add v0.7 models finetuned on Qwen14B.
Browse files- sakura_13b_model_v0.7_qwen14b/config.json +42 -0
- sakura_13b_model_v0.7_qwen14b/generation_config.json +11 -0
- sakura_13b_model_v0.7_qwen14b/pytorch_model-00001-of-00003.bin +3 -0
- sakura_13b_model_v0.7_qwen14b/pytorch_model-00002-of-00003.bin +3 -0
- sakura_13b_model_v0.7_qwen14b/pytorch_model-00003-of-00003.bin +3 -0
- sakura_13b_model_v0.7_qwen14b/pytorch_model.bin.index.json +330 -0
- sakura_13b_model_v0.7_qwen14b/qwen.tiktoken +0 -0
- sakura_13b_model_v0.7_qwen14b/special_tokens_map.json +3 -0
- sakura_13b_model_v0.7_qwen14b/tokenizer_config.json +12 -0
- sakura_13b_model_v0.7_qwen14b/trainer_state.json +0 -0
- sakura_13b_model_v0.7_qwen14b/training_args.bin +3 -0
sakura_13b_model_v0.7_qwen14b/config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen-14B-Chat",
|
3 |
+
"architectures": [
|
4 |
+
"QWenLMHeadModel"
|
5 |
+
],
|
6 |
+
"attn_dropout_prob": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "Qwen/Qwen-14B-Chat--configuration_qwen.QWenConfig",
|
9 |
+
"AutoModelForCausalLM": "Qwen/Qwen-14B-Chat--modeling_qwen.QWenLMHeadModel"
|
10 |
+
},
|
11 |
+
"bf16": true,
|
12 |
+
"emb_dropout_prob": 0.0,
|
13 |
+
"fp16": false,
|
14 |
+
"fp32": false,
|
15 |
+
"hidden_size": 5120,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 27392,
|
18 |
+
"kv_channels": 128,
|
19 |
+
"layer_norm_epsilon": 1e-06,
|
20 |
+
"max_position_embeddings": 8192,
|
21 |
+
"model_type": "qwen",
|
22 |
+
"no_bias": true,
|
23 |
+
"num_attention_heads": 40,
|
24 |
+
"num_hidden_layers": 40,
|
25 |
+
"onnx_safe": null,
|
26 |
+
"rotary_emb_base": 10000,
|
27 |
+
"rotary_pct": 1.0,
|
28 |
+
"scale_attn_weights": true,
|
29 |
+
"seq_length": 2048,
|
30 |
+
"softmax_in_fp32": false,
|
31 |
+
"tie_word_embeddings": false,
|
32 |
+
"tokenizer_class": "QWenTokenizer",
|
33 |
+
"torch_dtype": "bfloat16",
|
34 |
+
"transformers_version": "4.32.0",
|
35 |
+
"use_cache": false,
|
36 |
+
"use_cache_kernel": false,
|
37 |
+
"use_cache_quantization": false,
|
38 |
+
"use_dynamic_ntk": true,
|
39 |
+
"use_flash_attn": true,
|
40 |
+
"use_logn_attn": true,
|
41 |
+
"vocab_size": 152064
|
42 |
+
}
|
sakura_13b_model_v0.7_qwen14b/generation_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chat_format": "chatml",
|
3 |
+
"do_sample": true,
|
4 |
+
"eos_token_id": 151643,
|
5 |
+
"max_new_tokens": 512,
|
6 |
+
"max_window_size": 6144,
|
7 |
+
"pad_token_id": 151643,
|
8 |
+
"top_k": 0,
|
9 |
+
"top_p": 0.5,
|
10 |
+
"transformers_version": "4.32.0"
|
11 |
+
}
|
sakura_13b_model_v0.7_qwen14b/pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:974a7e9e631230753959c3c2b7b19d678cbaaa8e8a4dc57c8c21f19cb46f0286
|
3 |
+
size 9963536932
|
sakura_13b_model_v0.7_qwen14b/pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05e8aa1477364802e681f3553c8aef5511971f7b794c9a04d7b091cfbc85a730
|
3 |
+
size 9878406318
|
sakura_13b_model_v0.7_qwen14b/pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d2e927025d5204671531e51f7c962f8b3596043ddf66b56ac1997b9da36fef8
|
3 |
+
size 8492748196
|
sakura_13b_model_v0.7_qwen14b/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,330 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 28334581760
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
7 |
+
"transformer.h.0.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"transformer.h.0.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"transformer.h.0.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"transformer.h.0.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"transformer.h.0.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"transformer.h.0.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"transformer.h.0.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"transformer.h.1.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"transformer.h.1.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"transformer.h.1.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"transformer.h.1.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"transformer.h.1.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"transformer.h.1.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"transformer.h.1.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"transformer.h.10.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"transformer.h.10.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"transformer.h.10.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
27 |
+
"transformer.h.10.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
28 |
+
"transformer.h.10.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"transformer.h.10.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"transformer.h.10.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
31 |
+
"transformer.h.11.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
32 |
+
"transformer.h.11.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
33 |
+
"transformer.h.11.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
34 |
+
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
35 |
+
"transformer.h.11.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
36 |
+
"transformer.h.11.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
37 |
+
"transformer.h.11.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
38 |
+
"transformer.h.11.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
39 |
+
"transformer.h.12.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
40 |
+
"transformer.h.12.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
41 |
+
"transformer.h.12.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
42 |
+
"transformer.h.12.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
43 |
+
"transformer.h.12.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
44 |
+
"transformer.h.12.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
45 |
+
"transformer.h.12.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
46 |
+
"transformer.h.12.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
47 |
+
"transformer.h.13.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
48 |
+
"transformer.h.13.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
49 |
+
"transformer.h.13.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
50 |
+
"transformer.h.13.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
51 |
+
"transformer.h.13.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
52 |
+
"transformer.h.13.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"transformer.h.13.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"transformer.h.13.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"transformer.h.14.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"transformer.h.14.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
57 |
+
"transformer.h.14.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
59 |
+
"transformer.h.14.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"transformer.h.14.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"transformer.h.14.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"transformer.h.14.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
63 |
+
"transformer.h.15.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
64 |
+
"transformer.h.15.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"transformer.h.15.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"transformer.h.15.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"transformer.h.15.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
69 |
+
"transformer.h.15.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"transformer.h.15.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
71 |
+
"transformer.h.16.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"transformer.h.16.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"transformer.h.16.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"transformer.h.16.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"transformer.h.16.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"transformer.h.16.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"transformer.h.16.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
79 |
+
"transformer.h.17.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
80 |
+
"transformer.h.17.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
81 |
+
"transformer.h.17.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
82 |
+
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
83 |
+
"transformer.h.17.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
84 |
+
"transformer.h.17.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"transformer.h.17.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"transformer.h.17.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"transformer.h.18.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"transformer.h.18.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"transformer.h.18.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"transformer.h.18.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"transformer.h.18.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"transformer.h.18.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"transformer.h.18.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"transformer.h.19.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"transformer.h.19.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"transformer.h.19.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"transformer.h.19.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"transformer.h.19.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"transformer.h.19.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"transformer.h.19.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"transformer.h.2.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
104 |
+
"transformer.h.2.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
105 |
+
"transformer.h.2.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
106 |
+
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
107 |
+
"transformer.h.2.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
108 |
+
"transformer.h.2.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
109 |
+
"transformer.h.2.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
110 |
+
"transformer.h.2.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
111 |
+
"transformer.h.20.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
112 |
+
"transformer.h.20.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
113 |
+
"transformer.h.20.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
114 |
+
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
115 |
+
"transformer.h.20.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
116 |
+
"transformer.h.20.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
117 |
+
"transformer.h.20.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
118 |
+
"transformer.h.20.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
119 |
+
"transformer.h.21.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
120 |
+
"transformer.h.21.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
121 |
+
"transformer.h.21.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
122 |
+
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
123 |
+
"transformer.h.21.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
124 |
+
"transformer.h.21.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
125 |
+
"transformer.h.21.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
126 |
+
"transformer.h.21.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
127 |
+
"transformer.h.22.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
128 |
+
"transformer.h.22.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
129 |
+
"transformer.h.22.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
130 |
+
"transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
131 |
+
"transformer.h.22.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
132 |
+
"transformer.h.22.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
133 |
+
"transformer.h.22.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
134 |
+
"transformer.h.22.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
135 |
+
"transformer.h.23.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
136 |
+
"transformer.h.23.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
137 |
+
"transformer.h.23.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
138 |
+
"transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
139 |
+
"transformer.h.23.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
140 |
+
"transformer.h.23.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
141 |
+
"transformer.h.23.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
142 |
+
"transformer.h.23.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
143 |
+
"transformer.h.24.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
144 |
+
"transformer.h.24.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
145 |
+
"transformer.h.24.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
146 |
+
"transformer.h.24.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
147 |
+
"transformer.h.24.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
148 |
+
"transformer.h.24.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
149 |
+
"transformer.h.24.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
150 |
+
"transformer.h.24.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
151 |
+
"transformer.h.25.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
152 |
+
"transformer.h.25.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
153 |
+
"transformer.h.25.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
154 |
+
"transformer.h.25.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
155 |
+
"transformer.h.25.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
156 |
+
"transformer.h.25.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
157 |
+
"transformer.h.25.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
158 |
+
"transformer.h.25.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
159 |
+
"transformer.h.26.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
160 |
+
"transformer.h.26.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
161 |
+
"transformer.h.26.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
162 |
+
"transformer.h.26.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
163 |
+
"transformer.h.26.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
164 |
+
"transformer.h.26.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
165 |
+
"transformer.h.26.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
166 |
+
"transformer.h.26.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
167 |
+
"transformer.h.27.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
168 |
+
"transformer.h.27.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
169 |
+
"transformer.h.27.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
170 |
+
"transformer.h.27.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
171 |
+
"transformer.h.27.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
172 |
+
"transformer.h.27.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
173 |
+
"transformer.h.27.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
174 |
+
"transformer.h.27.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
175 |
+
"transformer.h.28.attn.c_attn.bias": "pytorch_model-00002-of-00003.bin",
|
176 |
+
"transformer.h.28.attn.c_attn.weight": "pytorch_model-00002-of-00003.bin",
|
177 |
+
"transformer.h.28.attn.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
178 |
+
"transformer.h.28.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
179 |
+
"transformer.h.28.ln_2.weight": "pytorch_model-00002-of-00003.bin",
|
180 |
+
"transformer.h.28.mlp.c_proj.weight": "pytorch_model-00002-of-00003.bin",
|
181 |
+
"transformer.h.28.mlp.w1.weight": "pytorch_model-00002-of-00003.bin",
|
182 |
+
"transformer.h.28.mlp.w2.weight": "pytorch_model-00002-of-00003.bin",
|
183 |
+
"transformer.h.29.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
184 |
+
"transformer.h.29.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
185 |
+
"transformer.h.29.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
186 |
+
"transformer.h.29.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
187 |
+
"transformer.h.29.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
188 |
+
"transformer.h.29.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
189 |
+
"transformer.h.29.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
190 |
+
"transformer.h.29.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
191 |
+
"transformer.h.3.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
192 |
+
"transformer.h.3.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
193 |
+
"transformer.h.3.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
194 |
+
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
195 |
+
"transformer.h.3.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
196 |
+
"transformer.h.3.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
197 |
+
"transformer.h.3.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
198 |
+
"transformer.h.3.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
199 |
+
"transformer.h.30.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
200 |
+
"transformer.h.30.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
201 |
+
"transformer.h.30.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
202 |
+
"transformer.h.30.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
203 |
+
"transformer.h.30.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
204 |
+
"transformer.h.30.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
205 |
+
"transformer.h.30.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
206 |
+
"transformer.h.30.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
207 |
+
"transformer.h.31.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
208 |
+
"transformer.h.31.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
209 |
+
"transformer.h.31.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
210 |
+
"transformer.h.31.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
211 |
+
"transformer.h.31.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
212 |
+
"transformer.h.31.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
213 |
+
"transformer.h.31.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
214 |
+
"transformer.h.31.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
215 |
+
"transformer.h.32.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
216 |
+
"transformer.h.32.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
217 |
+
"transformer.h.32.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
218 |
+
"transformer.h.32.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
219 |
+
"transformer.h.32.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
220 |
+
"transformer.h.32.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
221 |
+
"transformer.h.32.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
222 |
+
"transformer.h.32.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
223 |
+
"transformer.h.33.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
224 |
+
"transformer.h.33.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
225 |
+
"transformer.h.33.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
226 |
+
"transformer.h.33.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
227 |
+
"transformer.h.33.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
228 |
+
"transformer.h.33.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
229 |
+
"transformer.h.33.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
230 |
+
"transformer.h.33.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
231 |
+
"transformer.h.34.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
232 |
+
"transformer.h.34.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
233 |
+
"transformer.h.34.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
234 |
+
"transformer.h.34.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
235 |
+
"transformer.h.34.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
236 |
+
"transformer.h.34.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
237 |
+
"transformer.h.34.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
238 |
+
"transformer.h.34.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
239 |
+
"transformer.h.35.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
240 |
+
"transformer.h.35.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
241 |
+
"transformer.h.35.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
242 |
+
"transformer.h.35.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
243 |
+
"transformer.h.35.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
244 |
+
"transformer.h.35.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
245 |
+
"transformer.h.35.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
246 |
+
"transformer.h.35.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
247 |
+
"transformer.h.36.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
248 |
+
"transformer.h.36.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
249 |
+
