Hugging Face's logo

RedHatAI
/
Meta-Llama-3-8B-Instruct-FP8-KV

Text Generation
Transformers
Safetensors
llama
fp8
vllm
conversational
text-generation-inference
Model card Files
xet
 Community
1
robgreenberg3 commited on
Commit
6ab84bb
·
verified ·
1 Parent(s): 4b1f72a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -2
README.md CHANGED
@@ -2,6 +2,8 @@
2
  tags:
3
  - fp8
4
  - vllm
 
 
5
  ---
6
 
7
  # Meta-Llama-3-8B-Instruct-FP8-KV
@@ -52,5 +54,4 @@ model.save_quantized(quantized_model_dir)
52
  ### Open LLM Leaderboard evaluation scores
53
  | | Meta-Llama-3-8B-Instruct | Meta-Llama-3-8B-Instruct-FP8 | Meta-Llama-3-8B-Instruct-FP8-KV<br>(this model) |
54
  | :------------------: | :----------------------: | :--------------------------: | :---------------------------------------------: |
55
- | gsm8k<br>5-shot | 75.44 | 74.37 | 74.98 |
56
-
 
2
  tags:
3
  - fp8
4
  - vllm
5
+ base_model:
6
+ - meta-llama/Meta-Llama-3-8B-Instruct
7
  ---
8
 
9
  # Meta-Llama-3-8B-Instruct-FP8-KV
 
54
  ### Open LLM Leaderboard evaluation scores
55
  | | Meta-Llama-3-8B-Instruct | Meta-Llama-3-8B-Instruct-FP8 | Meta-Llama-3-8B-Instruct-FP8-KV<br>(this model) |
56
  | :------------------: | :----------------------: | :--------------------------: | :---------------------------------------------: |
57
+ | gsm8k<br>5-shot | 75.44 | 74.37 | 74.98 |