ptrdvn commited on
Commit
2c1308e
1 Parent(s): 948c9cd

Upload of AutoGPTQ quantized model

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/llm_training/axolotl/all_search_calling_1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bits": 4,
20
+ "damp_percent": 0.01,
21
+ "desc_act": false,
22
+ "group_size": 128,
23
+ "is_marlin_format": false,
24
+ "model_file_base_name": null,
25
+ "model_name_or_path": null,
26
+ "quant_method": "gptq",
27
+ "static_groups": false,
28
+ "sym": true,
29
+ "true_sequential": true
30
+ },
31
+ "rms_norm_eps": 1e-05,
32
+ "rope_theta": 1000000.0,
33
+ "sliding_window": null,
34
+ "tie_word_embeddings": false,
35
+ "torch_dtype": "float16",
36
+ "transformers_version": "4.38.2",
37
+ "use_cache": false,
38
+ "vocab_size": 32000
39
+ }
gptq_model-4bit-128g.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1729065618023084bb90ea1d49268814bea386e1bf3a97bf0042aed38de06945
3
+ size 4158662248
quantize_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 128,
4
+ "damp_percent": 0.01,
5
+ "desc_act": false,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": null,
10
+ "model_file_base_name": null,
11
+ "is_marlin_format": false,
12
+ "quant_method": "gptq"
13
+ }