shuyuej commited on
Commit
b6d49b5
1 Parent(s): d331dbc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -3
README.md CHANGED
@@ -1,3 +1,32 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
4
+
5
+ # The Quantized LLaMA 3.1 70B Instruct Model
6
+
7
+ Original Base Model: `meta-llama/Meta-Llama-3.1-70B`.<br>
8
+ Link: [https://huggingface.co/meta-llama/Meta-Llama-3.1-70B](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B)
9
+
10
+ ## Special Notice
11
+ Please note that this is a relatively smaller model by setting `group_size=1024`.<be>
12
+ For the standard `group_size=128` model, please check here, `shuyuej/Meta-Llama-3.1-70B-GPTQ`: [https://huggingface.co/shuyuej/Meta-Llama-3.1-70B-GPTQ](https://huggingface.co/shuyuej/Meta-Llama-3.1-70B-GPTQ)
13
+
14
+ ## Quantization Configurations
15
+ ```
16
+ "quantization_config": {
17
+ "bits": 4,
18
+ "checkpoint_format": "gptq",
19
+ "damp_percent": 0.01,
20
+ "desc_act": true,
21
+ "group_size": 1024,
22
+ "model_file_base_name": null,
23
+ "model_name_or_path": null,
24
+ "quant_method": "gptq",
25
+ "static_groups": false,
26
+ "sym": true,
27
+ "true_sequential": true
28
+ },
29
+ ```
30
+
31
+ ## Source Codes
32
+ Source Codes: [https://github.com/vkola-lab/medpodgpt/tree/main/quantization](https://github.com/vkola-lab/medpodgpt/tree/main/quantization).