Elcaida commited on
Commit
d9f2adb
·
verified ·
1 Parent(s): 1487ed7

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Mistral3ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": 1,
6
+ "eos_token_id": 2,
7
+ "image_token_index": 10,
8
+ "model_type": "mistral3",
9
+ "multimodal_projector_bias": false,
10
+ "pad_token_id": 11,
11
+ "projector_hidden_act": "gelu",
12
+ "quantization_config": {
13
+ "bnb_4bit_compute_dtype": "bfloat16",
14
+ "bnb_4bit_quant_type": "nf4",
15
+ "bnb_4bit_use_double_quant": true,
16
+ "llm_int8_enable_fp32_cpu_offload": false,
17
+ "llm_int8_has_fp16_weight": false,
18
+ "llm_int8_skip_modules": null,
19
+ "llm_int8_threshold": 6.0,
20
+ "load_in_4bit": true,
21
+ "load_in_8bit": false,
22
+ "quant_method": "bitsandbytes"
23
+ },
24
+ "spatial_merge_size": 2,
25
+ "text_config": {
26
+ "attention_dropout": 0.0,
27
+ "head_dim": 128,
28
+ "hidden_act": "silu",
29
+ "hidden_size": 5120,
30
+ "initializer_range": 0.02,
31
+ "intermediate_size": 32768,
32
+ "max_position_embeddings": 131072,
33
+ "model_type": "mistral",
34
+ "num_attention_heads": 32,
35
+ "num_hidden_layers": 40,
36
+ "num_key_value_heads": 8,
37
+ "rms_norm_eps": 1e-05,
38
+ "rope_scaling": null,
39
+ "rope_theta": 1000000000.0,
40
+ "sliding_window": null,
41
+ "torch_dtype": "bfloat16",
42
+ "use_cache": true,
43
+ "vocab_size": 131072
44
+ },
45
+ "torch_dtype": "bfloat16",
46
+ "transformers_version": "4.53.1",
47
+ "unsloth_fixed": true,
48
+ "unsloth_version": "2025.6.8",
49
+ "vision_config": {
50
+ "attention_dropout": 0.0,
51
+ "head_dim": 64,
52
+ "hidden_act": "silu",
53
+ "hidden_size": 1024,
54
+ "image_size": 1540,
55
+ "initializer_range": 0.02,
56
+ "intermediate_size": 4096,
57
+ "model_type": "pixtral",
58
+ "num_attention_heads": 16,
59
+ "num_channels": 3,
60
+ "num_hidden_layers": 24,
61
+ "patch_size": 14,
62
+ "rope_theta": 10000.0,
63
+ "torch_dtype": "bfloat16"
64
+ },
65
+ "vision_feature_layer": -1
66
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 1,
3
+ "do_sample": true,
4
+ "eos_token_id": 2,
5
+ "max_length": 131072,
6
+ "pad_token_id": 11,
7
+ "temperature": 0.15,
8
+ "transformers_version": "4.53.1"
9
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c805c89f28ebb3d1bcb60e5b6a10803e38b1f2e0865c29626c1a78d07ff5ce2
3
+ size 4928311458
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf57c457ac6109b469ef238cb5907a21985c5c77ceac73f3330b7b83e468fa39
3
+ size 4960910798
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe1bd437b94129cd0869be5f6ff8a6f0046e382a403851eee987436a64cf270
3
+ size 4669307485
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff