Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- added_tokens.json +28 -0
- chat_template.jinja +86 -0
- config.json +163 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00025.safetensors +3 -0
- model-00002-of-00025.safetensors +3 -0
- model-00003-of-00025.safetensors +3 -0
- model-00004-of-00025.safetensors +3 -0
- model-00005-of-00025.safetensors +3 -0
- model-00006-of-00025.safetensors +3 -0
- model-00007-of-00025.safetensors +3 -0
- model-00008-of-00025.safetensors +3 -0
- model-00009-of-00025.safetensors +3 -0
- model-00010-of-00025.safetensors +3 -0
- model-00011-of-00025.safetensors +3 -0
- model-00012-of-00025.safetensors +3 -0
- model-00013-of-00025.safetensors +3 -0
- model-00014-of-00025.safetensors +3 -0
- model-00015-of-00025.safetensors +3 -0
- model-00016-of-00025.safetensors +3 -0
- model-00017-of-00025.safetensors +3 -0
- model-00018-of-00025.safetensors +3 -0
- model-00019-of-00025.safetensors +3 -0
- model-00020-of-00025.safetensors +3 -0
- model-00021-of-00025.safetensors +3 -0
- model-00022-of-00025.safetensors +3 -0
- model-00023-of-00025.safetensors +3 -0
- model-00024-of-00025.safetensors +3 -0
- model-00025-of-00025.safetensors +3 -0
- model.safetensors.index.json +3 -0
- recipe.yaml +6 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,5 @@ 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 |
+
model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
|
37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</think>": 151668,
|
3 |
+
"</tool_call>": 151658,
|
4 |
+
"</tool_response>": 151666,
|
5 |
+
"<think>": 151667,
|
6 |
+
"<tool_call>": 151657,
|
7 |
+
"<tool_response>": 151665,
|
8 |
+
"<|box_end|>": 151649,
|
9 |
+
"<|box_start|>": 151648,
|
10 |
+
"<|endoftext|>": 151643,
|
11 |
+
"<|file_sep|>": 151664,
|
12 |
+
"<|fim_middle|>": 151660,
|
13 |
+
"<|fim_pad|>": 151662,
|
14 |
+
"<|fim_prefix|>": 151659,
|
15 |
+
"<|fim_suffix|>": 151661,
|
16 |
+
"<|im_end|>": 151645,
|
17 |
+
"<|im_start|>": 151644,
|
18 |
+
"<|image_pad|>": 151655,
|
19 |
+
"<|object_ref_end|>": 151647,
|
20 |
+
"<|object_ref_start|>": 151646,
|
21 |
+
"<|quad_end|>": 151651,
|
22 |
+
"<|quad_start|>": 151650,
|
23 |
+
"<|repo_name|>": 151663,
|
24 |
+
"<|video_pad|>": 151656,
|
25 |
+
"<|vision_end|>": 151653,
|
26 |
+
"<|vision_pad|>": 151654,
|
27 |
+
"<|vision_start|>": 151652
|
28 |
+
}
|
chat_template.jinja
ADDED
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{%- if tools %}
|
2 |
+
{{- '<|im_start|>system\n' }}
|
3 |
+
{%- if messages[0].role == 'system' %}
|
4 |
+
{{- messages[0].content + '\n\n' }}
|
5 |
+
{%- endif %}
|
6 |
+
{{- "# 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>" }}
|
7 |
+
{%- for tool in tools %}
|
8 |
+
{{- "\n" }}
|
9 |
+
{{- tool | tojson }}
|
10 |
+
{%- endfor %}
|
11 |
+
{{- "\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" }}
|
12 |
+
{%- else %}
|
13 |
+
{%- if messages[0].role == 'system' %}
|
14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
15 |
+
{%- endif %}
|
16 |
+
{%- endif %}
|
17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
18 |
+
{%- for message in messages[::-1] %}
|
19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
21 |
+
{%- set ns.multi_step_tool = false %}
|
22 |
+
{%- set ns.last_query_index = index %}
|
23 |
+
{%- endif %}
|
24 |
+
{%- endfor %}
|
25 |
+
{%- for message in messages %}
|
26 |
