Hugging Face's logo

aufklarer
/
Qwen3.5-0.8B-Chat-MLX

Text Generation
MLX
Safetensors
qwen3_chat
qwen3.5
on-device
apple-silicon
quantized
int4
int5
int8
Model card Files
xet
 Community
aufklarer commited on
Commit
2ef6fc5
·
verified ·
1 Parent(s): 7038e96

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +2 -0
  2. int4/config.json +50 -0
  3. int4/model.safetensors +3 -0
  4. int4/tokenizer.json +3 -0
  5. int4/tokenizer_config.json +32 -0
  6. int8/config.json +50 -0
  7. int8/model.safetensors +3 -0
  8. int8/tokenizer.json +3 -0
  9. int8/tokenizer_config.json +32 -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
+ int4/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ int8/tokenizer.json filter=lfs diff=lfs merge=lfs -text
int4/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hidden_size": 1024,
3
+ "num_hidden_layers": 24,
4
+ "num_attention_heads": 8,
5
+ "num_key_value_heads": 2,
6
+ "head_dim": 256,
7
+ "intermediate_size": 3584,
8
+ "vocab_size": 248320,
9
+ "max_seq_len": 2048,
10
+ "rope_theta": 10000000,
11
+ "rms_norm_eps": 1e-06,
12
+ "eos_token_id": 248046,
13
+ "pad_token_id": 248044,
14
+ "quantization": "int4",
15
+ "model_type": "qwen3_5_text",
16
+ "layer_types": [
17
+ "linear_attention",
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "full_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
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
+ ],
42
+ "full_attention_interval": 4,
43
+ "linear_num_key_heads": 16,
44
+ "linear_key_head_dim": 128,
45
+ "linear_num_value_heads": 16,
46
+ "linear_value_head_dim": 128,
47
+ "linear_conv_kernel_dim": 4,
48
+ "partial_rotary_factor": 0.25,
49
+ "tie_word_embeddings": true
50
+ }
int4/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e48b676aa0a3abcc7fd13372b45a502741aa4b50b563deb2101a811f33149d8b
3
+ size 424012292
int4/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
int4/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }
int8/config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "hidden_size": 1024,
3
+ "num_hidden_layers": 24,
4
+ "num_attention_heads": 8,
5
+ "num_key_value_heads": 2,
6
+ "head_dim": 256,
7
+ "intermediate_size": 3584,
8
+ "vocab_size": 248320,
9
+ "max_seq_len": 2048,
10
+ "rope_theta": 10000000,
11
+ "rms_norm_eps": 1e-06,
12
+ "eos_token_id": 248046,
13
+ "pad_token_id": 248044,
14
+ "quantization": "int8",
15
+ "model_type": "qwen3_5_text",
16
+ "layer_types": [
17
+ "linear_attention",
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "full_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "full_attention",
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
+ ],
42
+ "full_attention_interval": 4,
43
+ "linear_num_key_heads": 16,
44
+ "linear_key_head_dim": 128,
45
+ "linear_num_value_heads": 16,
46
+ "linear_value_head_dim": 128,
47
+ "linear_conv_kernel_dim": 4,
48
+ "partial_rotary_factor": 0.25,
49
+ "tie_word_embeddings": true
50
+ }
int8/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7417672b9bc10a825614819fa71e0fd98d4d7a715df04fa23dbdde60e59935d9
3
+ size 799959764
int8/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
3
+ size 19989343
int8/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }