Hugging Face's logo

superclient
/
qwen_finetune

GGUF
qwen3_5
llama.cpp
unsloth
vision-language-model
conversational
Model card Files
xet
 Community
brunasuperclient03 commited on
Commit
b02cdb5
·
0 Parent(s):

Duplicate from brunasuperclient03/qwen_finetune

Browse files
Files changed (5) hide show
  1. .gitattributes +37 -0
  2. Qwen3.5-0.8B.F16-mmproj.gguf +3 -0
  3. Qwen3.5-0.8B.Q4_K_M.gguf +3 -0
  4. README.md +21 -0
  5. config.json +104 -0
.gitattributes ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
+ Qwen3.5-0.8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Qwen3.5-0.8B.F16-mmproj.gguf filter=lfs diff=lfs merge=lfs -text
Qwen3.5-0.8B.F16-mmproj.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28e7672084d45f92e82e3ba2a1787e3deb2000b92750df11d298e27fa34f823
3
+ size 204986752
Qwen3.5-0.8B.Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30225c2f365eb432fd31a5f225eb2c55a9f469117326c5253942c3ae047945f9
3
+ size 541903584
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - gguf
4
+ - llama.cpp
5
+ - unsloth
6
+ - vision-language-model
7
+ ---
8
+
9
+ # qwen_finetune : GGUF
10
+
11
+ This model was finetuned and converted to GGUF format using [Unsloth](https://github.com/unslothai/unsloth).
12
+
13
+ **Example usage**:
14
+ - For text only LLMs: `llama-cli -hf brunasuperclient03/qwen_finetune --jinja`
15
+ - For multimodal models: `llama-mtmd-cli -hf brunasuperclient03/qwen_finetune --jinja`
16
+
17
+ ## Available Model files:
18
+ - `Qwen3.5-0.8B.Q4_K_M.gguf`
19
+ - `Qwen3.5-0.8B.F16-mmproj.gguf`
20
+ This was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
21
+ [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "torch_dtype": "float16",
6
+ "image_token_id": 248056,
7
+ "model_name": "unsloth/Qwen3.5-0.8B",
8
+ "model_type": "qwen3_5",
9
+ "mtp_num_hidden_layers": 1,
10
+ "pad_token_id": 248055,
11
+ "text_config": {
12
+ "attention_bias": false,
13
+ "attention_dropout": 0.0,
14
+ "attn_output_gate": true,
15
+ "bos_token_id": null,
16
+ "torch_dtype": "float16",
17
+ "eos_token_id": 248044,
18
+ "full_attention_interval": 4,
19
+ "head_dim": 256,
20
+ "hidden_act": "silu",
21
+ "hidden_size": 1024,
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3584,
24
+ "layer_types": [
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "full_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "full_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "full_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "full_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "full_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "full_attention"
49
+ ],
50
+ "linear_conv_kernel_dim": 4,
51
+ "linear_key_head_dim": 128,
52
+ "linear_num_key_heads": 16,
53
+ "linear_num_value_heads": 16,
54
+ "linear_value_head_dim": 128,
55
+ "mamba_ssm_dtype": "float32",
56
+ "max_position_embeddings": 262144,
57
+ "mlp_only_layers": [],
58
+ "model_type": "qwen3_5_text",
59
+ "mtp_num_hidden_layers": 1,
60
+ "mtp_use_dedicated_embeddings": false,
61
+ "num_attention_heads": 8,
62
+ "num_hidden_layers": 24,
63
+ "num_key_value_heads": 2,
64
+ "pad_token_id": null,
65
+ "partial_rotary_factor": 0.25,
66
+ "rms_norm_eps": 1e-06,
67
+ "rope_parameters": {
68
+ "mrope_interleaved": true,
69
+ "mrope_section": [
70
+ 11,
71
+ 11,
72
+ 10
73
+ ],
74
+ "partial_rotary_factor": 0.25,
75
+ "rope_theta": 10000000,
76
+ "rope_type": "default"
77
+ },
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "vocab_size": 248320
81
+ },
82
+ "tie_word_embeddings": true,
83
+ "unsloth_version": "2026.7.5",
84
+ "video_token_id": 248057,
85
+ "vision_config": {
86
+ "deepstack_visual_indexes": [],
87
+ "depth": 12,
88
+ "torch_dtype": "float16",
89
+ "hidden_act": "gelu_pytorch_tanh",
90
+ "hidden_size": 768,
91
+ "in_channels": 3,
92
+ "initializer_range": 0.02,
93
+ "intermediate_size": 3072,
94
+ "model_type": "qwen3_5",
95
+ "num_heads": 12,
96
+ "num_position_embeddings": 2304,
97
+ "out_hidden_size": 1024,
98
+ "patch_size": 16,
99
+ "spatial_merge_size": 2,
100
+ "temporal_patch_size": 2
101
+ },
102
+ "vision_end_token_id": 248054,
103
+ "vision_start_token_id": 248053
104
+ }