Hugging Face's logo

amd
/
Llama-3.3-70B-Instruct-FP8-KV

Safetensors
llama
fp8
Model card Files Community
bowenbaoamd commited on
Commit
588fc7e
·
verified ·
1 Parent(s): b1d7e1f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -7,7 +7,7 @@ base_model: meta-llama/Llama-3.3-70B-Instruct
7
 
8
  # Llama-3.3-70B-Instruct-FP8-KV
9
  - ## Introduction
10
- This model was created by applying [Quark](https://quark.docs.amd.com/latest/index.html) with calibration samples from Pile dataset.
11
  - ## Quantization Stragegy
12
  - ***Quantized Layers***: All linear layers excluding "lm_head"
13
  - ***Weight***: FP8 symmetric per-tensor
 
7
 
8
  # Llama-3.3-70B-Instruct-FP8-KV
9
  - ## Introduction
10
+ This model was built with Llama by applying [Quark](https://quark.docs.amd.com/latest/index.html) with calibration samples from Pile dataset.
11
  - ## Quantization Stragegy
12
  - ***Quantized Layers***: All linear layers excluding "lm_head"
13
  - ***Weight***: FP8 symmetric per-tensor