Hugging Face's logo

ZhangShenao
/
SELM-Llama-3-8B-Instruct-iter-2

Text Generation
Transformers
Safetensors
llama
alignment-handbook
dpo
trl
selm
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
ZhangShenao commited on
Commit
cff2b44
•
1 Parent(s): 2b940bc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -47,10 +47,10 @@ This model is a fine-tuned version of [ZhangShenao/SELM-Llama-3-8B-Instruct-iter
47
 
48
  |                                        | AlpacaEval 2.0 (LC WR) | MT-Bench (Average) |
49
  |----------------------------------------|------------------------|--------------------|
50
- | [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) |                   24.31         |                7.93       |
51
- | [SELM-Llama-3-8B-Instruct-iter-1](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-1) |                   32.02         |                7.92       |
52
- | [SELM-Llama-3-8B-Instruct-iter-2](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-2) |                   35.65         |                8.09      |
53
  | [SELM-Llama-3-8B-Instruct-iter-3](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-3) |                   33.47          |                8.29       |
 
 
 
54
 
55
 
56
  ### Training hyperparameters
 
47
 
48
  |                                        | AlpacaEval 2.0 (LC WR) | MT-Bench (Average) |
49
  |----------------------------------------|------------------------|--------------------|
 
 
 
50
  | [SELM-Llama-3-8B-Instruct-iter-3](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-3) |                   33.47          |                8.29       |
51
+ | [SELM-Llama-3-8B-Instruct-iter-2](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-2) |                   35.65         |                8.09      |
52
+ | [SELM-Llama-3-8B-Instruct-iter-1](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-1) |                   32.02         |                7.92       |
53
+ | [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) |                   24.31         |                7.93       |
54
 
55
 
56
  ### Training hyperparameters