Hugging Face's logo

kon171verma
/
intent-classifier

Text Classification
Transformers
ONNX
Safetensors
GGUF
intent-classification
tool-routing
llama.cpp
onnxruntime
conversational
Model card Files
xet
 Community
Konark Verma commited on
Commit
de98d11
·
verified ·
1 Parent(s): 136e1ec

Delete qwen3-0.6b

Browse files
Files changed (21) hide show
  1. qwen3-0.6b/gguf/qwen3-0.6b-Q4_K_M.gguf +0 -3
  2. qwen3-0.6b/gguf/qwen3-0.6b-Q6_K.gguf +0 -3
  3. qwen3-0.6b/gguf/qwen3-0.6b-Q8_0.gguf +0 -3
  4. qwen3-0.6b/gguf/qwen3-0.6b-f16.gguf +0 -3
  5. qwen3-0.6b/onnx/qwen3-0.6b-dynamic-int8/model.onnx +0 -3
  6. qwen3-0.6b/onnx/qwen3-0.6b-dynamic-int8/model.onnx.data +0 -3
  7. qwen3-0.6b/onnx/qwen3-0.6b-fp16/config.json +0 -64
  8. qwen3-0.6b/onnx/qwen3-0.6b-fp16/generation_config.json +0 -13
  9. qwen3-0.6b/onnx/qwen3-0.6b-fp16/model.onnx +0 -3
  10. qwen3-0.6b/onnx/qwen3-0.6b-fp32/config.json +0 -64
  11. qwen3-0.6b/onnx/qwen3-0.6b-fp32/generation_config.json +0 -13
  12. qwen3-0.6b/onnx/qwen3-0.6b-fp32/model.onnx +0 -3
  13. qwen3-0.6b/onnx/qwen3-0.6b-fp32/model.onnx_data +0 -3
  14. qwen3-0.6b/onnx/qwen3-0.6b-static-int8/model.onnx +0 -3
  15. qwen3-0.6b/onnx/qwen3-0.6b-static-int8/model.onnx.data +0 -3
  16. qwen3-0.6b/safetensors/chat_template.jinja +0 -89
  17. qwen3-0.6b/safetensors/config.json +0 -63
  18. qwen3-0.6b/safetensors/generation_config.json +0 -13
  19. qwen3-0.6b/safetensors/model.safetensors +0 -3
  20. qwen3-0.6b/safetensors/tokenizer.json +0 -3
  21. qwen3-0.6b/safetensors/tokenizer_config.json +0 -30
qwen3-0.6b/gguf/qwen3-0.6b-Q4_K_M.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:da220a3568346a62f6d41e663eb98ad406af44d8b45a98b7f1b8194cff0a51b1
3
- size 396704576
 
 
 
 
qwen3-0.6b/gguf/qwen3-0.6b-Q6_K.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:81bb61b703cf4191e25d2e6e2793260b740caba6b200b264e2dac3f923badd32
3
- size 495106880
 
 
 
 
qwen3-0.6b/gguf/qwen3-0.6b-Q8_0.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eff9296556b56f1bdd22888ab935ea5b175bd63d39897ac1a82fb8c6c243be7b
3
- size 639446848
 
 
 
 
qwen3-0.6b/gguf/qwen3-0.6b-f16.gguf DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:bda9591d891ce769cbae1fb180d83170e06597c657cac3dc5e5702079d95207f
3
- size 1198182208
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-dynamic-int8/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:766f6fe13527fb80812d0f035679308ad7c166264890017d13638cc4f5a71870
3
- size 3760961
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-dynamic-int8/model.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2643495ff57580aa9d60e56704296df71783b6f5facb6eebf275981e3426b198
3
- size 1949536256
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp16/config.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "float16",
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 1024,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_types": [
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
- ],
45
- "max_position_embeddings": 40960,
46
- "max_window_layers": 28,
47
- "model_type": "qwen3",
48
- "num_attention_heads": 16,
49
- "num_hidden_layers": 28,
50
- "num_key_value_heads": 8,
51
- "rms_norm_eps": 1e-06,
52
- "rope_parameters": {
53
- "rope_theta": 1000000,
54
- "rope_type": "default"
55
- },
56
- "rope_scaling": null,
57
- "rope_theta": 10000.0,
58
- "sliding_window": null,
59
- "tie_word_embeddings": true,
60
- "transformers_version": "4.57.6",
61
- "use_cache": true,
62
- "use_sliding_window": false,
63
- "vocab_size": 151936
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp16/generation_config.json DELETED
@@ -1,13 +0,0 @@
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": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.57.6"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp16/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c5d8f6500852f3ae75053389aa4a7dbe01c34985a4eb31080bbe9322d397cf9
3
- size 1621987093
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp32/config.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "float32",
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 1024,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_types": [
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
- ],
45
- "max_position_embeddings": 40960,
46
- "max_window_layers": 28,
47
- "model_type": "qwen3",
48
- "num_attention_heads": 16,
49
- "num_hidden_layers": 28,
50
- "num_key_value_heads": 8,
51
- "rms_norm_eps": 1e-06,
52
- "rope_parameters": {
53
- "rope_theta": 1000000,
54
- "rope_type": "default"
55
- },
56
- "rope_scaling": null,
57
- "rope_theta": 10000.0,
58
- "sliding_window": null,
59
- "tie_word_embeddings": true,
60
- "transformers_version": "4.57.6",
61
- "use_cache": true,
62
- "use_sliding_window": false,
63
- "vocab_size": 151936
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp32/generation_config.json DELETED
@@ -1,13 +0,0 @@
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": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "4.57.6"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp32/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f432cd3b9f32b1056db0dd17fcd9a38dfb4e3963eba4f004462f8829ff771047
3
- size 1430583
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-fp32/model.onnx_data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d33748fe84cb389b503919c0c8a33f666189f2d68f50f03be8ea7bb7bdb95cd3
3
- size 3006529792
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-static-int8/model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a9bc6aa28c0d07de962e9616c3a331d981ddf348bb7756a38f6c55bdcb21cf9
3
- size 3843823
 
 
 
 
qwen3-0.6b/onnx/qwen3-0.6b-static-int8/model.onnx.data DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2643495ff57580aa9d60e56704296df71783b6f5facb6eebf275981e3426b198
3
- size 1949536256
 
 
 
 
qwen3-0.6b/safetensors/chat_template.jinja DELETED
@@ -1,89 +0,0 @@
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
- {%- if enable_thinking is defined and enable_thinking is false %}
87
- {{- '<think>\n\n</think>\n\n' }}
88
- {%- endif %}
89
- {%- endif %}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/safetensors/config.json DELETED
@@ -1,63 +0,0 @@
1
- {
2
- "architectures": [
3
- "Qwen3ForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 151643,
8
- "dtype": "bfloat16",
9
- "eos_token_id": 151645,
10
- "head_dim": 128,
11
- "hidden_act": "silu",
12
- "hidden_size": 1024,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 3072,
15
- "layer_types": [
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
- ],
45
- "max_position_embeddings": 40960,
46
- "max_window_layers": 28,
47
- "model_type": "qwen3",
48
- "num_attention_heads": 16,
49
- "num_hidden_layers": 28,
50
- "num_key_value_heads": 8,
51
- "pad_token_id": null,
52
- "rms_norm_eps": 1e-06,
53
- "rope_parameters": {
54
- "rope_theta": 1000000,
55
- "rope_type": "default"
56
- },
57
- "sliding_window": null,
58
- "tie_word_embeddings": true,
59
- "transformers_version": "5.14.1",
60
- "use_cache": true,
61
- "use_sliding_window": false,
62
- "vocab_size": 151936
63
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/safetensors/generation_config.json DELETED
@@ -1,13 +0,0 @@
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": 0.6,
10
- "top_k": 20,
11
- "top_p": 0.95,
12
- "transformers_version": "5.14.1"
13
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
qwen3-0.6b/safetensors/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:42ef0b12e675c0c05e9ecb50841c6812ea474b0c20497e25101c42e958e4bb7f
3
- size 1192135096
 
 
 
 
qwen3-0.6b/safetensors/tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
3
- size 11422650
 
 
 
 
qwen3-0.6b/safetensors/tokenizer_config.json DELETED
@@ -1,30 +0,0 @@
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
- }