omitakahiro commited on
Commit
28fbcd2
0 Parent(s):

initial commit

Browse files
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc
3
+ language:
4
+ - ja
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
+ tags:
8
+ - japanese
9
+ - llama-2
10
+ - instruction-tuning
11
+ ---
12
+
13
+ # Stockmark-13b-instruct
14
+
15
+ Stockmark-13b-instruct is a instruction-tuned version of [Stockmark-13b](https://huggingface.co/stockmark/stockmark-13b), a 13 billion parameter Japanese LLM. This model is developed by [Stockmark Inc.](https://stockmark.co.jp/)
16
+
17
+ We used data (2023/11/03 version) from [Project of Development of Japanese Instruction data for LLM](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/) for instruction tuning.
18
+
19
+ This model is licensed under non-commercial license.
20
+
21
+ Please see our [blog](https://tech.stockmark.co.jp/blog/202311_stockmark_13b_instruct/) for more details.
22
+
23
+ ## How to use
24
+
25
+ ```python
26
+ import torch
27
+ from transformers import AutoModelForCausalLM, AutoTokenizer
28
+
29
+ model = AutoModelForCausalLM.from_pretrained("stockmark/stockmark-13b-instruct", device_map="auto", torch_dtype=torch.bfloat16)
30
+ tokenizer = AutoTokenizer.from_pretrained("stockmark/stockmark-13b-instruct")
31
+
32
+ instruction = "自然言語処理とは?"
33
+
34
+ prompt = f"""### Input:
35
+ {instruction}
36
+
37
+ ### Output:
38
+ """
39
+
40
+ inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
41
+ with torch.no_grad():
42
+ tokens = model.generate(
43
+ **inputs,
44
+ max_new_tokens=128,
45
+ do_sample=True,
46
+ temperature=0.7
47
+ )
48
+
49
+ output = tokenizer.decode(tokens[0], skip_special_tokens=True)
50
+ print(output)
51
+ ```
52
+
53
+ ## Training dataset
54
+ [Project of Development of Japanese Instruction data for LLM](https://liat-aip.sakura.ne.jp/wp/llm%E3%81%AE%E3%81%9F%E3%82%81%E3%81%AE%E6%97%A5%E6%9C%AC%E8%AA%9E%E3%82%A4%E3%83%B3%E3%82%B9%E3%83%88%E3%83%A9%E3%82%AF%E3%82%B7%E3%83%A7%E3%83%B3%E3%83%87%E3%83%BC%E3%82%BF%E4%BD%9C%E6%88%90/)
55
+
56
+ ## License
57
+ [CC BY-NC-SA](https://creativecommons.org/licenses/by-nc-sa/4.0/)
58
+
59
+ ## Developed by
60
+ [Stockmark Inc.](https://stockmark.co.jp/)
61
+
62
+ ## Author
63
+ [Takahiro Omi](https://huggingface.co/omitakahiro)
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stockmark/stockmark-13b-instruction",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 1,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "max_position_embeddings": 2048,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 40,
17
+ "num_key_value_heads": 40,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.34.1",
25
+ "use_cache": true,
26
+ "vocab_size": 50000
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 2,
5
+ "transformers_version": "4.34.1"
6
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447d0f26c73abc6d53717da1d6375432e8d5df575ef73b0f2290444b8497eda2
3
+ size 9886571608
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c533ae83bea0321785ddcde3f116d85a6ee9be0758b3865fc3a95278fae90ef2
3
+ size 9867444424
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6339dd8d676e072582089f0700d75fe629673f706a316ba43b4490558e10bd0
3
+ size 6646394880
model.safetensors.index.json ADDED
@@ -0,0 +1,370 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26400368640
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
323
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
324
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
325
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
326
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
327
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
328
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
329
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
330
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
331
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
332
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
333
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
334
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
335
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
336
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
337
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
338
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
339
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
340
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
341
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
342
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
343
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
344
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
345
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
346
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
347
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
348
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
349
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
350
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
351
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
352
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
353
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
354
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
355
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
356
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
357
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
358
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
359
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
360
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
361
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
362
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
363
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
364
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
365
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
366
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
367
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
368
+ "model.norm.weight": "model-00003-of-00003.safetensors"
369
+ }
370
+ }
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": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": false,
4
+ "eos_token": "</s>",
5
+ "model_max_length": 1000000000000000019884624838656,
6
+ "pad_token": "<pad>",
7
+ "padding_side": "right",
8
+ "tokenizer_class": "LlamaTokenizer",
9
+ "unk_token": "<unk>",
10
+ "use_default_system_prompt": true
11
+ }