Hugging Face's logo

FlorianJc
/
Vigostral-7b-Chat-GGUF

Text Generation
GGUF
French
mistral
finetuned
french
vigogne
text-generation-inference
Inference Endpoints
Model card Files Community
FlorianJc commited on
Commit
bc1f4af
·
1 Parent(s): 135bea1

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -8,6 +8,7 @@ tags:
8
  - finetuned
9
  - french
10
  - vigogne
 
11
  ---
12
 
13
  # Vigostral-7b-Chat GGUF
@@ -30,4 +31,4 @@ Elle n'est donc fournie ici que pour donner une approximation de la perte réél
30
  | Q8_0 | 7,2 Go | +0.0004 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q8_0.gguf |
31
  | Q6_K | 5,5 Go | -0.0008 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q6_K.gguf |
32
  | Q5_K_M | 4,8 Go | +0.0122 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q5_K_M.gguf |
33
- | Q4_K_M | 4,1 Go | +0.0532 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q4_K_M.gguf |
 
8
  - finetuned
9
  - french
10
  - vigogne
11
+ - text-generation-inference
12
  ---
13
 
14
  # Vigostral-7b-Chat GGUF
 
31
  | Q8_0 | 7,2 Go | +0.0004 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q8_0.gguf |
32
  | Q6_K | 5,5 Go | -0.0008 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q6_K.gguf |
33
  | Q5_K_M | 4,8 Go | +0.0122 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q5_K_M.gguf |
34
+ | Q4_K_M | 4,1 Go | +0.0532 ppl @ LLaMA-v1-7B | https://huggingface.co/FlorianJc/Vigostral-7b-Chat-GGUF/blob/main/vigostral-7b-chat-Q4_K_M.gguf |