
+ "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
341
+ "model.layers.42.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
342
+ "model.layers.42.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
343
+ "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
344
+ "model.layers.42.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
345
+ "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
346
+ "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
347
+ "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
348
+ "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
349
+ "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
350
+ "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
351
+ "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
352
+ "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
353
+ "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
354
+ "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
355
+ "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
356
+ "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
357
+ "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
358
+ "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
359
+ "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
360
+ "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
361
+ "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
362
+ "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
363
+ "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
364
+ "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
365
+ "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
366
+ "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
367
+ "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
368
+ "model.layers.45.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
369
+ "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
370
+ "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
371
+ "model.layers.45.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
372
+ "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
373
+ "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
374
+ "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
375
+ "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
376
+ "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
377
+ "model.layers.46.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
378
+ "model.layers.46.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
379
+ "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
380
+ "model.layers.46.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
381
+ "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
382
+ "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
383
+ "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
384
+ "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
385
+ "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
386
+ "model.layers.47.input_layernorm.weight": "pytorch_model-00005-of-00005.bin",
387
+ "model.layers.47.mlp.down_proj.weight": "pytorch_model-00005-of-00005.bin",
388
+ "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00005-of-00005.bin",
389
+ "model.layers.47.mlp.up_proj.weight": "pytorch_model-00005-of-00005.bin",
390
+ "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00005-of-00005.bin",
391
+ "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00005-of-00005.bin",
392
+ "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00005-of-00005.bin",
393
+ "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00005-of-00005.bin",
394
+ "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00005-of-00005.bin",
395
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
396
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
397
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
398
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
399
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
400
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
401
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
402
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
403
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
404
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
405
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
406
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
407
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
408
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
409
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
410
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
411
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
412
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
413
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
414
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
415
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
416
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
417
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
418
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
419
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
420
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
421
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
422
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
423
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
424
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
425
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
426
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
427
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
428
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
429
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
430
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
431
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
432
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
433
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
434
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
435
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
436
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
437
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
438
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
439
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
440
+ "model.norm.weight": "pytorch_model-00005-of-00005.bin"
441
+ }
442
+ }