Hugging Face's logo

cmarkea
/
Mixtral-8x7B-Instruct-v0.1-4bit

Text Generation
Transformers
Safetensors
mixtral
Mixture of Experts
conversational
text-generation-inference
Inference Endpoints
4-bit precision
bitsandbytes
Model card Files Community
Cyrile commited on
Commit
36bd97e
·
verified ·
1 Parent(s): 5d27613

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -24,8 +24,11 @@ Performance Scores (on a scale of 5):
24
  | gpt-4o | 4.13 | N/A | N/A |
25
  | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.71 | 46.7 | 93.4 |
26
  | **cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit** | **3.68** | **46.7** | **23.35** |
 
27
  | gpt-3.5-turbo | 3.66 | 175 | 350 |
 
28
  | TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ | 3.56 | 46.7 | 46.7 |
 
29
  | mistralai/Mistral-7B-Instruct-v0.2 | 1.98 | 7.25 | 14.5 |
30
  | cmarkea/bloomz-7b1-mt-sft-chat | 1.69 | 7.07 | 14.14 |
31
  | cmarkea/bloomz-3b-dpo-chat | 1.68 | 3 | 6 |
 
24
  | gpt-4o | 4.13 | N/A | N/A |
25
  | mistralai/Mixtral-8x7B-Instruct-v0.1 | 3.71 | 46.7 | 93.4 |
26
  | **cmarkea/Mixtral-8x7B-Instruct-v0.1-4bit** | **3.68** | **46.7** | **23.35** |
27
+ | meta-llama/Meta-Llama-3.1-70B-Instruct | 3.68 | 70.06 | 140.12 |
28
  | gpt-3.5-turbo | 3.66 | 175 | 350 |
29
+ | cmarkea/Meta-Llama-3.1-70B-Instruct-4bit | 3.64 | 70.06 | 35.3 |
30
  | TheBloke/Mixtral-8x7B-Instruct-v0.1-GPTQ | 3.56 | 46.7 | 46.7 |
31
+ | meta-llama/Meta-Llama-3.1-8B-Instruct | 3.25 | 8.03 | 16.06 |
32
  | mistralai/Mistral-7B-Instruct-v0.2 | 1.98 | 7.25 | 14.5 |
33
  | cmarkea/bloomz-7b1-mt-sft-chat | 1.69 | 7.07 | 14.14 |
34
  | cmarkea/bloomz-3b-dpo-chat | 1.68 | 3 | 6 |