Hugging Face's logo

ModelCloud
/
Meta-Llama-3.1-8B-Instruct-gptq-4bit

Text Generation
Transformers
Safetensors
llama
gptq
4bit
int4
gptqmodel
modelcloud
llama-3.1
8b
instruct
conversational
text-generation-inference
Inference Endpoints
4-bit precision
Model card Files Community
7

Upload folder using huggingface_hub

#7
by lrl-modelcloud - opened
base: refs/heads/main
←
from: refs/pr/7
Discussion Files changed
+7
-6
Files changed (3) hide show
  1. config.json +4 -3
  2. model.safetensors +1 -1
  3. quantize_config.json +2 -2
config.json CHANGED
@@ -21,16 +21,17 @@
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
 
24
  "pretraining_tp": 1,
25
  "quantization_config": {
26
  "bits": 4,
27
  "checkpoint_format": "gptq",
28
  "damp_percent": 0.005,
29
- "desc_act": true,
30
  "group_size": 128,
31
  "lm_head": false,
32
  "meta": {
33
- "quantizer": "gptqmodel:0.9.9-dev0"
34
  },
35
  "model_file_base_name": null,
36
  "model_name_or_path": null,
@@ -53,4 +54,4 @@
53
  "transformers_version": "4.44.0.dev0",
54
  "use_cache": true,
55
  "vocab_size": 128256
56
- }
 
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
24
+ "pad_token_id": 128004,
25
  "pretraining_tp": 1,
26
  "quantization_config": {
27
  "bits": 4,
28
  "checkpoint_format": "gptq",
29
  "damp_percent": 0.005,
30
+ "desc_act": false,
31
  "group_size": 128,
32
  "lm_head": false,
33
  "meta": {
34
+ "quantizer": "gptqmodel:0.9.10-dev0"
35
  },
36
  "model_file_base_name": null,
37
  "model_name_or_path": null,
 
54
  "transformers_version": "4.44.0.dev0",
55
  "use_cache": true,
56
  "vocab_size": 128256
57
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f382a2071ccb88ad4f920cf2924e531909c35071dd5ee9c459ae0a5ed3761a
3
  size 5732943672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22ead7ca212f7be98881c8842ae9146e7362ecbbcc2ae69ff1f6a19a802972de
3
  size 5732943672
quantize_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "bits": 4,
3
  "group_size": 128,
4
- "desc_act": true,
5
  "static_groups": false,
6
  "sym": true,
7
  "lm_head": false,
@@ -12,6 +12,6 @@
12
  "quant_method": "gptq",
13
  "checkpoint_format": "gptq",
14
  "meta": {
15
- "quantizer": "gptqmodel:0.9.9-dev0"
16
  }
17
  }
 
1
  {
2
  "bits": 4,
3
  "group_size": 128,
4
+ "desc_act": false,
5
  "static_groups": false,
6
  "sym": true,
7
  "lm_head": false,
 
12
  "quant_method": "gptq",
13
  "checkpoint_format": "gptq",
14
  "meta": {
15
+ "quantizer": "gptqmodel:0.9.10-dev0"
16
  }
17
  }