Upload folder using huggingface_hub
Browse files- config.json +68 -0
- generation_config.json +9 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +162 -0
config.json
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct",
|
3 |
+
"architectures": [
|
4 |
+
"DeepseekV2ForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"auto_map": {
|
9 |
+
"AutoConfig": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--configuration_deepseek.DeepseekV2Config",
|
10 |
+
"AutoModel": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--modeling_deepseek.DeepseekV2Model",
|
11 |
+
"AutoModelForCausalLM": "deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct--modeling_deepseek.DeepseekV2ForCausalLM"
|
12 |
+
},
|
13 |
+
"aux_loss_alpha": 0.001,
|
14 |
+
"bos_token_id": 100000,
|
15 |
+
"eos_token_id": 100001,
|
16 |
+
"ep_size": 1,
|
17 |
+
"first_k_dense_replace": 1,
|
18 |
+
"hidden_act": "silu",
|
19 |
+
"hidden_size": 2048,
|
20 |
+
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 10944,
|
22 |
+
"kv_lora_rank": 512,
|
23 |
+
"max_position_embeddings": 163840,
|
24 |
+
"model_type": "deepseek_v2",
|
25 |
+
"moe_intermediate_size": 1408,
|
26 |
+
"moe_layer_freq": 1,
|
27 |
+
"n_group": 1,
|
28 |
+
"n_routed_experts": 64,
|
29 |
+
"n_shared_experts": 2,
|
30 |
+
"norm_topk_prob": false,
|
31 |
+
"num_attention_heads": 16,
|
32 |
+
"num_experts_per_tok": 6,
|
33 |
+
"num_hidden_layers": 27,
|
34 |
+
"num_key_value_heads": 16,
|
35 |
+
"pretraining_tp": 1,
|
36 |
+
"q_lora_rank": null,
|
37 |
+
"qk_nope_head_dim": 128,
|
38 |
+
"qk_rope_head_dim": 64,
|
39 |
+
"quantization_config": {
|
40 |
+
"activation_scheme": "static",
|
41 |
+
"ignored_layers": [
|
42 |
+
"lm_head"
|
43 |
+
],
|
44 |
+
"quant_method": "fp8"
|
45 |
+
},
|
46 |
+
"rms_norm_eps": 1e-06,
|
47 |
+
"rope_scaling": {
|
48 |
+
"beta_fast": 32,
|
49 |
+
"beta_slow": 1,
|
50 |
+
"factor": 40,
|
51 |
+
"mscale": 0.707,
|
52 |
+
"mscale_all_dim": 0.707,
|
53 |
+
"original_max_position_embeddings": 4096,
|
54 |
+
"type": "yarn"
|
55 |
+
},
|
56 |
+
"rope_theta": 10000,
|
57 |
+
"routed_scaling_factor": 1.0,
|
58 |
+
"scoring_func": "softmax",
|
59 |
+
"seq_aux": true,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"topk_group": 1,
|
62 |
+
"topk_method": "greedy",
|
63 |
+
"torch_dtype": "bfloat16",
|
64 |
+
"transformers_version": "4.42.4",
|
65 |
+
"use_cache": true,
|
66 |
+
"v_head_dim": 128,
|
67 |
+
"vocab_size": 102400
|
68 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100000,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 100001,
|
6 |
+
"temperature": 0.3,
|
7 |
+
"top_p": 0.95,
|
8 |
+
"transformers_version": "4.42.4"
|
9 |
+
}
|
model-00001-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0eb6fc113953955054f87f53eb8ff2a1b10c583bf7a77d1e18c5b93f74522e88
|
3 |
+
size 4998917616
|
model-00002-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:238472f2aa34612748175fae9a00d6b707166e90be362965de997c8a9ebe59e7
|
3 |
+
size 5000166448
|
model-00003-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b988fe2a1efa9503c81018c1387850f2f42df7fca41b87dd2580ab18dd0b5f1
|
3 |
+
size 5000552320
|
model-00004-of-00004.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5dba94fadfcaf20f445cd4faa42508ae08c5d8182702939e9c2303a5f9955f8a
|
3 |
+
size 1131651032
|
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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end▁of▁sentence|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,162 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"100000": {
|
7 |
+
"content": "<|begin▁of▁sentence|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"100001": {
|
15 |
+
"content": "<|end▁of▁sentence|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"100002": {
|
23 |
+
"content": "<|fim▁hole|>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"100003": {
|
31 |
+
"content": "<|fim▁begin|>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"100004": {
|
39 |
+
"content": "<|fim▁end|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"100005": {
|
47 |
+
"content": "<|completion|>",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"100006": {
|
55 |
+
"content": "<|User|>",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"100007": {
|
63 |
+
"content": "<|Assistant|>",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"100008": {
|
71 |
+
"content": "<|EOT|>",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
"100009": {
|
79 |
+
"content": "<|tool▁calls▁begin|>",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"100010": {
|
87 |
+
"content": "<|tool▁calls▁end|>",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"100011": {
|
95 |
+
"content": "<|tool▁call▁begin|>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"100012": {
|
103 |
+
"content": "<|tool▁call▁end|>",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"100013": {
|
111 |
+
"content": "<|tool▁outputs▁begin|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"100014": {
|
119 |
+
"content": "<|tool▁outputs▁end|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"100015": {
|
127 |
+
"content": "<|tool▁output▁begin|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"100016": {
|
135 |
+
"content": "<|tool▁output▁end|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"100017": {
|
143 |
+
"content": "<|tool▁sep|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
}
|
150 |
+
},
|
151 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
152 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{ 'User: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ 'Assistant: ' + message['content'] + eos_token }}{% elif message['role'] == 'system' %}{{ message['content'] + '\n\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'Assistant:' }}{% endif %}",
|
153 |
+
"clean_up_tokenization_spaces": false,
|
154 |
+
"eos_token": "<|end▁of▁sentence|>",
|
155 |
+
"legacy": true,
|
156 |
+
"model_max_length": 16384,
|
157 |
+
"pad_token": "<|end▁of▁sentence|>",
|
158 |
+
"sp_model_kwargs": {},
|
159 |
+
"tokenizer_class": "LlamaTokenizer",
|
160 |
+
"unk_token": null,
|
161 |
+
"use_default_system_prompt": false
|
162 |
+
}
|