"transformer.h.36.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
250 |
+
"transformer.h.36.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
251 |
+
"transformer.h.36.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
252 |
+
"transformer.h.36.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
253 |
+
"transformer.h.36.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
254 |
+
"transformer.h.36.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
255 |
+
"transformer.h.37.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
256 |
+
"transformer.h.37.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
257 |
+
"transformer.h.37.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
258 |
+
"transformer.h.37.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
259 |
+
"transformer.h.37.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
260 |
+
"transformer.h.37.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
261 |
+
"transformer.h.37.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
262 |
+
"transformer.h.37.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
263 |
+
"transformer.h.38.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
264 |
+
"transformer.h.38.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
265 |
+
"transformer.h.38.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
266 |
+
"transformer.h.38.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
267 |
+
"transformer.h.38.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
268 |
+
"transformer.h.38.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
269 |
+
"transformer.h.38.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
270 |
+
"transformer.h.38.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
271 |
+
"transformer.h.39.attn.c_attn.bias": "pytorch_model-00003-of-00003.bin",
|
272 |
+
"transformer.h.39.attn.c_attn.weight": "pytorch_model-00003-of-00003.bin",
|
273 |
+
"transformer.h.39.attn.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
274 |
+
"transformer.h.39.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
275 |
+
"transformer.h.39.ln_2.weight": "pytorch_model-00003-of-00003.bin",
|
276 |
+
"transformer.h.39.mlp.c_proj.weight": "pytorch_model-00003-of-00003.bin",
|
277 |
+
"transformer.h.39.mlp.w1.weight": "pytorch_model-00003-of-00003.bin",
|
278 |
+
"transformer.h.39.mlp.w2.weight": "pytorch_model-00003-of-00003.bin",
|
279 |
+
"transformer.h.4.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
280 |
+
"transformer.h.4.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
281 |
+
"transformer.h.4.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
282 |
+
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
283 |
+
"transformer.h.4.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
284 |
+
"transformer.h.4.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
285 |
+
"transformer.h.4.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
286 |
+
"transformer.h.4.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
287 |
+
"transformer.h.5.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
288 |
+
"transformer.h.5.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
289 |
+
"transformer.h.5.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
290 |
+
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
291 |
+
"transformer.h.5.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
292 |
+
"transformer.h.5.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
293 |
+
"transformer.h.5.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
294 |
+
"transformer.h.5.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
295 |
+
"transformer.h.6.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
296 |
+
"transformer.h.6.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
297 |
+
"transformer.h.6.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
298 |
+
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
299 |
+
"transformer.h.6.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
300 |
+
"transformer.h.6.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
301 |
+
"transformer.h.6.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
302 |
+
"transformer.h.6.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
303 |
+
"transformer.h.7.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
304 |
+
"transformer.h.7.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
305 |
+
"transformer.h.7.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
306 |
+
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
307 |
+
"transformer.h.7.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
308 |
+
"transformer.h.7.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
309 |
+
"transformer.h.7.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
310 |
+
"transformer.h.7.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
311 |
+
"transformer.h.8.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
312 |
+
"transformer.h.8.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
313 |
+
"transformer.h.8.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
314 |
+
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
315 |
+
"transformer.h.8.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
316 |
+
"transformer.h.8.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
317 |
+
"transformer.h.8.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
318 |
+
"transformer.h.8.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
319 |
+
"transformer.h.9.attn.c_attn.bias": "pytorch_model-00001-of-00003.bin",
|
320 |
+
"transformer.h.9.attn.c_attn.weight": "pytorch_model-00001-of-00003.bin",
|
321 |
+
"transformer.h.9.attn.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
322 |
+
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
323 |
+
"transformer.h.9.ln_2.weight": "pytorch_model-00001-of-00003.bin",
|
324 |
+
"transformer.h.9.mlp.c_proj.weight": "pytorch_model-00001-of-00003.bin",
|
325 |
+
"transformer.h.9.mlp.w1.weight": "pytorch_model-00001-of-00003.bin",
|
326 |
+
"transformer.h.9.mlp.w2.weight": "pytorch_model-00001-of-00003.bin",
|
327 |
+
"transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
|
328 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
329 |
+
}
|
330 |
+
}
|
sakura_13b_model_v0.7_qwen14b/qwen.tiktoken
ADDED
The diff for this file is too large to render.
See raw diff
|
|
sakura_13b_model_v0.7_qwen14b/special_tokens_map.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pad_token": "<|endoftext|>"
|
3 |
+
}
|
sakura_13b_model_v0.7_qwen14b/tokenizer_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"Qwen/Qwen-14B-Chat--tokenization_qwen.QWenTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"clean_up_tokenization_spaces": true,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding_side": "right",
|
11 |
+
"tokenizer_class": "QWenTokenizer"
|
12 |
+
}
|
sakura_13b_model_v0.7_qwen14b/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
sakura_13b_model_v0.7_qwen14b/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e011282ed5b0fd8aa9421e76784bd1516d84950e64d203acb72264f0f3398478
|
3 |
+
size 6520
|