+
{%- if message.content is string %}
|
27 |
+
{%- set content = message.content %}
|
28 |
+
{%- else %}
|
29 |
+
{%- set content = '' %}
|
30 |
+
{%- endif %}
|
31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
33 |
+
{%- elif message.role == "assistant" %}
|
34 |
+
{%- set reasoning_content = '' %}
|
35 |
+
{%- if message.reasoning_content is string %}
|
36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
37 |
+
{%- else %}
|
38 |
+
{%- if '</think>' in content %}
|
39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
41 |
+
{%- endif %}
|
42 |
+
{%- endif %}
|
43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
46 |
+
{%- else %}
|
47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
48 |
+
{%- endif %}
|
49 |
+
{%- else %}
|
50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
51 |
+
{%- endif %}
|
52 |
+
{%- if message.tool_calls %}
|
53 |
+
{%- for tool_call in message.tool_calls %}
|
54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
55 |
+
{{- '\n' }}
|
56 |
+
{%- endif %}
|
57 |
+
{%- if tool_call.function %}
|
58 |
+
{%- set tool_call = tool_call.function %}
|
59 |
+
{%- endif %}
|
60 |
+
{{- '<tool_call>\n{"name": "' }}
|
61 |
+
{{- tool_call.name }}
|
62 |
+
{{- '", "arguments": ' }}
|
63 |
+
{%- if tool_call.arguments is string %}
|
64 |
+
{{- tool_call.arguments }}
|
65 |
+
{%- else %}
|
66 |
+
{{- tool_call.arguments | tojson }}
|
67 |
+
{%- endif %}
|
68 |
+
{{- '}\n</tool_call>' }}
|
69 |
+
{%- endfor %}
|
70 |
+
{%- endif %}
|
71 |
+
{{- '<|im_end|>\n' }}
|
72 |
+
{%- elif message.role == "tool" %}
|
73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
74 |
+
{{- '<|im_start|>user' }}
|
75 |
+
{%- endif %}
|
76 |
+
{{- '\n<tool_response>\n' }}
|
77 |
+
{{- content }}
|
78 |
+
{{- '\n</tool_response>' }}
|
79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
80 |
+
{{- '<|im_end|>\n' }}
|
81 |
+
{%- endif %}
|
82 |
+
{%- endif %}
|
83 |
+
{%- endfor %}
|
84 |
+
{%- if add_generation_prompt %}
|
85 |
+
{{- '<|im_start|>assistant\n' }}
|
86 |
+
{%- endif %}
|
config.json
ADDED
@@ -0,0 +1,163 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Qwen3MoeForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"decoder_sparse_step": 1,
|
9 |
+
"eos_token_id": 151645,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 12288,
|
15 |
+
"max_position_embeddings": 262144,
|
16 |
+
"max_window_layers": 94,
|
17 |
+
"mlp_only_layers": [],
|
18 |
+
"model_type": "qwen3_moe",
|
19 |
+
"moe_intermediate_size": 1536,
|
20 |
+
"norm_topk_prob": true,
|
21 |
+
"num_attention_heads": 64,
|
22 |
+
"num_experts": 128,
|
23 |
+
"num_experts_per_tok": 8,
|
24 |
+
"num_hidden_layers": 94,
|
25 |
+
"num_key_value_heads": 4,
|
26 |
+
"output_router_logits": false,
|
27 |
+
"quantization_config": {
|
28 |
+
"config_groups": {
|
29 |
+
"group_0": {
|
30 |
+
"input_activations": null,
|
31 |
+
"output_activations": null,
|
32 |
+
"targets": [
|
33 |
+
"Linear"
|
34 |
+
],
|
35 |
+
"weights": {
|
36 |
+
"actorder": null,
|
37 |
+
"block_structure": null,
|
38 |
+
"dynamic": false,
|
39 |
+
"group_size": 128,
|
40 |
+
"num_bits": 4,
|
41 |
+
"observer": "minmax",
|
42 |
+
"observer_kwargs": {},
|
43 |
+
"strategy": "group",
|
44 |
+
"symmetric": true,
|
45 |
+
"type": "int"
|
46 |
+
}
|
47 |
+
}
|
48 |
+
},
|
49 |
+
"format": "pack-quantized",
|
50 |
+
"global_compression_ratio": null,
