mistralai
/

Mixtral-8x7B-v0.1

Text Generation

Mixture of Experts

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

Resources

View closed (12)

How to train every expert in mixtral 8x7B on different domain data ?

#56 opened 14 days ago by

training every expert of mixtral-8x7b

#55 opened 14 days ago by

What does each consolidated.0x.pt consist of? How to load model using them?

#54 opened 18 days ago by

Colab Notebook: Fine-tune Mixtral-8x7B (QLoRA)

#53 opened 20 days ago by

How to fully fine-tune Mixtral 8x7b without using any adapters ?

#52 opened 29 days ago by

HELP: How to host mixtral model as openai server

#51 opened 29 days ago by

Update README.md

#50 opened about 1 month ago by

Is this best open source model for code summarization?

#47 opened about 2 months ago by

Adding Evaluation Results

#46 opened 2 months ago by

leaderboard-pr-bot

Complex SQL Query Generator

#45 opened 2 months ago by

Help: CUDA Out of Memory. Hardware Requirements. vLLm and FastChat

#44 opened 2 months ago by

[AUTOMATED] Model Memory Requirements

#43 opened 2 months ago by

model-sizer-bot

Request failed during generation: Server error: CUDA out of memory

#42 opened 3 months ago by

Out of Memory issue in sagemaker ml.g5.12xLarge instance

#41 opened 3 months ago by

How to host mistral online?

#39 opened 3 months ago by

Request: DOI

#38 opened 3 months ago by

Azure VM not launching Mixtral

#37 opened 3 months ago by

Running inference on multi GPU

#36 opened 3 months ago by

Update README.md

#35 opened 3 months ago by

Out of memory issue.

#34 opened 4 months ago by

Use embeddings create with API on my completions

#33 opened 4 months ago by

training data

#32 opened 4 months ago by

Merci / Thanks

#31 opened 4 months ago by

How to fine tune mixtral 8x7B?

#30 opened 4 months ago by

remove old disclaimer

#28 opened 4 months ago by

train mixtral

#27 opened 4 months ago by

KeyError: 'mixtral'

#26 opened 5 months ago by

WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu.

#25 opened 5 months ago by

Question: Maximizing GPU Utilization for Inference

#24 opened 5 months ago by

Prompt format of mistralai/Mixtral-8x7B-v0.1 model

#22 opened 5 months ago by

Delete model-00010-of-00019.safetensors

#21 opened 5 months ago by

bonjour

#20 opened 5 months ago by

Wrong solution for 1+1=

#18 opened 5 months ago by

Error while loading model

#16 opened 5 months ago by

Deployment failing on Sagemaker

#15 opened 5 months ago by

Maybe remove the `+` signs in the demo code?

#13 opened 5 months ago by

FSDP Finetuning

#12 opened 5 months ago by

🚀 Torrent File for AI Model Download 🚀

#11 opened 5 months ago by

Fine-tuning toolkit for Mixtral 8x7B MoE model

#10 opened 5 months ago by

Sagemaker deployment config for sub second real time inference

#9 opened 5 months ago by

AutoModelForCausalLM does not seem to work for Mixtral

#8 opened 5 months ago by

A question

#6 opened 5 months ago by

No multi GPU inference support?

#4 opened 5 months ago by

Is it possible to get GPTQ quants in 4 bpw?

#2 opened 5 months ago by