ghostplant commited on
Commit
f37e742
·
verified ·
1 Parent(s): 7ba9c63

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +70 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +35 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_deepseek.DeepseekV3Config",
9
+ "AutoModel": "modeling_deepseek.DeepseekV3Model",
10
+ "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
11
+ },
12
+ "aux_loss_alpha": 0.001,
13
+ "bos_token_id": 0,
14
+ "eos_token_id": 1,
15
+ "ep_size": 1,
16
+ "first_k_dense_replace": 3,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 7168,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 18432,
21
+ "kv_lora_rank": 512,
22
+ "max_position_embeddings": 163840,
23
+ "model_type": "deepseek_v3",
24
+ "moe_intermediate_size": 2048,
25
+ "moe_layer_freq": 1,
26
+ "n_group": 8,
27
+ "n_routed_experts": 256,
28
+ "n_shared_experts": 1,
29
+ "norm_topk_prob": true,
30
+ "num_attention_heads": 128,
31
+ "num_experts_per_tok": 8,
32
+ "num_hidden_layers": 61,
33
+ "num_key_value_heads": 128,
34
+ "num_nextn_predict_layers": 1,
35
+ "pretraining_tp": 1,
36
+ "q_lora_rank": 1536,
37
+ "qk_nope_head_dim": 128,
38
+ "qk_rope_head_dim": 64,
39
+ "quantization_config": {
40
+ "activation_scheme": "dynamic",
41
+ "fmt": "e4m3",
42
+ "quant_method": "fp8",
43
+ "weight_block_size": [
44
+ 128,
45
+ 128
46
+ ]
47
+ },
48
+ "rms_norm_eps": 1e-06,
49
+ "rope_scaling": {
50
+ "beta_fast": 32,
51
+ "beta_slow": 1,
52
+ "factor": 40,
53
+ "mscale": 1.0,
54
+ "mscale_all_dim": 1.0,
55
+ "original_max_position_embeddings": 4096,
56
+ "type": "yarn"
57
+ },
58
+ "rope_theta": 10000,
59
+ "routed_scaling_factor": 2.5,
60
+ "scoring_func": "sigmoid",
61
+ "seq_aux": true,
62
+ "tie_word_embeddings": false,
63
+ "topk_group": 4,
64
+ "topk_method": "noaux_tc",
65
+ "torch_dtype": "bfloat16",
66
+ "transformers_version": "4.46.3",
67
+ "use_cache": true,
68
+ "v_head_dim": 128,
69
+ "vocab_size": 129280
70
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|begin▁of▁sentence|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|end▁of▁sentence|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": true,
22
+ "model_max_length": 16384,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<|end▁of▁sentence|>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "sp_model_kwargs": {},
32
+ "unk_token": null,
33
+ "tokenizer_class": "LlamaTokenizerFast",
34
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='', is_first_sp=true) %}{%- for message in messages %}{%- if message['role'] == 'system' %}{%- if ns.is_first_sp %}{% set ns.system_prompt = ns.system_prompt + message['content'] %}{% set ns.is_first_sp = false %}{%- else %}{% set ns.system_prompt = ns.system_prompt + '\\n\\n' + message['content'] %}{%- endif %}{%- endif %}{%- endfor %}{{ bos_token }}{{ ns.system_prompt }}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' in message %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls'] %}{%- if not ns.is_first %}{%- if message['content'] is none %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- else %}{{'<|Assistant|>' + message['content'] + '<|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- endif %}{%- endfor %}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- if message['role'] == 'assistant' and 'tool_calls' not in message %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}"
35
+ }