Hugging Face's logo

timmyAlvice
/
house_md_transfer_learning

Text Generation
Transformers
Safetensors
gemma3_text
trl
sft
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
timmyAlvice commited on
Commit
89b6ede
·
verified ·
1 Parent(s): 5cad8c6

Upload Gemma3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +27 -21
  2. generation_config.json +11 -6
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,25 +1,28 @@
1
  {
2
- "_name_or_path": "HuggingFaceTB/SmolLM-1.7B-Instruct",
3
  "architectures": [
4
- "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
- "bos_token_id": 1,
9
- "eos_token_id": 2,
10
- "head_dim": 64,
11
- "hidden_act": "silu",
12
- "hidden_size": 2048,
 
 
 
 
 
 
13
  "initializer_range": 0.02,
14
- "intermediate_size": 8192,
15
- "max_position_embeddings": 2048,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 32,
19
- "num_hidden_layers": 24,
20
- "num_key_value_heads": 32,
21
- "pad_token_id": 2,
22
- "pretraining_tp": 1,
23
  "quantization_config": {
24
  "_load_in_4bit": true,
25
  "_load_in_8bit": false,
@@ -35,12 +38,15 @@
35
  "load_in_8bit": false,
36
  "quant_method": "bitsandbytes"
37
  },
38
- "rms_norm_eps": 1e-05,
 
 
39
  "rope_scaling": null,
40
- "rope_theta": 10000.0,
41
- "tie_word_embeddings": true,
 
42
  "torch_dtype": "float32",
43
- "transformers_version": "4.49.0",
44
  "use_cache": true,
45
- "vocab_size": 49152
46
  }
 
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": [
11
+ 1,
12
+ 106
13
+ ],
14
+ "final_logit_softcapping": null,
15
+ "head_dim": 256,
16
+ "hidden_activation": "gelu_pytorch_tanh",
17
+ "hidden_size": 1152,
18
  "initializer_range": 0.02,
19
+ "intermediate_size": 6912,
20
+ "max_position_embeddings": 32768,
21
+ "model_type": "gemma3_text",
22
+ "num_attention_heads": 4,
23
+ "num_hidden_layers": 26,
24
+ "num_key_value_heads": 1,
25
+ "pad_token_id": 0,
 
 
26
  "quantization_config": {
27
  "_load_in_4bit": true,
28
  "_load_in_8bit": false,
 
38
  "load_in_8bit": false,
39
  "quant_method": "bitsandbytes"
40
  },
41
+ "query_pre_attn_scalar": 256,
42
+ "rms_norm_eps": 1e-06,
43
+ "rope_local_base_freq": 10000,
44
  "rope_scaling": null,
45
+ "rope_theta": 1000000,
46
+ "sliding_window": 512,
47
+ "sliding_window_pattern": 6,
48
  "torch_dtype": "float32",
49
+ "transformers_version": "4.50.0",
50
  "use_cache": true,
51
+ "vocab_size": 262144
52
  }
generation_config.json CHANGED
@@ -1,8 +1,13 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "max_new_tokens": 40,
6
- "pad_token_id": 2,
7
- "transformers_version": "4.49.0"
 
 
 
 
 
8
  }
 
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": "4.50.0"
13
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:67929f43fc21c7eba3a0408a8052279ff9c9ff21e59544b67bd24e3b001fe324
3
- size 1302142406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f59dd1baa08acf807cc847c351e59b944dcbf04968518d377d62652486a7b8d6
3
+ size 1617811758