Hugging Face's logo

NotoriousH2
/
gemma-3-1b-it-Math

Text Generation
Transformers
Safetensors
gemma3_text
conversational
text-generation-inference
Model card Files
xet
 Community
NotoriousH2 commited on
Commit
db739ad
·
verified ·
1 Parent(s): 5446cde

Upload Gemma3ForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +3 -6
  2. generation_config.json +2 -1
  3. model.safetensors +1 -1
config.json CHANGED
@@ -9,10 +9,7 @@
9
  "bos_token_id": 2,
10
  "cache_implementation": "hybrid",
11
  "dtype": "bfloat16",
12
- "eos_token_id": [
13
- 1,
14
- 106
15
- ],
16
  "final_logit_softcapping": null,
17
  "head_dim": 256,
18
  "hidden_activation": "gelu_pytorch_tanh",
@@ -52,7 +49,7 @@
52
  "num_attention_heads": 4,
53
  "num_hidden_layers": 26,
54
  "num_key_value_heads": 1,
55
- "pad_token_id": 0,
56
  "query_pre_attn_scalar": 256,
57
  "rms_norm_eps": 1e-06,
58
  "rope_local_base_freq": 10000,
@@ -62,6 +59,6 @@
62
  "sliding_window_pattern": 6,
63
  "transformers_version": "4.57.3",
64
  "use_bidirectional_attention": false,
65
- "use_cache": true,
66
  "vocab_size": 262144
67
  }
 
9
  "bos_token_id": 2,
10
  "cache_implementation": "hybrid",
11
  "dtype": "bfloat16",
12
+ "eos_token_id": 1,
 
 
 
13
  "final_logit_softcapping": null,
14
  "head_dim": 256,
15
  "hidden_activation": "gelu_pytorch_tanh",
 
49
  "num_attention_heads": 4,
50
  "num_hidden_layers": 26,
51
  "num_key_value_heads": 1,
52
+ "pad_token_id": 1,
53
  "query_pre_attn_scalar": 256,
54
  "rms_norm_eps": 1e-06,
55
  "rope_local_base_freq": 10000,
 
59
  "sliding_window_pattern": 6,
60
  "transformers_version": "4.57.3",
61
  "use_bidirectional_attention": false,
62
+ "use_cache": false,
63
  "vocab_size": 262144
64
  }
generation_config.json CHANGED
@@ -3,10 +3,11 @@
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": "4.57.3"
 
3
  "cache_implementation": "hybrid",
4
  "do_sample": true,
5
  "eos_token_id": [
6
+ 1,
7
  1,
8
  106
9
  ],
10
+ "pad_token_id": 1,
11
  "top_k": 64,
12
  "top_p": 0.95,
13
  "transformers_version": "4.57.3"
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d4ef8d71c14db7e448a09ebe891cfb6bf32c57a9b44499ae0d1c098e48516b6
3
  size 1999811208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fa46f2ee0ff78b3929eb742ecb774db451a64233958dc9205337265625c88aa
3
  size 1999811208