Hugging Face's logo

Magpie-Align
/
MagpieLM-8B-SFT-v0.1

Text Generation
Transformers
PyTorch
Safetensors
llama
axolotl
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
Zhangchen Xu commited on
Commit
de82fb5
·
verified ·
1 Parent(s): 5a9b52a

End of training

Browse files
Files changed (7) hide show
  1. README.md +154 -0
  2. generation_config.json +9 -0
  3. pytorch_model-00001-of-00004.bin +3 -0
  4. pytorch_model-00002-of-00004.bin +3 -0
  5. pytorch_model-00003-of-00004.bin +3 -0
  6. pytorch_model-00004-of-00004.bin +3 -0
  7. pytorch_model.bin.index.json +298 -0
README.md ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Meta-Llama-3.1-8B
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: Llama-3.1-8B-Magpie-SFT-GMix-550K
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+
22
+ base_model: meta-llama/Meta-Llama-3.1-8B
23
+ model_type: LlamaForCausalLM
24
+ tokenizer_type: AutoTokenizer
25
+ chat_template: llama3
26
+
27
+ load_in_8bit: false
28
+ load_in_4bit: false
29
+ strict: false
30
+ main_process_port: 0
31
+
32
+ datasets:
33
+ - path: flydust/Magpie-Llama-3-70B-300K-Gemma2-9B
34
+ type: sharegpt
35
+ conversation: llama3
36
+ - path: flydust/Magpie-Reasoning-150K-Gemma2-9B
37
+ type: sharegpt
38
+ conversation: llama3
39
+ - path: flydust/Magpie-100k-Gemma2-9B
40
+ type: sharegpt
41
+ conversation: llama3
42
+ dataset_prepared_path: /data/zhangchen_xu/last_run_prepared
43
+ val_set_size: 0.001
44
+ output_dir: /data/zhangchen_xu/axolotl_out/Llama-3.1-8B-SFT-GMix-550K
45
+
46
+ sequence_len: 8192
47
+ sample_packing: true
48
+ eval_sample_packing: false
49
+ pad_to_sequence_len: true
50
+
51
+ wandb_project: SynDa
52
+ wandb_entity:
53
+ wandb_watch:
54
+ wandb_name: Llama-3.1-8B-Mix-SFT-GMix-550K
55
+ wandb_log_model:
56
+ hub_model_id: Magpie-Align/Llama-3.1-8B-Magpie-SFT-GMix-550K
57
+
58
+ gradient_accumulation_steps: 32
59
+ micro_batch_size: 1
60
+ num_epochs: 2
61
+ optimizer: paged_adamw_8bit
62
+ lr_scheduler: cosine
63
+ learning_rate: 2e-5
64
+
65
+ train_on_inputs: false
66
+ group_by_length: false
67
+ bf16: auto
68
+ fp16:
69
+ tf32: false
70
+
71
+ gradient_checkpointing: true
72
+ gradient_checkpointing_kwargs:
73
+ use_reentrant: false
74
+ early_stopping_patience:
75
+ resume_from_checkpoint:
76
+ logging_steps: 1
77
+ xformers_attention:
78
+ flash_attention: true
79
+
80
+ warmup_ratio: 0.1
81
+ evals_per_epoch: 5
82
+ eval_table_size:
83
+ saves_per_epoch:
84
+ debug:
85
+ deepspeed:
86
+ weight_decay: 0.0
87
+ fsdp:
88
+ fsdp_config:
89
+ special_tokens:
90
+ pad_token: <|end_of_text|>
91
+
92
+ ```
93
+
94
+ </details><br>
95
+
96
+ # Llama-3.1-8B-Magpie-SFT-GMix-550K
97
+
98
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the None dataset.
99
+ It achieves the following results on the evaluation set:
100
+ - Loss: 0.4544
101
+
102
+ ## Model description
103
+
104
+ More information needed
105
+
106
+ ## Intended uses & limitations
107
+
108
+ More information needed
109
+
110
+ ## Training and evaluation data
111
+
112
+ More information needed
113
+
114
+ ## Training procedure
115
+
116
+ ### Training hyperparameters
117
+
118
+ The following hyperparameters were used during training:
119
+ - learning_rate: 2e-05
120
+ - train_batch_size: 1
121
+ - eval_batch_size: 1
122
+ - seed: 42
123
+ - distributed_type: multi-GPU
124
+ - num_devices: 4
125
+ - gradient_accumulation_steps: 32
126
+ - total_train_batch_size: 128
127
+ - total_eval_batch_size: 4
128
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
129
+ - lr_scheduler_type: cosine
130
+ - lr_scheduler_warmup_steps: 51
131
+ - num_epochs: 2
132
+
133
+ ### Training results
134
+
135
+ | Training Loss | Epoch | Step | Validation Loss |
136
+ |:-------------:|:------:|:----:|:---------------:|
137
+ | 0.9311 | 0.0038 | 1 | 0.9847 |
138
+ | 0.561 | 0.2015 | 53 | 0.5765 |
139
+ | 0.4843 | 0.4030 | 106 | 0.5039 |
140
+ | 0.4608 | 0.6045 | 159 | 0.4814 |
141
+ | 0.4454 | 0.8060 | 212 | 0.4678 |
142
+ | 0.4403 | 1.0075 | 265 | 0.4596 |
143
+ | 0.3965 | 1.1938 | 318 | 0.4574 |
144
+ | 0.3952 | 1.3953 | 371 | 0.4554 |
145
+ | 0.3962 | 1.5968 | 424 | 0.4547 |
146
+ | 0.3948 | 1.7983 | 477 | 0.4544 |
147
+
148
+
149
+ ### Framework versions
150
+
151
+ - Transformers 4.45.0.dev0
152
+ - Pytorch 2.3.0+cu121
153
+ - Datasets 2.19.1
154
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.45.0.dev0"
9
+ }
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91f0b270dd6e3c6ff4eaa32250f99cd3c4465ca49dc9474c552d3cd3d10acbc6
3
+ size 4976718466
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4e9de5afda4e23c562d35cc9aee610e631bf40644de8cd81fe97985a4a1efc
3
+ size 4999827718
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ea5e756a8c2b9b9e2955b0a839520fd9627b82936f90edfab0b183f9645e465
3
+ size 4915940170
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0c1c3b5f27baa18880a0e40b16ee14c6fb4241f867a3cf599b945c817a1bf0a
3
+ size 1168140873
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00004-of-00004.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
296
+ "model.norm.weight": "pytorch_model-00004-of-00004.bin"
297
+ }
298
+ }