Hugging Face's logo

Aakash010
/
Gemma-3-4b-it-MathQA

Safetensors
gemma3
trl
sft
4-bit precision
bitsandbytes
Model card Files
xet
 Community
Aakash010 commited on
Commit
8946609
·
verified ·
1 Parent(s): 43cc599

Upload Gemma3ForConditionalGeneration

Browse files
Files changed (4) hide show
  1. README.md +3 -0
  2. config.json +123 -0
  3. generation_config.json +14 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -1,3 +1,6 @@
1
  ---
2
  license: apache-2.0
 
 
 
3
  ---
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - trl
5
+ - sft
6
  ---
config.json ADDED
@@ -0,0 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
+ ],
5
+ "boi_token_index": 255999,
6
+ "bos_token_id": 2,
7
+ "dtype": "float32",
8
+ "eoi_token_index": 256000,
9
+ "eos_token_id": 1,
10
+ "image_token_index": 262144,
11
+ "initializer_range": 0.02,
12
+ "mm_tokens_per_image": 256,
13
+ "model_type": "gemma3",
14
+ "pad_token_id": 0,
15
+ "quantization_config": {
16
+ "_load_in_4bit": true,
17
+ "_load_in_8bit": false,
18
+ "bnb_4bit_compute_dtype": "float16",
19
+ "bnb_4bit_quant_storage": "uint8",
20
+ "bnb_4bit_quant_type": "nf4",
21
+ "bnb_4bit_use_double_quant": false,
22
+ "llm_int8_enable_fp32_cpu_offload": false,
23
+ "llm_int8_has_fp16_weight": false,
24
+ "llm_int8_skip_modules": null,
25
+ "llm_int8_threshold": 6.0,
26
+ "load_in_4bit": true,
27
+ "load_in_8bit": false,
28
+ "quant_method": "bitsandbytes"
29
+ },
30
+ "text_config": {
31
+ "_sliding_window_pattern": 6,
32
+ "attention_bias": false,
33
+ "attention_dropout": 0.0,
34
+ "attn_logit_softcapping": null,
35
+ "bos_token_id": 2,
36
+ "dtype": "float16",
37
+ "eos_token_id": 1,
38
+ "final_logit_softcapping": null,
39
+ "head_dim": 256,
40
+ "hidden_activation": "gelu_pytorch_tanh",
41
+ "hidden_size": 2560,
42
+ "initializer_range": 0.02,
43
+ "intermediate_size": 10240,
44
+ "layer_types": [
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "full_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "sliding_attention",
56
+ "full_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "sliding_attention",
61
+ "sliding_attention",
62
+ "full_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "sliding_attention",
67
+ "sliding_attention",
68
+ "full_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "sliding_attention",
73
+ "sliding_attention",
74
+ "full_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "sliding_attention"
79
+ ],
80
+ "max_position_embeddings": 131072,
81
+ "model_type": "gemma3_text",
82
+ "num_attention_heads": 8,
83
+ "num_hidden_layers": 34,
84
+ "num_key_value_heads": 4,
85
+ "pad_token_id": 0,
86
+ "query_pre_attn_scalar": 256,
87
+ "rms_norm_eps": 1e-06,
88
+ "rope_parameters": {
89
+ "full_attention": {
90
+ "factor": 8.0,
91
+ "rope_theta": 1000000.0,
92
+ "rope_type": "linear"
93
+ },
94
+ "sliding_attention": {
95
+ "rope_theta": 10000.0,
96
+ "rope_type": "default"
97
+ }
98
+ },
99
+ "sliding_window": 1024,
100
+ "tie_word_embeddings": true,
101
+ "use_bidirectional_attention": false,
102
+ "use_cache": true,
103
+ "vocab_size": 262208
104
+ },
105
+ "tie_word_embeddings": true,
106
+ "transformers_version": "5.9.0",
107
+ "use_cache": false,
108
+ "vision_config": {
109
+ "attention_dropout": 0.0,
110
+ "dtype": "float16",
111
+ "hidden_act": "gelu_pytorch_tanh",
112
+ "hidden_size": 1152,
113
+ "image_size": 896,
114
+ "intermediate_size": 4304,
115
+ "layer_norm_eps": 1e-06,
116
+ "model_type": "siglip_vision_model",
117
+ "num_attention_heads": 16,
118
+ "num_channels": 3,
119
+ "num_hidden_layers": 27,
120
+ "patch_size": 14,
121
+ "vision_use_head": false
122
+ }
123
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 1,
8
+ 106
9
+ ],
10
+ "pad_token_id": 0,
11
+ "top_k": 64,
12
+ "top_p": 0.95,
13
+ "transformers_version": "5.9.0"
14
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2e2d427555b4b5975c7c944100a4b535d9db3693b94f2a18d19df5f9cb20bc
3
+ size 4757903358