Alirezamp commited on
Commit
3c17cd6
1 Parent(s): 5e4031c

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +37 -0
  2. generation_config.json +8 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./quantized_model",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_activation": "gelu_pytorch_tanh",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 16384,
16
+ "max_position_embeddings": 8192,
17
+ "model_type": "gemma",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 18,
20
+ "num_key_value_heads": 1,
21
+ "pad_token_id": 0,
22
+ "quantization_config": {
23
+ "bits": 4,
24
+ "group_size": 128,
25
+ "modules_to_not_convert": null,
26
+ "quant_method": "awq",
27
+ "version": "gemm",
28
+ "zero_point": true
29
+ },
30
+ "rms_norm_eps": 1e-06,
31
+ "rope_scaling": null,
32
+ "rope_theta": 10000.0,
33
+ "torch_dtype": "bfloat16",
34
+ "transformers_version": "4.42.3",
35
+ "use_cache": false,
36
+ "vocab_size": 256000
37
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "do_sample": true,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.42.3"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cd2f9ab6e3545b5755018faad68975ee051b52e3bde8858956156eda531d9b1
3
+ size 3126961880