|
51 |
+
"ignore": [
|
52 |
+
"model.layers.0.mlp.gate",
|
53 |
+
"model.layers.1.mlp.gate",
|
54 |
+
"model.layers.2.mlp.gate",
|
55 |
+
"model.layers.3.mlp.gate",
|
56 |
+
"model.layers.4.mlp.gate",
|
57 |
+
"model.layers.5.mlp.gate",
|
58 |
+
"model.layers.6.mlp.gate",
|
59 |
+
"model.layers.7.mlp.gate",
|
60 |
+
"model.layers.8.mlp.gate",
|
61 |
+
"model.layers.9.mlp.gate",
|
62 |
+
"model.layers.10.mlp.gate",
|
63 |
+
"model.layers.11.mlp.gate",
|
64 |
+
"model.layers.12.mlp.gate",
|
65 |
+
"model.layers.13.mlp.gate",
|
66 |
+
"model.layers.14.mlp.gate",
|
67 |
+
"model.layers.15.mlp.gate",
|
68 |
+
"model.layers.16.mlp.gate",
|
69 |
+
"model.layers.17.mlp.gate",
|
70 |
+
"model.layers.18.mlp.gate",
|
71 |
+
"model.layers.19.mlp.gate",
|
72 |
+
"model.layers.20.mlp.gate",
|
73 |
+
"model.layers.21.mlp.gate",
|
74 |
+
"model.layers.22.mlp.gate",
|
75 |
+
"model.layers.23.mlp.gate",
|
76 |
+
"model.layers.24.mlp.gate",
|
77 |
+
"model.layers.25.mlp.gate",
|
78 |
+
"model.layers.26.mlp.gate",
|
79 |
+
"model.layers.27.mlp.gate",
|
80 |
+
"model.layers.28.mlp.gate",
|
81 |
+
"model.layers.29.mlp.gate",
|
82 |
+
"model.layers.30.mlp.gate",
|
83 |
+
"model.layers.31.mlp.gate",
|
84 |
+
"model.layers.32.mlp.gate",
|
85 |
+
"model.layers.33.mlp.gate",
|
86 |
+
"model.layers.34.mlp.gate",
|
87 |
+
"model.layers.35.mlp.gate",
|
88 |
+
"model.layers.36.mlp.gate",
|
89 |
+
"model.layers.37.mlp.gate",
|
90 |
+
"model.layers.38.mlp.gate",
|
91 |
+
"model.layers.39.mlp.gate",
|
92 |
+
"model.layers.40.mlp.gate",
|
93 |
+
"model.layers.41.mlp.gate",
|
94 |
+
"model.layers.42.mlp.gate",
|
95 |
+
"model.layers.43.mlp.gate",
|
96 |
+
"model.layers.44.mlp.gate",
|
97 |
+
"model.layers.45.mlp.gate",
|
98 |
+
"model.layers.46.mlp.gate",
|
99 |
+
"model.layers.47.mlp.gate",
|
100 |
+
"model.layers.48.mlp.gate",
|
101 |
+
"model.layers.49.mlp.gate",
|
102 |
+
"model.layers.50.mlp.gate",
|
103 |
+
"model.layers.51.mlp.gate",
|
104 |
+
"model.layers.52.mlp.gate",
|
105 |
+
"model.layers.53.mlp.gate",
|
106 |
+
"model.layers.54.mlp.gate",
|
107 |
+
"model.layers.55.mlp.gate",
|
108 |
+
"model.layers.56.mlp.gate",
|
109 |
+
"model.layers.57.mlp.gate",
|
110 |
+
"model.layers.58.mlp.gate",
|
111 |
+
"model.layers.59.mlp.gate",
|
112 |
+
"model.layers.60.mlp.gate",
|
113 |
+
"model.layers.61.mlp.gate",
|
114 |
+
"model.layers.62.mlp.gate",
|
115 |
+
"model.layers.63.mlp.gate",
|
116 |
+
"model.layers.64.mlp.gate",
|
117 |
+
"model.layers.65.mlp.gate",
|
118 |
+
"model.layers.66.mlp.gate",
|
119 |
+
"model.layers.67.mlp.gate",
|
120 |
+
"model.layers.68.mlp.gate",
|
121 |
+
"model.layers.69.mlp.gate",
|
122 |
+
"model.layers.70.mlp.gate",
|
123 |
+
"model.layers.71.mlp.gate",
|
124 |
+
"model.layers.72.mlp.gate",
|
125 |
+
"model.layers.73.mlp.gate",
|
126 |
+
"model.layers.74.mlp.gate",
|
127 |
+
"model.layers.75.mlp.gate",
|
128 |
+
"model.layers.76.mlp.gate",
|
129 |
+
"model.layers.77.mlp.gate",
|
130 |
+
"model.layers.78.mlp.gate",
|
131 |
+
"model.layers.79.mlp.gate",
|
132 |
+
"model.layers.80.mlp.gate",
|
133 |
+
"model.layers.81.mlp.gate",
|
134 |
+
"model.layers.82.mlp.gate",
|
135 |
+
"model.layers.83.mlp.gate",
|
136 |
+
"model.layers.84.mlp.gate",
|
137 |
+
"model.layers.85.mlp.gate",
|
138 |
+
"model.layers.86.mlp.gate",
|
139 |
+
"model.layers.87.mlp.gate",
|
140 |
+
"model.layers.88.mlp.gate",
|
141 |
+
