mgoin commited on
Commit
20252d6
1 Parent(s): c2d3b3e

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen/Qwen2-57B-A14B-Instruct",
3
+ "architectures": [
4
+ "Qwen2MoeForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "eos_token_id": 151643,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3584,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 32768,
15
+ "max_window_layers": 28,
16
+ "mlp_only_layers": [],
17
+ "model_type": "qwen2_moe",
18
+ "moe_intermediate_size": 2560,
19
+ "norm_topk_prob": false,
20
+ "num_attention_heads": 28,
21
+ "num_experts": 64,
22
+ "num_experts_per_tok": 8,
23
+ "num_hidden_layers": 28,
24
+ "num_key_value_heads": 4,
25
+ "output_router_logits": false,
26
+ "quantization_config": {
27
+ "activation_scheme": "dynamic",
28
+ "ignored_layers": [
29
+ "model.layers.9.mlp.shared_expert_gate",
30
+ "model.layers.23.mlp.gate",
31
+ "model.layers.27.mlp.shared_expert_gate",
32
+ "model.layers.17.mlp.gate",
33
+ "model.layers.4.mlp.shared_expert_gate",
34
+ "model.layers.15.mlp.gate",
35
+ "model.layers.19.mlp.gate",
36
+ "model.layers.18.mlp.gate",
37
+ "model.layers.26.mlp.gate",
38
+ "model.layers.27.mlp.gate",
39
+ "model.layers.14.mlp.gate",
40
+ "model.layers.22.mlp.shared_expert_gate",
41
+ "model.layers.21.mlp.gate",
42
+ "model.layers.24.mlp.shared_expert_gate",
43
+ "model.layers.18.mlp.shared_expert_gate",
44
+ "model.layers.26.mlp.shared_expert_gate",
45
+ "model.layers.13.mlp.shared_expert_gate",
46
+ "model.layers.6.mlp.gate",
47
+ "model.layers.0.mlp.gate",
48
+ "model.layers.12.mlp.gate",
49
+ "model.layers.2.mlp.shared_expert_gate",
50
+ "model.layers.17.mlp.shared_expert_gate",
51
+ "model.layers.8.mlp.shared_expert_gate",
52
+ "model.layers.7.mlp.shared_expert_gate",
53
+ "model.layers.0.mlp.shared_expert_gate",
54
+ "model.layers.10.mlp.shared_expert_gate",
55
+ "model.layers.7.mlp.gate",
56
+ "model.layers.20.mlp.shared_expert_gate",
57
+ "model.layers.25.mlp.shared_expert_gate",
58
+ "model.layers.8.mlp.gate",
59
+ "model.layers.14.mlp.shared_expert_gate",
60
+ "model.layers.5.mlp.shared_expert_gate",
61
+ "model.layers.2.mlp.gate",
62
+ "model.layers.1.mlp.shared_expert_gate",
63
+ "model.layers.6.mlp.shared_expert_gate",
64
+ "model.layers.12.mlp.shared_expert_gate",
65
+ "model.layers.22.mlp.gate",
66
+ "model.layers.16.mlp.shared_expert_gate",
67
+ "model.layers.13.mlp.gate",
68
+ "model.layers.25.mlp.gate",
69
+ "model.layers.19.mlp.shared_expert_gate",
70
+ "model.layers.23.mlp.shared_expert_gate",
71
+ "model.layers.3.mlp.gate",
72
+ "lm_head",
73
+ "model.layers.3.mlp.shared_expert_gate",
74
+ "model.layers.11.mlp.gate",
75
+ "model.layers.1.mlp.gate",
76
+ "model.layers.20.mlp.gate",
77
+ "model.layers.4.mlp.gate",
78
+ "model.layers.10.mlp.gate",
79
+ "model.layers.21.mlp.shared_expert_gate",
80
+ "model.layers.11.mlp.shared_expert_gate",
81
+ "model.layers.15.mlp.shared_expert_gate",
82
+ "model.layers.9.mlp.gate",
83
+ "model.layers.16.mlp.gate",
84
+ "model.layers.5.mlp.gate",
85
+ "model.layers.24.mlp.gate"
86
+ ],
87
+ "kv_cache_scheme": "static",
88
+ "quant_method": "fp8"
89
+ },
90
+ "rms_norm_eps": 1e-06,
91
+ "rope_theta": 1000000.0,
92
+ "router_aux_loss_coef": 0.001,
93
+ "shared_expert_intermediate_size": 20480,
94
+ "sliding_window": 65536,
95
+ "tie_word_embeddings": false,
96
+ "torch_dtype": "bfloat16",
97
+ "transformers_version": "4.42.1",
98
+ "use_cache": true,
99
+ "use_sliding_window": false,
100
+ "vocab_size": 151936
101
+ }
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": "4.42.1"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cebe8151c2c66e7f7350e3db42e04fddd4ffa75251dda13cb24366b7ea98431f
3
+ size 4965667088
model-00002-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08e8fd971f42cb6f186d3ab0aa62acc03dfd8c749ff9facc088da6b0e46bb440
3
+ size 4998314052
model-00003-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a257f4554bf89c19c065eac41075669c9b783846a64cb303a5226b9843c25262
3
+ size 4986816740
model-00004-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edcad491a8b87dcdf6bdd1e4d0dd1cd517b1ca1f7da2717a55b6584f60b85a2d
3
+ size 4998312400
model-00005-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336635fdebfa9ea0ccf628af9925533a7b36f61b3f18527c666fd0c4c8880602
3
+ size 4995992800
model-00006-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:033c612a70b424b734515987d6f7f8adbc210d9c6e83061bf3a5c6bc45070def
3
+ size 4998313376
model-00007-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba23b5a20471325dcf8a4cc9006c0af3b9e9b7c3bbd183425799a42b36551abc
3
+ size 4995993032
model-00008-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87d76a7e7ae3fd95e87a9243bfb622fdcc0f39c52ddc7c016aa6b63eaeeaeb6e
3
+ size 4998313368
model-00009-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e155c8e931f48454de5576843c94fac98e76e8bed626cea3e135b386b3cd72b1
3
+ size 4995993032
model-00010-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c3d3678cf09f212da62d5731e72ad2412a140fc1572e41ae4e3a00c704166d
3
+ size 4998313376
model-00011-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1711ff39fcac72f01bef20afe1b1227c47a2d6a8b914523a553ede5815873a47
3
+ size 4995993032
model-00012-of-00012.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17f71669ec1ff4dd21c9d1250e7bce932aed4ca3174c0f6d6d584bb36c7c59a1
3
+ size 3577922600
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 65536,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff