h4shy commited on
Commit
1d9839f
·
verified ·
1 Parent(s): 53a55a0

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma3nForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "eos_token_id": 1,
9
+ "head_dim": 256,
10
+ "hidden_act": "gelu_pytorch_tanh",
11
+ "hidden_activation": null,
12
+ "hidden_size": 2096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma3n",
17
+ "num_attention_heads": 16,
18
+ "num_heads": 16,
19
+ "num_hidden_layers": 28,
20
+ "num_key_value_heads": 16,
21
+ "num_layers": 12,
22
+ "pad_token_id": 0,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_theta": 10000.0,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.52.3",
27
+ "use_cache": true,
28
+ "vocab_size": 256000
29
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d4bd0d507411c2b099678660c226c6ed80d1f67b881a39351d075befa5a83e
3
+ size 3900211536
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:195161db8732664acb240a7da8540f83e15596b659c94dfe9323f6f599dcb559
3
+ size 3900264327
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6daa52d93d7aad10e8388bd526c4e501d914b47177398d1d9621f1fe48438c7
3
+ size 4683319
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"tokenizer_class": "LlamaTokenizer", "bos_token": "<bos>", "eos_token": "<eos>", "model_max_length": 8192, "pad_token": "<pad>", "unk_token": "<unk>"}