Hugging Face's logo

dqwdqweqw
/
lmsys-chat-1m-lora_model

Any-to-Any
Transformers
PyTorch
English
gemma3
text-generation-inference
unsloth
trl
4-bit precision
bitsandbytes
Model card Files
xet
Community
1
dqwdqweqw commited on
Commit
f4738e0
·
verified ·
1 Parent(s): 61e9d3c

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (6) hide show
  1. config.json +125 -0
  2. generation_config.json +13 -0
  3. pytorch_model-00001-of-00003.bin +3 -0
  4. pytorch_model-00002-of-00003.bin +3 -0
  5. pytorch_model-00003-of-00003.bin +3 -0
  6. pytorch_model.bin.index.json +0 -0
config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "eoi_token_index": 256000,
8
+ "eos_token_id": 106,
9
+ "image_token_index": 262144,
10
+ "initializer_range": 0.02,
11
+ "mm_tokens_per_image": 256,
12
+ "model_type": "gemma3",
13
+ "pad_token_id": 0,
14
+ "quantization_config": {
15
+ "bnb_4bit_compute_dtype": "float16",
16
+ "bnb_4bit_quant_type": "nf4",
17
+ "bnb_4bit_use_double_quant": true,
18
+ "llm_int8_enable_fp32_cpu_offload": false,
19
+ "llm_int8_has_fp16_weight": false,
20
+ "llm_int8_skip_modules": null,
21
+ "llm_int8_threshold": 6.0,
22
+ "load_in_4bit": true,
23
+ "load_in_8bit": false,
24
+ "quant_method": "bitsandbytes"
25
+ },
26
+ "text_config": {
27
+ "attention_bias": false,
28
+ "attention_dropout": 0.0,
29
+ "attn_logit_softcapping": null,
30
+ "cache_implementation": "hybrid",
31
+ "final_logit_softcapping": null,
32
+ "head_dim": 256,
33
+ "hidden_activation": "gelu_pytorch_tanh",
34
+ "hidden_size": 3840,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 15360,
37
+ "layer_types": [
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "full_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "full_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "full_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "full_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention",
79
+ "full_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "sliding_attention",
85
+ "full_attention"
86
+ ],
87
+ "max_position_embeddings": 131072,
88
+ "model_type": "gemma3_text",
89
+ "num_attention_heads": 16,
90
+ "num_hidden_layers": 48,
91
+ "num_key_value_heads": 8,
92
+ "query_pre_attn_scalar": 256,
93
+ "rms_norm_eps": 1e-06,
94
+ "rope_local_base_freq": 10000.0,
95
+ "rope_scaling": {
96
+ "factor": 8.0,
97
+ "rope_type": "linear"
98
+ },
99
+ "rope_theta": 1000000.0,
100
+ "sliding_window": 1024,
101
+ "sliding_window_pattern": 6,
102
+ "torch_dtype": "float16",
103
+ "use_cache": true,
104
+ "vocab_size": 262208
105
+ },
106
+ "torch_dtype": "float16",
107
+ "transformers_version": "4.53.1",
108
+ "unsloth_fixed": true,
109
+ "unsloth_version": "2025.7.3",
110
+ "vision_config": {
111
+ "attention_dropout": 0.0,
112
+ "hidden_act": "gelu_pytorch_tanh",
113
+ "hidden_size": 1152,
114
+ "image_size": 896,
115
+ "intermediate_size": 4304,
116
+ "layer_norm_eps": 1e-06,
117
+ "model_type": "siglip_vision_model",
118
+ "num_attention_heads": 16,
119
+ "num_channels": 3,
120
+ "num_hidden_layers": 27,
121
+ "patch_size": 14,
122
+ "torch_dtype": "float16",
123
+ "vision_use_head": false
124
+ }
125
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.53.1"
13
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed0e9d1891be8846ca76f125aaea7f3bb22d71dcd2346d44a7bad5d8b216d245
3
+ size 4955667625
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcd234c6d1afcaed48ad2f50f94fdad4447fc30d1921c97900a36a0f1d0d4e06
3
+ size 4975470602
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c62aa8cb1914c15b4363ae89223d7c713ee4dcf28db5433dc932011baed3867
3
+ size 2837269353
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff