Hugging Face's logo

MaziyarPanahi
/
Mixtral-8x22B-Instruct-v0.1-GGUF

Text Generation
GGUF
quantized
2-bit
3-bit
4-bit precision
5-bit
6-bit
8-bit precision
16-bit
GGUF
mixtral
Mixture of Experts
conversational
Model card Files Community
37
New discussion

strange errors with Mixtral-8x22B-Instruct-v0.1.Q5_K_M
#37 opened 6 months ago by cyrilAub

'output_norm.weight' not found

2
#36 opened 8 months ago by harryballantyne

Mixtral 8x22B mixing up syllables

1
#35 opened 8 months ago by Stefanvarunix

How to merge .gguf into one file?

2
#34 opened 8 months ago by Lunitaris

MistralTokenizer

3
#33 opened 8 months ago by Esj-DL

Llama-cpp-python meet ValueError: Failed to create llama_context
#32 opened 8 months ago by zhouzr

Tokenizer is match？especially for function / tool call

1
#31 opened 8 months ago by zhouzr

Less is more

5
#25 opened 8 months ago by Henk717

llama_model_load: error loading model: vocab size mismatch

4
#8 opened 8 months ago by luccazen

A request

4
#6 opened 8 months ago by Hoioi