"model.layers.89.mlp.gate",
|
142 |
+
"model.layers.90.mlp.gate",
|
143 |
+
"model.layers.91.mlp.gate",
|
144 |
+
"model.layers.92.mlp.gate",
|
145 |
+
"model.layers.93.mlp.gate",
|
146 |
+
"lm_head"
|
147 |
+
],
|
148 |
+
"kv_cache_scheme": null,
|
149 |
+
"quant_method": "compressed-tensors",
|
150 |
+
"quantization_status": "compressed"
|
151 |
+
},
|
152 |
+
"rms_norm_eps": 1e-06,
|
153 |
+
"rope_scaling": null,
|
154 |
+
"rope_theta": 5000000,
|
155 |
+
"router_aux_loss_coef": 0.001,
|
156 |
+
"sliding_window": null,
|
157 |
+
"tie_word_embeddings": false,
|
158 |
+
"torch_dtype": "bfloat16",
|
159 |
+
"transformers_version": "4.53.2",
|
160 |
+
"use_cache": true,
|
161 |
+
"use_sliding_window": false,
|
162 |
+
"vocab_size": 151936
|
163 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"temperature": 0.7,
|
10 |
+
"top_k": 20,
|
11 |
+
"top_p": 0.8,
|
12 |
+
"transformers_version": "4.53.2"
|
13 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4cc917298ed77416dd0ccca11342ce99e1a358eca69fb6df08d7e9f7eeeae06
|
3 |
+
size 4998377088
|
model-00002-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14602b18a9a9f1ead0b59672b7301d17a70ca098d2e2351bcbc7420f00376245
|
3 |
+
size 4998490184
|
model-00003-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d76a492a765f6c5d75ece36c88e541ce7f72efc7725f8304c58caec191cfc6a
|
3 |
+
size 4998491112
|
model-00004-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c294db10c57936c3dc0942e61a240514e7f63c1d3b9755b7b18599912b9bbe6
|
3 |
+
size 4998494856
|
model-00005-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6f2befeb09650a55b629b07360665ad83cc878d11c5eb7562c3d0c9f6486406
|
3 |
+
size 4998494856
|
model-00006-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:690455f8a3e2c5b443f6c6dab85c0123370553d25ec2d1e757ca1d1c2eef2b1f
|
3 |
+
size 4998494856
|
model-00007-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efebcfebddc3f285b8314b462e5bc35b907f2af73d44bb7089fb53d8057f9ef5
|
3 |
+
size 4998494856
|
model-00008-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e1c6916e6b2b8b6914e4825afb0db6592f930b7464e35f1028ee6f7ad7ef9a
|
3 |
+
size 4998494856
|
model-00009-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3665ea3760b2364ecd5b23f2769c269e0bfe03605551ae90d117d2a008858359
|
3 |
+
size 4998494888
|
model-00010-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:490a6a74b86b86472cae004bea88587592678957bc615b10e511ca053e47687a
|
3 |
+
size 4999594720
|
model-00011-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d72a1db6ee7a372b6ffca8f661a5826d7335db9da39448a2e9b70d045a245fd
|
3 |
+
size 4998494728
|
model-00012-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4360fd4d31b62c6a8a270dc8a2e3a0271f467236354b0488b479ec7f6de723b3
|
3 |
+
size 4998494768
|
model-00013-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba537c1dc6bc793228dc3aec2eb113d4209fdcc9dfeb5b27711c2ad4b4dd2d08
|
3 |
+
size 4998494856
|
model-00014-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb78b91936980e8b327dc817dfdd3d708115ffaa3ca81cd163b80be7a00bb6ac
|
3 |
+
size 4998494856
|
model-00015-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75a6956422399cfd2cb356510fe21dacaf351751205e540f4c8efc4d72ee9534
|
3 |
+
size 4998494856
|
model-00016-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d49e43b9f5f5f0bfd2ffabeae973c107dbb4db9292d65ddc113cb7f5f4a95f38
|
3 |
+
