Cran-May commited on
Commit
8290598
0 Parent(s):

Duplicate from NLPark/B-and-W_Flycatcher

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 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - zh
4
+ - en
5
+ pipeline_tag: text-generation
6
+ tags:
7
+ - qwen2.5
8
+ license: apache-2.0
9
+ ---
10
+ Base Model: Qwen2.5-14B-Instruct
11
+
12
+ License: Apache 2.0
added_tokens.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|blank|>": 151674,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|call|>": 151671,
8
+ "<|define|>": 151670,
9
+ "<|endoftext|>": 151643,
10
+ "<|end|>": 151668,
11
+ "<|file_sep|>": 151664,
12
+ "<|fill|>": 151675,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|hint|>": 151673,
18
+ "<|im_end|>": 151645,
19
+ "<|im_start|>": 151644,
20
+ "<|image_pad|>": 151655,
21
+ "<|object_ref_end|>": 151647,
22
+ "<|object_ref_start|>": 151646,
23
+ "<|pad0|>": 151676,
24
+ "<|params|>": 151672,
25
+ "<|quad_end|>": 151651,
26
+ "<|quad_start|>": 151650,
27
+ "<|repo_name|>": 151663,
28
+ "<|role|>": 151665,
29
+ "<|said|>": 151666,
30
+ "<|says|>": 151667,
31
+ "<|stop|>": 151669,
32
+ "<|video_pad|>": 151656,
33
+ "<|vision_end|>": 151653,
34
+ "<|vision_pad|>": 151654,
35
+ "<|vision_start|>": 151652
36
+ }
config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "NLPark/Blue-and-White_Flycatcher-3AD1E",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 151643,
9
+ "eos_token_id": 151645,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 5120,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 13824,
15
+ "max_position_embeddings": 200000,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 40,
19
+ "num_hidden_layers": 48,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 32768,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 1000000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.45.0.dev0",
34
+ "use_cache": false,
35
+ "vocab_size": 152064
36
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.45.0.dev0"
14
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a103c622bcbc0a3e7b75a995ad1c3935a70de3dcc59ac15485e43176b43305ab
3
+ size 4986108624
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8ec56215e7f62d9812ca9556676729f27b88f84a71182fe9cd6e2b64b9db7cf
3
+ size 4954715344
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:100ed3a8ff8ba11de22fa8348e43486458ec0ff66b48f29430ab699399502923
3
+ size 4954715376
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae4791514cab4746cdc69b43e77953e75ef066055cdfedea272e205b2f348cb8
3
+ size 4954715376
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f95eb36315c660490c96ca708007d7231a65a7a3c54bcad058f5d119a505bc23
3
+ size 4954715376
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4fe0de4a97da05e96c23f0c8369cbccb3fd3e8a4004d1171fc242f2d84ea36
3
+ size 4734459816
model.safetensors.index.json ADDED
@@ -0,0 +1,442 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29539379200
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00006-of-00006.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
395
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
396
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
397
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
398
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
399
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
400
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
401
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
402
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
403
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
404
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
405
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
406
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
407
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
408
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
409
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
410
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
411
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
412
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
413
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
414
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
415
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
416
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
417
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
418
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
419
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
420
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
421
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
422
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
423
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
424
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
425
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
426
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
427
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
428
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
429
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
430
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
431
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
432
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
433
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
434
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
435
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
436
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
437
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
438
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
439
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
440
+ "model.norm.weight": "model-00006-of-00006.safetensors"
441
+ }
442
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,90 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|role|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|said|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|says|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|end|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|stop|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|define|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|call|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|params|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<|hint|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<|blank|>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<|fill|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<|pad0|>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ }
87
+ ],
88
+ "eos_token": "<|end|>",
89
+ "pad_token": "<|pad0|>"
90
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,302 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<|role|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|said|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|says|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<|end|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<|stop|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|define|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|call|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|params|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|hint|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|blank|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|fill|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<|pad0|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ }
277
+ },
278
+ "additional_special_tokens": [
279
+ "<|role|>",
280
+ "<|said|>",
281
+ "<|says|>",
282
+ "<|end|>",
283
+ "<|stop|>",
284
+ "<|define|>",
285
+ "<|call|>",
286
+ "<|params|>",
287
+ "<|hint|>",
288
+ "<|blank|>",
289
+ "<|fill|>",
290
+ "<|pad0|>"
291
+ ],
292
+ "bos_token": null,
293
+ "chat_template": "{% for message in messages %}{{'<|role|>' + message['role'] + '<|says|>' + message['content'] + '<|end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|role|>assistant<|says|>' }}{% endif %}",
294
+ "clean_up_tokenization_spaces": false,
295
+ "eos_token": "<|end|>",
296
+ "errors": "replace",
297
+ "model_max_length": 131072,
298
+ "pad_token": "<|pad0|>",
299
+ "split_special_tokens": false,
300
+ "tokenizer_class": "Qwen2Tokenizer",
301
+ "unk_token": null
302
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff