mistralai/Mistral-7B-Instruct-v0.1

#74 opened over 1 year ago by

ldavid

How to pass system prompts when using Mistral?

#73 opened over 1 year ago by

luissimoes

Mistral with LangChain What is the Model_Type?

#72 opened over 1 year ago by

luissimoes

Ready to use Mistral-7B-Instruct-v0.1 with Langchain via Huggingface Inference API

#70 opened over 1 year ago by

unixguru2k

Error while doing inference

#69 opened over 1 year ago by

SivaPrasad02

Often "\_" generated for "_" in code generation.

#68 opened over 1 year ago by

heejune

Template for chat

#67 opened over 1 year ago by

Coinman

Mistral doesn't have a `pad_token_id`? 🤔

#66 opened over 1 year ago by

ingo-m

Multilingual Support

#65 opened over 1 year ago by

abrehmaaan

How do i get the confidence score of an answer? I want to use this model for question answering task.

#64 opened over 1 year ago by

prajwalJumde

Align tokenizer_config chat template with docs.mistral.ai chat template

#63 opened over 1 year ago by

eliseobao

Datasets used

12

#62 opened over 1 year ago by

dlowl

Doesn't work when I deploy in the Spaces

#61 opened over 1 year ago by

asg145

[Request] Train a Medusa version of the model using the original training data

#58 opened over 1 year ago by

narai

`max_position_embeddings=32768` with "attention span of 131K tokens"

#57 opened over 1 year ago by

Nadav-Timor

Mistral en français

#56 opened over 1 year ago by

YorelNation

Is there a way to access the decoder portion of this model?

#54 opened over 1 year ago by

doofango

apply_chat_template result of Mistral is not restrictly align to the template on its website

#53 opened over 1 year ago by

Annorita

Update config.json

#52 opened over 1 year ago by

lukelv

[AUTOMATED] Model Memory Requirements

#50 opened over 1 year ago by

model-sizer-bot

Prompt template for question answering

19

#49 opened over 1 year ago by

gxxxz

Ideal tokenizer with Sentence Transformer?

#48 opened over 1 year ago by

mahimairaja

Which padding side to choose while finetuning

12

4

#47 opened over 1 year ago by

parikshit1619

killed message

#46 opened over 1 year ago by

TwoCats17

Install latest BitsandBytes

13

#44 opened over 1 year ago by

codegood

Cold boot

#42 opened over 1 year ago by

Akalilol

System Prompt

#41 opened over 1 year ago by

sakshat98

Mistral rules

#40 opened over 1 year ago by

iNeverLearnedHowToRead

Langchain with Mistral

#38 opened over 1 year ago by

19Peppe95

Update README.md

#36 opened over 1 year ago by

Ahelaraj

ValueError: Please specify `target_modules` in `peft_config`

#34 opened over 1 year ago by

Tapendra

error while running the model

#33 opened over 1 year ago by

adityaasish

Possibilities injecting custom system into mistral?

5

#32 opened over 1 year ago by

TikaToka

Deployment on Sagemaker endpoint with text generation inference container does not work

#30 opened over 1 year ago by

AnOtterDeveloper

Ready to use Mistral-7B-Instruct-v0.1-GGUF model as OpenAI API compatible endpoint

13

#29 opened over 1 year ago by

limcheekin

Any idea on how to do few shot prompting with the tokenizer provided in the transformers library?

#28 opened over 1 year ago by

ajinkyaathlye

Problem with using Mistralai model api from Huggingface

#26 opened over 1 year ago by

Hawks101

Just a quick test, but how good is it?

#25 opened over 1 year ago by

Stelarion

Does it work with local open interpreter, and how many gigs of ram is required?

#24 opened over 1 year ago by

aiworld44

Sharing a script to run a local streaming chat interface

#20 opened over 1 year ago by

tarruda

Is the Instruct version also commercial?

9

#18 opened over 1 year ago by

jianguozhang001

highest score yet out of a plain vanilla 7B model!!!!

#17 opened over 1 year ago by

silvacarl

What is the context size of this model?

#15 opened over 1 year ago by

saikatkumardey

How to fine tune ?

14

#12 opened over 1 year ago by

NickyNicky

Missing parameters