Hugging Face's logo

kingabzpro
/
Gemma-3-4B-Fin-QA-Reasoning

Text Generation
Transformers
Safetensors
English
gemma3
image-text-to-text
text-generation-inference
trl
sft
finance
conversational
Model card Files Community
kingabzpro commited on
Commit
45bffc6
·
verified ·
1 Parent(s): 2a43415

Upload Gemma3ForConditionalGeneration

Browse files
Files changed (6) hide show
  1. README.md +2 -0
  2. config.json +55 -30
  3. generation_config.json +4 -1
  4. model-00001-of-00002.safetensors +2 -2
  5. model-00002-of-00002.safetensors +2 -2
  6. model.safetensors.index.json +0 -0
README.md CHANGED
@@ -5,6 +5,8 @@ tags:
5
  - transformers
6
  - unsloth
7
  - gemma3
 
 
8
  license: apache-2.0
9
  language:
10
  - en
 
5
  - transformers
6
  - unsloth
7
  - gemma3
8
+ - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json CHANGED
@@ -1,37 +1,62 @@
1
  {
2
  "architectures": [
3
- "Gemma3ForCausalLM"
4
  ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "attn_logit_softcapping": null,
8
- "bos_token_id": 2,
9
- "cache_implementation": "hybrid",
10
- "eos_token_id": 1,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 2560,
15
  "initializer_range": 0.02,
16
- "intermediate_size": 10240,
17
- "max_position_embeddings": 131072,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 8,
20
- "num_hidden_layers": 34,
21
- "num_key_value_heads": 4,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000.0,
26
- "rope_scaling": {
27
- "factor": 8.0,
28
- "rope_type": "linear"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  },
30
- "rope_theta": 1000000.0,
31
- "sliding_window": 1024,
32
- "sliding_window_pattern": 6,
33
- "torch_dtype": "float16",
34
  "transformers_version": "4.50.0.dev0",
35
- "use_cache": true,
36
- "vocab_size": 262208
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
 
1
  {
2
  "architectures": [
3
+ "Gemma3ForConditionalGeneration"
4
  ],
5
+ "boi_token_index": 255999,
6
+ "eoi_token_index": 256000,
7
+ "eos_token_id": [
8
+ 1,
9
+ 106
10
+ ],
11
+ "image_token_index": 262144,
 
 
 
12
  "initializer_range": 0.02,
13
+ "mm_tokens_per_image": 256,
14
+ "model_type": "gemma3",
15
+ "text_config": {
16
+ "attention_bias": false,
17
+ "attention_dropout": 0.0,
18
+ "attn_logit_softcapping": null,
19
+ "cache_implementation": "hybrid",
20
+ "final_logit_softcapping": null,
21
+ "head_dim": 256,
22
+ "hidden_activation": "gelu_pytorch_tanh",
23
+ "hidden_size": 2560,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 10240,
26
+ "max_position_embeddings": 131072,
27
+ "model_type": "gemma3_text",
28
+ "num_attention_heads": 8,
29
+ "num_hidden_layers": 34,
30
+ "num_key_value_heads": 4,
31
+ "query_pre_attn_scalar": 256,
32
+ "rms_norm_eps": 1e-06,
33
+ "rope_local_base_freq": 10000.0,
34
+ "rope_scaling": {
35
+ "factor": 8.0,
36
+ "rope_type": "linear"
37
+ },
38
+ "rope_theta": 1000000.0,
39
+ "sliding_window": 1024,
40
+ "sliding_window_pattern": 6,
41
+ "torch_dtype": "float32",
42
+ "use_cache": true,
43
+ "vocab_size": 262208
44
  },
45
+ "torch_dtype": "bfloat16",
 
 
 
46
  "transformers_version": "4.50.0.dev0",
47
+ "vision_config": {
48
+ "attention_dropout": 0.0,
49
+ "hidden_act": "gelu_pytorch_tanh",
50
+ "hidden_size": 1152,
51
+ "image_size": 896,
52
+ "intermediate_size": 4304,
53
+ "layer_norm_eps": 1e-06,
54
+ "model_type": "siglip_vision_model",
55
+ "num_attention_heads": 16,
56
+ "num_channels": 3,
57
+ "num_hidden_layers": 27,
58
+ "patch_size": 14,
59
+ "torch_dtype": "float32",
60
+ "vision_use_head": false
61
+ }
62
  }
generation_config.json CHANGED
@@ -2,7 +2,10 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
5
- "eos_token_id": 1,
 
 
 
6
  "pad_token_id": 0,
7
  "transformers_version": "4.50.0.dev0"
8
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 2,
4
  "cache_implementation": "hybrid",
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
  "pad_token_id": 0,
10
  "transformers_version": "4.50.0.dev0"
11
  }
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be954f5cbcc5355e1228bfcdd9f56ffc51c9eef63e3cbac6bffb1908a6aa8593
3
- size 4961251568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2f71603466be84ef5b73ed41e917257a8c6392e1f97eb9db6bfa6e1a3a1869
3
+ size 4957678832
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9933d9cf65f431173fe7f7e1b50e24485ad4c3f4aafbad834d0c2377601553d0
3
- size 3639025080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3bfd409c056d9b214d6b50f5c484b83189ec1a90530ae9b4207039e83b1fd5
3
+ size 4167311288
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff