CocoRoF commited on
Commit
8b6fb56
·
verified ·
1 Parent(s): d1b97d4

Upload Gemma3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +37 -0
  2. generation_config.json +13 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "query_pre_attn_scalar": 256,
27
+ "rms_norm_eps": 1e-06,
28
+ "rope_local_base_freq": 10000,
29
+ "rope_scaling": null,
30
+ "rope_theta": 1000000,
31
+ "sliding_window": 512,
32
+ "sliding_window_pattern": 6,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.50.0",
35
+ "use_cache": true,
36
+ "vocab_size": 262144
37
+ }
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": "4.50.0"
13
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6db35c863472398b5622e68c1be7181527838796fe434096d257d700d2b6bbc3
3
+ size 2603791264