Hugging Face's logo

EZCon
/
FastVLM-1.5B-8bit-mlx

Image-Text-to-Text
MLX
Safetensors
Transformers
llava_qwen2
text-generation
conversational
custom_code
8-bit precision
Model card Files
xet
 Community
1
hermeschen-ezcon commited on
Commit
8aa6194
·
verified ·
1 Parent(s): 9fe3198

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. README.md +1 -1
  2. preprocessor_config.json +1 -2
  3. processor_config.json +41 -0
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +7 -31
  6. vocab.json +0 -0
README.md CHANGED
@@ -7,7 +7,7 @@ tags:
7
  ---
8
 
9
  # EZCon/FastVLM-1.5B-8bit-mlx
10
- This model was converted to MLX format from [`apple/FastVLM-1.5B`]() using mlx-vlm version **0.3.9**.
11
  Refer to the [original model card](https://huggingface.co/apple/FastVLM-1.5B) for more details on the model.
12
  ## Use with mlx
13
 
 
7
  ---
8
 
9
  # EZCon/FastVLM-1.5B-8bit-mlx
10
+ This model was converted to MLX format from [`apple/FastVLM-1.5B`]() using mlx-vlm version **0.3.10**.
11
  Refer to the [original model card](https://huggingface.co/apple/FastVLM-1.5B) for more details on the model.
12
  ## Use with mlx
13
 
preprocessor_config.json CHANGED
@@ -14,7 +14,6 @@
14
  "do_center_crop": true,
15
  "do_convert_rgb": true,
16
  "do_normalize": true,
17
- "do_pad": null,
18
  "do_rescale": true,
19
  "do_resize": true,
20
  "image_mean": [
@@ -29,7 +28,6 @@
29
  1.0
30
  ],
31
  "input_data_format": null,
32
- "pad_size": null,
33
  "processor_class": "FastVLMProcessor",
34
  "resample": 3,
35
  "rescale_factor": 0.00392156862745098,
@@ -38,3 +36,4 @@
38
  "shortest_edge": 1024
39
  }
40
  }
 
 
14
  "do_center_crop": true,
15
  "do_convert_rgb": true,
16
  "do_normalize": true,
 
17
  "do_rescale": true,
18
  "do_resize": true,
19
  "image_mean": [
 
28
  1.0
29
  ],
30
  "input_data_format": null,
 
31
  "processor_class": "FastVLMProcessor",
32
  "resample": 3,
33
  "rescale_factor": 0.00392156862745098,
 
36
  "shortest_edge": 1024
37
  }
38
  }
39
+
processor_config.json CHANGED
@@ -2,5 +2,46 @@
2
  "auto_map": {
3
  "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
4
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "processor_class": "FastVLMProcessor"
6
  }
 
2
  "auto_map": {
3
  "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
4
  },
5
+ "image_processor": {
6
+ "auto_map": {
7
+ "AutoImageProcessor": "processing_fastvlm.FastVLMImageProcessor",
8
+ "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
9
+ },
10
+ "crop_size": {
11
+ "height": 1024,
12
+ "width": 1024
13
+ },
14
+ "data_format": "channels_first",
15
+ "default_to_square": false,
16
+ "device": null,
17
+ "disable_grouping": null,
18
+ "do_center_crop": true,
19
+ "do_convert_rgb": true,
20
+ "do_normalize": true,
21
+ "do_pad": null,
22
+ "do_rescale": true,
23
+ "do_resize": true,
24
+ "image_mean": [
25
+ 0.0,
26
+ 0.0,
27
+ 0.0
28
+ ],
29
+ "image_processor_type": "FastVLMImageProcessor",
30
+ "image_seq_length": null,
31
+ "image_std": [
32
+ 1.0,
33
+ 1.0,
34
+ 1.0
35
+ ],
36
+ "input_data_format": null,
37
+ "pad_size": null,
38
+ "processor_class": "FastVLMProcessor",
39
+ "resample": 3,
40
+ "rescale_factor": 0.00392156862745098,
41
+ "return_tensors": null,
42
+ "size": {
43
+ "shortest_edge": 1024
44
+ }
45
+ },
46
  "processor_class": "FastVLMProcessor"
47
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22a32bc7af1fc17ed370988966140a379f0421b0a508e4ae3fe4bcf7a86644e1
3
- size 11413100
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec23d32bfebacd1282375a053db63076675f588b20c7df4b075286851b0675a5
3
+ size 11413376
tokenizer_config.json CHANGED
@@ -1,43 +1,19 @@
1
  {
2
  "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "151643": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "151644": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "151645": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- }
28
- },
29
- "additional_special_tokens": [
30
- "<|im_start|>",
31
- "<|im_end|>"
32
- ],
33
  "auto_map": {
34
  "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
35
  },
 
36
  "bos_token": null,
37
  "clean_up_tokenization_spaces": false,
38
  "eos_token": "<|im_end|>",
39
  "errors": "replace",
40
- "extra_special_tokens": {},
 
 
 
 
41
  "model_max_length": 8192,
42
  "pad_token": "<|endoftext|>",
43
  "padding_side": "right",
 
1
  {
2
  "add_prefix_space": false,
3
+ "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "auto_map": {
5
  "AutoProcessor": "processing_fastvlm.FastVLMProcessor"
6
  },
7
+ "backend": "tokenizers",
8
  "bos_token": null,
9
  "clean_up_tokenization_spaces": false,
10
  "eos_token": "<|im_end|>",
11
  "errors": "replace",
12
+ "extra_special_tokens": [
13
+ "<|im_start|>",
14
+ "<|im_end|>"
15
+ ],
16
+ "is_local": true,
17
  "model_max_length": 8192,
18
  "pad_token": "<|endoftext|>",
19
  "padding_side": "right",
vocab.json CHANGED
The diff for this file is too large to render. See raw diff