Hugging Face's logo

nm-testing
/
fp8_static_per_tensor-e2e

Safetensors
llama
compressed-tensors
Model card Files
xet
 Community
nm-autobot commited on
Commit
e29f3c0
·
verified ·
1 Parent(s): 29ee16b

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +54 -15
  3. config.json +60 -20
  4. generation_config.json +12 -5
  5. model.safetensors +2 -2
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +27 -40
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja CHANGED
@@ -1,15 +1,54 @@
1
- {% for message in messages %}
2
- {% if message['role'] == 'user' %}
3
- {{ '<|user|>
4
- ' + message['content'] + eos_token }}
5
- {% elif message['role'] == 'system' %}
6
- {{ '<|system|>
7
- ' + message['content'] + eos_token }}
8
- {% elif message['role'] == 'assistant' %}
9
- {{ '<|assistant|>
10
- ' + message['content'] + eos_token }}
11
- {% endif %}
12
- {% if loop.last and add_generation_prompt %}
13
- {{ '<|assistant|>' }}
14
- {% endif %}
15
- {% endfor %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0]['role'] == 'system' %}
4
+ {{- messages[0]['content'] }}
5
+ {%- else %}
6
+ {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
7
+ {%- endif %}
8
+ {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
9
+ {%- for tool in tools %}
10
+ {{- "\n" }}
11
+ {{- tool | tojson }}
12
+ {%- endfor %}
13
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
14
+ {%- else %}
15
+ {%- if messages[0]['role'] == 'system' %}
16
+ {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
17
+ {%- else %}
18
+ {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
19
+ {%- endif %}
20
+ {%- endif %}
21
+ {%- for message in messages %}
22
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
23
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
24
+ {%- elif message.role == "assistant" %}
25
+ {{- '<|im_start|>' + message.role }}
26
+ {%- if message.content %}
27
+ {{- '\n' + message.content }}
28
+ {%- endif %}
29
+ {%- for tool_call in message.tool_calls %}
30
+ {%- if tool_call.function is defined %}
31
+ {%- set tool_call = tool_call.function %}
32
+ {%- endif %}
33
+ {{- '\n<tool_call>\n{"name": "' }}
34
+ {{- tool_call.name }}
35
+ {{- '", "arguments": ' }}
36
+ {{- tool_call.arguments | tojson }}
37
+ {{- '}\n</tool_call>' }}
38
+ {%- endfor %}
39
+ {{- '<|im_end|>\n' }}
40
+ {%- elif message.role == "tool" %}
41
+ {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
42
+ {{- '<|im_start|>user' }}
43
+ {%- endif %}
44
+ {{- '\n<tool_response>\n' }}
45
+ {{- message.content }}
46
+ {{- '\n</tool_response>' }}
47
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
48
+ {{- '<|im_end|>\n' }}
49
+ {%- endif %}
50
+ {%- endif %}
51
+ {%- endfor %}
52
+ {%- if add_generation_prompt %}
53
+ {{- '<|im_start|>assistant\n' }}
54
+ {%- endif %}
config.json CHANGED
@@ -1,24 +1,60 @@
1
  {
2
  "architectures": [
3
- "LlamaForCausalLM"
4
  ],
5
- "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
  "dtype": "bfloat16",
9
- "eos_token_id": 2,
10
- "head_dim": 64,
11
  "hidden_act": "silu",
12
  "hidden_size": 2048,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 5632,
15
- "max_position_embeddings": 2048,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 32,
19
- "num_hidden_layers": 22,
20
- "num_key_value_heads": 4,
21
- "pretraining_tp": 1,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "quantization_config": {
23
  "config_groups": {
24
  "group_0": {
@@ -67,13 +103,17 @@
67
  "quantization_status": "compressed",
68
  "sparsity_config": {},
69
  "transform_config": {},
70
- "version": "0.15.1.a20260526"
 
 
 
 
 
71
  },
72
- "rms_norm_eps": 1e-05,
73
- "rope_scaling": null,
74
- "rope_theta": 10000.0,
75
- "tie_word_embeddings": false,
76
- "transformers_version": "4.57.6",
77
  "use_cache": true,
78
- "vocab_size": 32000
 
79
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen2ForCausalLM"
4
  ],
 
5
  "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
  "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
 
9
  "hidden_act": "silu",
10
  "hidden_size": 2048,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention"
50
+ ],
51
+ "max_position_embeddings": 32768,
52
+ "max_window_layers": 70,
53
+ "model_type": "qwen2",
54
+ "num_attention_heads": 16,
55
+ "num_hidden_layers": 36,
56
+ "num_key_value_heads": 2,
57
+ "pad_token_id": null,
58
  "quantization_config": {
59
  "config_groups": {
60
  "group_0": {
 
103
  "quantization_status": "compressed",
104
  "sparsity_config": {},
105
  "transform_config": {},
106
+ "version": "0.1.dev1+g9c3dd05"
107
+ },
108
+ "rms_norm_eps": 1e-06,
109
+ "rope_parameters": {
110
+ "rope_theta": 1000000.0,
111
+ "rope_type": "default"
112
  },
113
+ "sliding_window": null,
114
+ "tie_word_embeddings": true,
115
+ "transformers_version": "5.10.0.dev0",
 
 
116
  "use_cache": true,
117
+ "use_sliding_window": false,
118
+ "vocab_size": 151936
119
  }
generation_config.json CHANGED
@@ -1,7 +1,14 @@
1
  {
2
- "bos_token_id": 1,
3
- "eos_token_id": 2,
4
- "max_length": 2048,
5
- "pad_token_id": 0,
6
- "transformers_version": "4.57.6"
 
 
 
 
 
 
 
7
  }
 
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": "5.10.0.dev0"
14
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e60f940ec0aaba8086ec98cb3d31bc29c5d73a7713492cfa39dbf581fc2ed6f
3
- size 1231270880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bd64259302ab48533d01978a3997f6cb3febd8a251b10bf24696292da979d18
3
+ size 3397452680
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,43 +1,30 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
13
- },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": false,
27
- "single_word": false,
28
- "special": true
29
- }
30
- },
31
- "bos_token": "<s>",
32
  "clean_up_tokenization_spaces": false,
33
- "eos_token": "</s>",
34
- "extra_special_tokens": {},
35
- "legacy": false,
36
- "model_max_length": 2048,
37
- "pad_token": "</s>",
38
- "padding_side": "right",
39
- "sp_model_kwargs": {},
40
- "tokenizer_class": "LlamaTokenizer",
41
- "unk_token": "<unk>",
42
- "use_default_system_prompt": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
43
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|im_start|>",
10
+ "<|im_end|>",
11
+ "<|object_ref_start|>",
12
+ "<|object_ref_end|>",
13
+ "<|box_start|>",
14
+ "<|box_end|>",
15
+ "<|quad_start|>",
16
+ "<|quad_end|>",
17
+ "<|vision_start|>",
18
+ "<|vision_end|>",
19
+ "<|vision_pad|>",
20
+ "<|image_pad|>",
21
+ "<|video_pad|>"
22
+ ],
23
+ "is_local": false,
24
+ "local_files_only": false,
25
+ "model_max_length": 131072,
26
+ "pad_token": "<|endoftext|>",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "Qwen2Tokenizer",
29
+ "unk_token": null
30
  }