size 4998494856
|
model-00017-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63a6b5f81b70ec09dd9cda0ff0c99b902081ba8fb22036dc6d24c4475f73bb73
|
3 |
+
size 4998494856
|
model-00018-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b67e3b4b2e95d5186c2629a1a1365729527d9dd05b8b1fa5a3910f4a362ff8cf
|
3 |
+
size 4998494856
|
model-00019-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6974c795e7f7da4a718ba739c63303ee6bc49c87c0dadd5add70a2cb30e9f1a4
|
3 |
+
size 4999610168
|
model-00020-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6cba91aab9cd076daedbf2e600a5d39699e2cf64ad2027f5912de48168e7875b
|
3 |
+
size 4998479376
|
model-00021-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3350e6ffc7c609b79470a2524f946f3a1b046a31b0a28a893e7774cf974788d
|
3 |
+
size 4998494728
|
model-00022-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a363647297b7edbadac36402349c2850965d8af69ff01f6b9b60dd1daec0c5e
|
3 |
+
size 4998494840
|
model-00023-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4cc1b5ef5139d580dd51869e8d70fb15b09f3b93674643592bb18aff5f770114
|
3 |
+
size 4998494856
|
model-00024-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ad3d7a55aeaad1fef46cbe08b86ad11eb0dbb117dd022d1c2bef0389bf3a6aa
|
3 |
+
size 4998494856
|
model-00025-of-00025.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:670edac38857822119759beec3c856777fa70918d74ef307d8a7948d1c43bdb9
|
3 |
+
size 3190235160
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30f5de7c7c9281e9fd301826f4bcc0a1db22eab7382f5f7072017f0530cfe827
|
3 |
+
size 10611364
|
recipe.yaml
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
default_stage:
|
2 |
+
default_modifiers:
|
3 |
+
QuantizationModifier:
|
4 |
+
targets: [Linear]
|
5 |
+
ignore: [lm_head, 're:.*\.mlp\.gate$']
|
6 |
+
scheme: W4A16
|
special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
3 |
+
size 11422654
|
tokenizer_config.json
ADDED
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
},
|
181 |
+
"151665": {
|
182 |
+
"content": "<tool_response>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": false
|
188 |
+
},
|
189 |
+
"151666": {
|
190 |
+
"content": "</tool_response>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": false
|
196 |
+
},
|
197 |
+
"151667": {
|
198 |
+
"content": "<think>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": false
|
204 |
+
},
|
205 |
+
"151668": {
|
206 |
+
"content": "</think>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": false
|
212 |
+
}
|
213 |
+
},
|
214 |
+
"additional_special_tokens": [
|
215 |
+
"<|im_start|>",
|
216 |
+
"<|im_end|>",
|
217 |
+
"<|object_ref_start|>",
|
218 |
+
"<|object_ref_end|>",
|
219 |
+
"<|box_start|>",
|
220 |
+
"<|box_end|>",
|
221 |
+
"<|quad_start|>",
|
222 |
+
"<|quad_end|>",
|
223 |
+
"<|vision_start|>",
|
224 |
+
"<|vision_end|>",
|
225 |
+
"<|vision_pad|>",
|
226 |
+
"<|image_pad|>",
|
227 |
+
"<|video_pad|>"
|
228 |
+
],
|
229 |
+
"bos_token": null,
|
230 |
+
"clean_up_tokenization_spaces": false,
|
231 |
+
"eos_token": "<|im_end|>",
|
232 |
+
"errors": "replace",
|
233 |
+
"extra_special_tokens": {},
|
234 |
+
"model_max_length": 262144,
|
235 |
+
"pad_token": "<|endoftext|>",
|
236 |
+
"split_special_tokens": false,
|
237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
238 |
+
"unk_token": null
|
239 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|