wooder commited on
Commit
470e04c
·
verified ·
1 Parent(s): eec1cf9

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json CHANGED
@@ -1,34 +1,46 @@
1
  {
2
- "_name_or_path": "unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit",
3
- "architectures": [
4
- "MllamaForConditionalGeneration"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  ],
6
- "image_token_index": 128256,
7
- "model_type": "mllama",
8
- "pad_token_id": 128004,
9
- "text_config": {
10
- "eos_token_id": [
11
- 128001,
12
- 128008,
13
- 128009
14
- ],
15
- "model_type": "mllama_text_model",
16
- "rope_scaling": {
17
- "factor": 8.0,
18
- "high_freq_factor": 4.0,
19
- "low_freq_factor": 1.0,
20
- "original_max_position_embeddings": 8192,
21
- "rope_type": "llama3"
22
- },
23
- "torch_dtype": "bfloat16"
24
  },
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.49.0",
27
- "unsloth_fixed": true,
28
- "unsloth_version": "2025.2.15",
29
- "vision_config": {
30
- "image_size": 560,
31
- "model_type": "mllama_vision_model",
32
- "torch_dtype": "bfloat16"
33
- }
34
- }
 
 
 
1
  {
2
+ "_name_or_path": "unsloth/llama-3.2-11b-vision-instruct-unsloth-bnb-4bit",
3
+ "architectures": [
4
+ "MllamaForConditionalGeneration"
5
+ ],
6
+ "image_token_index": 128256,
7
+ "model_type": "mllama",
8
+ "pad_token_id": 128004,
9
+ "quantization_config": {
10
+ "bnb_4bit_compute_dtype": "bfloat16",
11
+ "bnb_4bit_quant_type": "nf4",
12
+ "bnb_4bit_use_double_quant": true,
13
+ "llm_int8_enable_fp32_cpu_offload": false,
14
+ "llm_int8_has_fp16_weight": false,
15
+ "llm_int8_skip_modules": null,
16
+ "llm_int8_threshold": 6.0,
17
+ "load_in_4bit": true,
18
+ "load_in_8bit": false,
19
+ "quant_method": "bitsandbytes"
20
+ },
21
+ "text_config": {
22
+ "eos_token_id": [
23
+ 128001,
24
+ 128008,
25
+ 128009
26
  ],
27
+ "model_type": "mllama_text_model",
28
+ "rope_scaling": {
29
+ "factor": 8.0,
30
+ "high_freq_factor": 4.0,
31
+ "low_freq_factor": 1.0,
32
+ "original_max_position_embeddings": 8192,
33
+ "rope_type": "llama3"
 
 
 
 
 
 
 
 
 
 
 
34
  },
35
+ "torch_dtype": "bfloat16"
36
+ },
37
+ "torch_dtype": "bfloat16",
38
+ "transformers_version": "4.49.0",
39
+ "unsloth_fixed": true,
40
+ "unsloth_version": "2025.2.15",
41
+ "vision_config": {
42
+ "image_size": 560,
43
+ "model_type": "mllama_vision_model",
44
+ "torch_dtype": "bfloat16"
45
+ }
46
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:074ef31020bb19f3db9dbf8da7cac31771b05770e4f2f6e25501c04873c5eed5
3
+ size 4971535111
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe472b601690f76bc8b781b2094ec22de6d25fb1d8280b9c5eed4842c4c2203
3
+ size 2937067202
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff