Chhagan005 commited on
Commit
ccff8b5
·
verified ·
1 Parent(s): 481ad9a

Upload folder using huggingface_hub

Browse files
.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 ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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") %} {{- '<|im_start|>user' }}
42
+ {%- endif %}
43
+ {{- '\n<tool_response>\n' }}
44
+ {{- message.content }}
45
+ {{- '\n</tool_response>' }}
46
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
47
+ {{- '<|im_end|>\n' }}
48
+ {%- endif %}
49
+ {%- endif %}
50
+ {%- endfor %}
51
+ {%- if add_generation_prompt %}
52
+ {{- '<|im_start|>assistant\n' }}
53
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "float16",
6
+ "image_token_id": 151655,
7
+ "model_type": "qwen3_vl",
8
+ "pad_token_id": 151643,
9
+ "quantization_config": {
10
+ "_load_in_4bit": true,
11
+ "_load_in_8bit": false,
12
+ "bnb_4bit_compute_dtype": "bfloat16",
13
+ "bnb_4bit_quant_storage": "uint8",
14
+ "bnb_4bit_quant_type": "nf4",
15
+ "bnb_4bit_use_double_quant": true,
16
+ "llm_int8_enable_fp32_cpu_offload": false,
17
+ "llm_int8_has_fp16_weight": false,
18
+ "llm_int8_skip_modules": null,
19
+ "llm_int8_threshold": 6.0,
20
+ "load_in_4bit": true,
21
+ "load_in_8bit": false,
22
+ "quant_method": "bitsandbytes"
23
+ },
24
+ "text_config": {
25
+ "attention_bias": false,
26
+ "attention_dropout": 0.0,
27
+ "bos_token_id": 151643,
28
+ "dtype": "float16",
29
+ "eos_token_id": 151645,
30
+ "head_dim": 128,
31
+ "hidden_act": "silu",
32
+ "hidden_size": 4096,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 12288,
35
+ "max_position_embeddings": 262144,
36
+ "model_type": "qwen3_vl_text",
37
+ "num_attention_heads": 32,
38
+ "num_hidden_layers": 36,
39
+ "num_key_value_heads": 8,
40
+ "pad_token_id": null,
41
+ "rms_norm_eps": 1e-06,
42
+ "rope_parameters": {
43
+ "mrope_interleaved": true,
44
+ "mrope_section": [
45
+ 24,
46
+ 20,
47
+ 20
48
+ ],
49
+ "rope_theta": 5000000,
50
+ "rope_type": "default"
51
+ },
52
+ "use_cache": true,
53
+ "vocab_size": 151936
54
+ },
55
+ "tie_word_embeddings": false,
56
+ "transformers_version": "5.2.0",
57
+ "unsloth_version": "2026.2.1",
58
+ "video_token_id": 151656,
59
+ "vision_config": {
60
+ "deepstack_visual_indexes": [
61
+ 8,
62
+ 16,
63
+ 24
64
+ ],
65
+ "depth": 27,
66
+ "dtype": "float16",
67
+ "hidden_act": "gelu_pytorch_tanh",
68
+ "hidden_size": 1152,
69
+ "in_channels": 3,
70
+ "initializer_range": 0.02,
71
+ "intermediate_size": 4304,
72
+ "model_type": "qwen3_vl",
73
+ "num_heads": 16,
74
+ "num_position_embeddings": 2304,
75
+ "out_hidden_size": 4096,
76
+ "patch_size": 16,
77
+ "spatial_merge_size": 2,
78
+ "temporal_patch_size": 2
79
+ },
80
+ "vision_end_token_id": 151653,
81
+ "vision_start_token_id": 151652
82
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "pad_token_id": 151643,
6
+ "transformers_version": "5.2.0",
7
+ "use_cache": true
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6b0d2f7b3870ee323d6a9e538df5fc30104529c6e2e034e1a6d0a9bd9205cb7
3
+ size 6378432932
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
+ size 11422650
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
9
+ "model_max_length": 262144,
10
+ "pad_token": "<|endoftext|>",
11
+ "padding_side": "left",
12
+ "processor_class": "_Unsloth_Patched_Qwen3VLProcessor",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null
16
+ }