ancient-ancient commited on
Commit
e67e188
1 Parent(s): 2799b8e

initial commit

Browse files
README.md ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: llama2
3
+ ---
4
+
5
+
6
+ ## WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct (RLEIF)
7
+
8
+
9
+ <p align="center">
10
+ 🤗 <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
11
+ </p>
12
+ <p align="center">
13
+ 👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
14
+ </p>
15
+
16
+ | Model | Checkpoint | Paper | HumanEval | MBPP | Demo | License |
17
+ | ----- |------| ---- |------|-------| ----- | ----- |
18
+ | WizardCoder-Python-34B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 73.2 | 61.2 | [Demo](http://47.103.63.15:50085/) | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
19
+ | WizardCoder-15B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-15B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 59.8 |50.6 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
20
+ | WizardCoder-Python-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 64.0 | 55.6 | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
21
+ | WizardCoder-Python-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 55.5 | 51.6 | [Demo](http://47.103.63.15:50088/) | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
22
+ | WizardCoder-3B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-3B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 34.8 |37.4 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
23
+ | WizardCoder-1B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-1B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 23.8 |28.6 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
24
+
25
+
26
+ | Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|
27
+ | ----- |------| ---- |------|-------| ----- | ----- |
28
+ | WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
29
+ | WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
30
+ | WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
31
+
32
+
33
+
34
+ <font size=4>
35
+
36
+ | <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>GSM8k</sup> | <sup>HumanEval</sup> | <sup>License</sup>|
37
+ | ----- |------| ---- |------|-------| ----- | ----- | ----- |
38
+ | <sup>**WizardLM-70B-V1.0**</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-70B-V1.0" target="_blank">HF Link</a> </sup>|<sup>📃**Coming Soon**</sup>| <sup>**7.78**</sup> | <sup>**92.91%**</sup> |<sup>**77.6%**</sup> | <sup> **50.6 pass@1**</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
39
+ | <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a> </sup>| | <sup>7.06</sup> | <sup>89.17%</sup> |<sup>55.3%</sup> | <sup>36.6 pass@1</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
40
+ | <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup> | | <sup>25.0 pass@1</sup>| <sup>Non-commercial</sup>|
41
+ | <sup>WizardLM-30B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-30B-V1.0" target="_blank">HF Link</a></sup> | | <sup>7.01</sup> | | | <sup>37.8 pass@1</sup>| <sup>Non-commercial</sup> |
42
+ | <sup>WizardLM-13B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.0" target="_blank">HF Link</a> </sup> | | <sup>6.35</sup> | <sup>75.31%</sup> | | <sup> 24.0 pass@1 </sup> | <sup>Non-commercial</sup>|
43
+ | <sup>WizardLM-7B-V1.0 </sup>| <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-7B-V1.0" target="_blank">HF Link</a> </sup> |<sup> 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> </sup>| | | |<sup>19.1 pass@1 </sup>|<sup> Non-commercial</sup>|
44
+ </font>
45
+
46
+ **Github Repo**: https://github.com/nlpxucan/WizardLM/tree/main/WizardMath
47
+
48
+ **Twitter**: https://twitter.com/WizardLM_AI/status/1689998428200112128
49
+
50
+ **Discord**: https://discord.gg/VZjjHtWrKs
51
+
52
+ ## Comparing WizardMath-V1.0 with Other LLMs.
53
+
54
+ 🔥 The following figure shows that our **WizardMath-70B-V1.0 attains the fifth position in this benchmark**, surpassing ChatGPT (81.6 vs. 80.8) , Claude Instant (81.6 vs. 80.9), PaLM 2 540B (81.6 vs. 80.7).
55
+
56
+ <p align="center" width="100%">
57
+ <a ><img src="https://raw.githubusercontent.com/nlpxucan/WizardLM/main/WizardMath/images/wizardmath_gsm8k.png" alt="WizardMath" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
58
+ </p>
59
+
60
+ ❗<b>Note for model system prompts usage:</b>
61
+
62
+ Please use **the same systems prompts strictly** with us, and we do not guarantee the accuracy of the **quantified versions**.
63
+
64
+ **Default version:**
65
+
66
+ ```
67
+ "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
68
+ ```
69
+
70
+
71
+ **CoT Version:** (❗For the **simple** math questions, we do NOT recommend to use the CoT prompt.)
72
+
73
+
74
+ ```
75
+ "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."
76
+ ```
77
+
78
+ ## Inference WizardMath Demo Script
79
+
80
+ We provide the WizardMath inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).
