hugginglaoda commited on
Commit
56ebdf9
1 Parent(s): b9fd72b

AutoGPTQ model for facebook/opt-125m: 4bits, gr128, desc_act=False

Browse files
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "opt-125m-4bit",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "torch_dtype": "float16",
27
+ "transformers_version": "4.31.0",
28
+ "use_cache": true,
29
+ "vocab_size": 50272,
30
+ "word_embed_proj_dim": 768
31
+ }
gptq_model-4bit-128g.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5716b0d566350cbaa6e84159c812f73ddcbb1a3207609568c3b9db2441a81cb9
3
+ size 125211919
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfec0c6e3d947f05c368cebb92fbf41b42d34edd6324121702763694def950e4
3
+ size 242792208
quantize_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "sym": true,
7
+ "true_sequential": true,
8
+ "model_name_or_path": "opt-125m-4bit",
9
+ "model_file_base_name": "gptq_model-4bit-128g"
10
+ }