hf-transformers-bot commited on
Commit
1800e4c
·
verified ·
1 Parent(s): 802f8fe

Update tiny models for DeepseekV3ForSequenceClassification

Browse files
chat_template.jinja ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% 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 + '
2
+
3
+ ' + 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 message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
4
+ ' + '```json' + '
5
+ ' + tool['function']['arguments'] + '
6
+ ' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'
7
+ ' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '
8
+ ' + '```json' + '
9
+ ' + tool['function']['arguments'] + '
10
+ ' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{{'<|Assistant|>' + message['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 %}{{'
11
+ <|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|>'}}{% endif %}
config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DeepseekV3ForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "aux_loss_alpha": 0.001,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "eos_token_id": 1,
11
+ "first_k_dense_replace": 1,
12
+ "head_dim": 16,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 32,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 32,
17
+ "kv_lora_rank": 16,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "deepseek_v3",
20
+ "moe_intermediate_size": 16,
21
+ "n_group": 2,
22
+ "n_routed_experts": 8,
23
+ "n_shared_experts": 1,
24
+ "norm_topk_prob": true,
25
+ "num_attention_heads": 4,
26
+ "num_experts_per_tok": 8,
27
+ "num_hidden_layers": 2,
28
+ "num_key_value_heads": 4,
29
+ "num_nextn_predict_layers": 1,
30
+ "pad_token_id": 1,
31
+ "pretraining_tp": 1,
32
+ "q_lora_rank": 32,
33
+ "qk_head_dim": 48,
34
+ "qk_nope_head_dim": 32,
35
+ "qk_rope_head_dim": 16,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_interleave": true,
38
+ "rope_parameters": {
39
+ "rope_theta": 10000.0,
40
+ "rope_type": "default"
41
+ },
42
+ "routed_scaling_factor": 2.5,
43
+ "tie_word_embeddings": false,
44
+ "topk_group": 1,
45
+ "transformers_version": "5.16.0.dev0",
46
+ "use_cache": true,
47
+ "v_head_dim": 32,
48
+ "vocab_size": 128815
49
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17339e166a37b9b9e02e04e4b41d0454867b2eb7f30b3936c285d57ca48fdd23
3
+ size 16695248
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|begin▁of▁sentence|>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<|end▁of▁sentence|>",
6
+ "is_local": true,
7
+ "legacy": true,
8
+ "local_files_only": false,
9
+ "model_max_length": 512,
10
+ "pad_token": "<|end▁of▁sentence|>",
11
+ "sp_model_kwargs": {},
12
+ "tokenizer_class": "TokenizersBackend",
13
+ "unk_token": null
14
+ }