81
+
82
+
83
+ ❗<b>To commen concern about dataset:</b>
84
+
85
+ Recently, there have been clear changes in the open-source policy and regulations of our overall organization's code, data, and models.
86
+ Despite this, we have still worked hard to obtain opening the weights of the model first, but the data involves stricter auditing and is in review with our legal team .
87
+ Our researchers have no authority to publicly release them without authorization.
88
+ Thank you for your understanding.
89
+
90
+
91
+ ## Citation
92
+
93
+ Please cite the repo if you use the data, method or code in this repo.
94
+
95
+ ```
96
+ @article{luo2023wizardmath,
97
+ title={WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct},
98
+ author={Luo, Haipeng and Sun, Qingfeng and Xu, Can and Zhao, Pu and Lou, Jianguang and Tao, Chongyang and Geng, Xiubo and Lin, Qingwei and Chen, Shifeng and Zhang, Dongmei},
99
+ journal={arXiv preprint arXiv:2308.09583},
100
+ year={2023}
101
+ }
102
+ ```
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/model_weights/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 13824,
12
+ "max_position_embeddings": 4096,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 40,
15
+ "num_hidden_layers": 40,
16
+ "num_key_value_heads": 40,
17
+ "pad_token_id": 0,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.31.0",
24
+ "use_cache": false,
25
+ "vocab_size": 32001
26
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "eos_token_id": 2,
4
+ "max_length": 4096,
5
+ "pad_token_id": 0,
6
+ "temperature": 0.9,
7
+ "top_p": 0.6,
8
+ "transformers_version": "4.31.0"
9
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c562e7300e8c50d0ca2ccea54dc89366cdfc5c313142b30c6bd0a4534bae2e72
3
+ size 9956564363
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e964964518563b9f31bd929f6b8184c0bb8d72a5f4d06598146e19ca893b62c
3
+ size 9940856385
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:783df5970529a252be871daf32e36bc1bda5a747340c58671b7ab7ace4660c3c
3
+ size 9940856943
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65f00ab47e363bdc9daf5b8a6336fcc8a91dc95d22ea26aa5f6118d01f3e3481
3
+ size 9867415289
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aa3129356acb97560d5799d50d7d2735bcb7874fdb3e500ca74419dd94e0657
3
+ size 9867456961
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18089fb3ed51f02b4cc9da2da894321112fcebd27f61e6f574317f6623b02d6f
3
+ size 2490496687
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,410 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 52063508480
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
268
+ "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
269
+ "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
270
+ "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
271
+ "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
272
+ "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
273
+ "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
274
+ "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
275
+ "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
276
+ "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
277
+ "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
278
+ "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
279
+ "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
280
+ "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
281
+ "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
282
+ "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
283
+ "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
284
+ "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
285
+ "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
286
+ "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
287
+ "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
288
+ "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
289
+ "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
290
+ "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
291
+ "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
292
+ "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
293
+ "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
294
+ "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
295
+ "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
296
+ "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
297
+ "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
298
+ "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
299
+ "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
300
+ "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
301
+ "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
302
+ "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
303
+ "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
304
+ "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
305
+ "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
306
+ "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
307
+ "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
308
+ "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
309
+ "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
310
+ "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
311
+ "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
312
+ "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
313
+ "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
314
+ "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
315
+ "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
316
+ "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
317
+ "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
318
+ "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
319
+ "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
320
+ "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
321
+ "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
322
+ "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
323
+ "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
324
+ "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
325
+ "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
326
+ "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
327
+ "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
328
+ "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
329
+ "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
330
+ "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
331
+ "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
332
+ "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
333
+ "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
334
+ "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
335
+ "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
336
+ "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
337
+ "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
338
+ "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
339
+ "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
340
+ "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
341
+ "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
342
+ "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
343
+ "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
344
+ "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
345
+ "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
346
+ "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
347
+ "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
348
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
349
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
350
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
351
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
352
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
353
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
354
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
355
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
356
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
357
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
358
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
359
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
360
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
361
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
362
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
363
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
364
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
365
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
366
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
367
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
368
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
369
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
370
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
371
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
372
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
373
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
374
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
375
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
376
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
377
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
378
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
379
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
380
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
381
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
382
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
383
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
384
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
385
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
386
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
387
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
388
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
389
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
390
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
391
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
392
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
393
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
394
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
395
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
396
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
397
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
398
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
399
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
400
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
401
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
402
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
403
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
404
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
405
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
406
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
407
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
408
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
409
+ }
410
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "</s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "[PAD]",
5
+ "unk_token": "</s>"
6
+ }
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }