mistralai/Mistral-Nemo-Instruct-2407

Add a response template

#93 opened 13 days ago by

Rocketknight1

Add signalbench (In-Band Signal Compliance) community eval

#92 opened 4 months ago by

thamilvendhan

Add EvalEval community eval results

#91 opened 5 months ago by

EvalEvalBot

First Attempt at using native llama.cpp finetune..

#90 opened about 1 year ago by

LinuxMagic

Upgrade to Nemo when?

👍 4

#89 opened over 1 year ago by

mpasila

Test using M1 Max (64G) and Word

#88 opened over 1 year ago by

gptlocalhost

why the model is returng biasedbiasedbiasedbiasedbiasedbiasedbiasedbiased!!!!!!

#86 opened almost 2 years ago by

garurumon2

Where to find the datasets for this model?

#85 opened almost 2 years ago by

KLimaLima

Update the tempalte so that the system prompt will not be ignored if the last message is not user message e.g. tool use

1

#84 opened almost 2 years ago by

gary1999

model keeps timing out?

👀 3

14

#83 opened about 2 years ago by

0xHalo22

Tokenizer issues with "Ő" and "Ű" characters

7

#82 opened about 2 years ago by

LouiSeHU

Update README.md

#81 opened about 2 years ago by

hamsinim12

Problem with 'mistralai/Mistral-Nemo-Instruct-2407's API for Chat completion

#80 opened about 2 years ago by

adelamare-blockchain

Converting from mistral-finetune to hf compatible

3

#79 opened about 2 years ago by

azimjon

Is it possible to run this model on a V100?

1

#77 opened about 2 years ago by

datenbergwerk

Chat template ignores system message after a tool response.

#76 opened about 2 years ago by

SeanIsYoung

model is not working

➕😔 4

1

#74 opened about 2 years ago by

lowpex

The following `model_kwargs` are not used by the model

#72 opened about 2 years ago by

zoher15

Nvidia NIM?

#71 opened about 2 years ago by

anujn

Batch inference example

#70 opened about 2 years ago by

amezasor

Model Loading since 2hrs

2

#69 opened about 2 years ago by

gagarwal1

Google Colab RAM crash, after 4-bit quantization.

#68 opened about 2 years ago by

BlankHead

Which version of transformers works with this model?

2

#66 opened over 2 years ago by

aw632

Function calling - force tool calling

1

#64 opened over 2 years ago by

rtilman

Does vllm support this model yet?

🚀 1

#63 opened over 2 years ago by

SongXiaoMao

RuntimeError: shape '[1, 688, 32, 160]' is invalid for input of size 2818048

1

#62 opened over 2 years ago by

CarlRD

Chat template is broken after tool calling support was added to the template

9

#61 opened over 2 years ago by

romanwozniak

can we dowload this model and save in disk?

1

#60 opened over 2 years ago by

ikanand

On windows : UnicodeDecodeError: 'charmap' codec can't decode byte 0x81 in position 32549

2

#55 opened over 2 years ago by

Pioupiouu

Mistral-Nemo-Instruct-2407 just hangs on my Mac M3?

1

#53 opened over 2 years ago by

lancejpollard

How to use Minstral with Node.js / transformers.js?

1

#52 opened over 2 years ago by

lancejpollard

Please release also a 7B-9B model!

#51 opened over 2 years ago by

ZeroWw

My "SILLY" experiment.

#50 opened over 2 years ago by

ZeroWw

Problems binding tools with LangChain and LangGraph

#49 opened over 2 years ago by

tldevelop

AssertionError & Shard Cannot Start

➕ 2

#48 opened over 2 years ago by

subapon

System Prompt added to last message

👍 3

21

#47 opened over 2 years ago by

turentado

Error: FIM is not enabled for this model using open-mixtral-8x7b model

#46 opened over 2 years ago by

mdarsalanarain

Tool message type raise Exception because of chat_template

1

#45 opened over 2 years ago by

aloababa

Getting Error: ShardCannotStart

👍 1

4

#44 opened over 2 years ago by

deepaksiloka

Help: How to inference with this model in FP8

➕👀 8

2

#43 opened over 2 years ago by

YukiTomita-CC

Sometimes she breaks down and I get replies like this...[Help!]

2

#41 opened over 2 years ago by

taellinglin

This is a 13B model... any chance you also made a 7B/8B model?

2

#40 opened over 2 years ago by

ZeroWw

Model's Hidden Dim in readme is Wrong

1

#38 opened over 2 years ago by

ShiLuohe

size mismatch for model.layers when loading with from pretrained

👍 2

8

#35 opened over 2 years ago by

C-Felix

Thanks, my discord bot now is stunningly intelligent.

#34 opened over 2 years ago by

taellinglin

Add to inference APIs

1

#33 opened over 2 years ago by

mrfakename

what would be best sillytavern insturct&context template anyone willing to share?

4

#32 opened over 2 years ago by

swer

小説生成

❤️ 1

1

#31 opened over 2 years ago by

AIzeke

NAN when training

1

#29 opened over 2 years ago by

nthehai01

Mathmatics : Optimal settings for a model :

👍 1

#28 opened over 2 years ago by

LeroyDyer