Hugging Face's logo

MustafaIbrahim
/
gemma-medQa-v1.3

Text Generation
Transformers
Safetensors
English
gemma3_text
text-generation-inference
unsloth
trl
sft
conversational
4-bit precision
bitsandbytes
Model card Files Community
MustafaIbrahim commited on
Commit
61a172d
·
verified ·
1 Parent(s): 8c6a040

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (3) hide show
  1. README.md +2 -0
  2. config.json +47 -35
  3. model.safetensors +2 -2
README.md CHANGED
@@ -5,6 +5,8 @@ tags:
5
  - transformers
6
  - unsloth
7
  - gemma3_text
 
 
8
  license: apache-2.0
9
  language:
10
  - en
 
5
  - transformers
6
  - unsloth
7
  - gemma3_text
8
+ - trl
9
+ - sft
10
  license: apache-2.0
11
  language:
12
  - en
config.json CHANGED
@@ -1,36 +1,48 @@
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": 106,
11
- "final_logit_softcapping": null,
12
- "head_dim": 256,
13
- "hidden_activation": "gelu_pytorch_tanh",
14
- "hidden_size": 1152,
15
- "initializer_range": 0.02,
16
- "intermediate_size": 6912,
17
- "max_position_embeddings": 32768,
18
- "model_type": "gemma3_text",
19
- "num_attention_heads": 4,
20
- "num_hidden_layers": 26,
21
- "num_key_value_heads": 1,
22
- "pad_token_id": 0,
23
- "query_pre_attn_scalar": 256,
24
- "rms_norm_eps": 1e-06,
25
- "rope_local_base_freq": 10000,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000,
28
- "sliding_window": 512,
29
- "sliding_window_pattern": 6,
30
- "torch_dtype": "float16",
31
- "transformers_version": "4.50.0.dev0",
32
- "unsloth_fixed": true,
33
- "unsloth_version": "2025.3.14",
34
- "use_cache": true,
35
- "vocab_size": 262144
36
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 106,
11
+ "final_logit_softcapping": null,
12
+ "head_dim": 256,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 1152,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 6912,
17
+ "max_position_embeddings": 32768,
18
+ "model_type": "gemma3_text",
19
+ "num_attention_heads": 4,
20
+ "num_hidden_layers": 26,
21
+ "num_key_value_heads": 1,
22
+ "pad_token_id": 0,
23
+ "quantization_config": {
24
+ "bnb_4bit_compute_dtype": "float16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": true,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "query_pre_attn_scalar": 256,
36
+ "rms_norm_eps": 1e-06,
37
+ "rope_local_base_freq": 10000,
38
+ "rope_scaling": null,
39
+ "rope_theta": 1000000,
40
+ "sliding_window": 512,
41
+ "sliding_window_pattern": 6,
42
+ "torch_dtype": "float16",
43
+ "transformers_version": "4.50.0.dev0",
44
+ "unsloth_fixed": true,
45
+ "unsloth_version": "2025.3.14",
46
+ "use_cache": true,
47
+ "vocab_size": 262144
48
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3159dcd4cadcaa2046a47e8f9086468a1010f168bda5adef2afdce3186b9022c
3
- size 1999810800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f06ea3a58607ca4a0e0d948c52cb481b78771c43c5677901936a60840f00b8ed
3
+ size 1000024374