mistralai/Mixtral-8x7B-Instruct-v0.1

#95 opened 9 months ago by

icemaro

Run Mistral model on Remote server

#94 opened 9 months ago by

icemaro

Cuda Error

#93 opened 9 months ago by

HuggySSO

Not supported with TGI

#92 opened 9 months ago by

abhishek3jangid

deepspeed load mixtral-8x7B hang or oom

#91 opened 9 months ago by

guowl

Add MOE (mixture of experts) tag

#90 opened 9 months ago by

davanstrien

Update README.md

#89 opened 9 months ago by

schuyler12

Failure in loading the model on AWS

8

#88 opened 9 months ago by

bweinstein123

Hardware Requirements

#86 opened 9 months ago by

ShivanshMathur007

Response content was truncated

19

#84 opened 9 months ago by

ludomare

Best parameter setting for Mixtral model on the text-generation task

#83 opened 9 months ago by

kmukeshreddy

Any hints on prompt to reduce / stop hallucinations

#82 opened 9 months ago by

dnovak232

Still the best Mixtral based instruct model. We should change that

#81 opened 9 months ago by

rombodawg

Could not convert to integer: 3221225477 error

#80 opened 9 months ago by

KharabinDev42

Serving the model as API on vLLM and 2 x A6000

#78 opened 9 months ago by

dnovak232

How much memory do I need for this model (on Windows)?

#77 opened 9 months ago by

roboboot

Inconsistent prompt format. Which is correct the Model card or the tokenizer_config.json?

#75 opened 9 months ago by

lemonflourorange

can not run sft full finetuning.

9

#74 opened 9 months ago by

hegang126

[Chinese Version] Mixtral-8x7B model | 中文Mixtral-8x7B模型

#73 opened 9 months ago by

wangrongsheng

Update the deprecated Flash Attention call parameter in from_pretrained() method

#72 opened 9 months ago by

DeathReaper0965

can't load the model

#71 opened 9 months ago by

JayZhang1

What is the best way for the inference process in LORA in PEFT approach

8

#70 opened 9 months ago by

Pradeep1995

How to use system prompt?

#69 opened 9 months ago by

mznw

Is there any simple way to solve the problem of redundant output

#68 opened 9 months ago by

jjplane

Which is the actual way to store the adapters after PEFT finetuning

4

#67 opened 9 months ago by

Pradeep1995

Failed to import transformers.models.mixtral.modeling_mixtral because of the following error (look up to see its traceback): libcudart.so.12: cannot open shared object file: No such file or directory

#66 opened 9 months ago by

MukeshSharma

Model not loading, even with 4-bit quantization

#65 opened 9 months ago by

soumodeep-semut

did Mixtral start from Mistral or from-scratch?

#64 opened 9 months ago by

DaehanKim

How many GPUs do we need to run this out of box?

#63 opened 9 months ago by

kz919

Is this model can choose expert for every token? Or just choose two expert for a input

#62 opened 9 months ago by

PandaMaster

AutoTokenizer.from_pretrained show OSError

#61 opened 10 months ago by

sean29

does file with .safetensors necessary for continue sft training?

#60 opened 10 months ago by

hegang126

Incomplete Answers

7

#59 opened 10 months ago by

samparksoftwares

How can we enable continuous learning with the LLM model ?

#58 opened 10 months ago by

Tapendra

Inference generation extremely slow

#57 opened 10 months ago by

aledane

Optimizing Mixtral-8x7B-Instruct-v0.1 for Hugging Face Chat

#54 opened 10 months ago by

Husain

SageMaker Deployment Error

11

#53 opened 10 months ago by

seabasshn

killed on Loading checkpoint shards

#52 opened 10 months ago by

asmatveev

Playground?

#51 opened 10 months ago by

pbourmeau

vectorstore

#50 opened 10 months ago by

philgrey

Enable inference API

#49 opened 10 months ago by

mrfakename

How to use consolidated.xx.pt?

#47 opened 10 months ago by

Wan62

Model not loading and not printing any error message

#45 opened 10 months ago by

robotrage

open weights???

#43 opened 10 months ago by

alanchan808

Prompt Template for RAG

#42 opened 10 months ago by

mox

there is no sliding_window in params.json

#41 opened 10 months ago by

Moses25

Question on further fine-tuning

#40 opened 10 months ago by

vldvasi

KeyError: 'mixtral' when following the 'run the model' section