Hugging Face's logo

cmarkea
/
Meta-Llama-3.1-70B-Instruct-4bit

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
4-bit precision
bitsandbytes
Model card Files
xet
Community
Cyrile commited on
Commit
c2cec70
·
verified ·
1 Parent(s): 97f7e7d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -18,9 +18,9 @@ Performance Scores (on a scale of 5):
18
  | Model | Score | # params (Billion) | size (GB) |
19
  |---------------------------------------------:|:--------:|:------------------:|:---------:|
20
  | gpt-4o | 4.13 | N/A | N/A |
21
- | Qwen/Qwen2.5-Coder-32B-Instruct | 4.41 | 32.8 | 65.6 |
22
- | Qwen/Qwen2.5-32B-Instruct | 4.40 | 32.8 | 65.6 |
23
- | cmarkea/Qwen2.5-32B-Instruct-4bit | 4.36 | 32.8 | 16.4 |
24
  | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.71 | 46.7 | 93.4 |
25
  | cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit | 3.68 | 46.7 | 23.35 |
26
  | meta-llama/Meta-Llama-3.1-70B-Instruct | 3.68 | 70.06 | 140.12 |
 
18
  | Model | Score | # params (Billion) | size (GB) |
19
  |---------------------------------------------:|:--------:|:------------------:|:---------:|
20
  | gpt-4o | 4.13 | N/A | N/A |
21
+ | gpt-4o-mini | 4.02 | N/A | N/A |
22
+ | Qwen/Qwen2.5-32B-Instruct | 3.99 | 32.8 | 65.6 |
23
+ | cmarkea/Qwen2.5-32B-Instruct-4bit | 3.98 | 32.8 | 16.4 |
24
  | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.71 | 46.7 | 93.4 |
25
  | cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit | 3.68 | 46.7 | 23.35 |
26
  | meta-llama/Meta-Llama-3.1-70B-Instruct | 3.68 | 70.06 | 140.12 |