mistralai/Mistral-7B-v0.1

#125 opened 11 months ago by

limha

Mistral 7B produces different results when we hit via postman api

7

#124 opened 11 months ago by

DivyaKanniah

Load and extract the model for language modeling

1

#123 opened 11 months ago by

theodp

Unexpected keyword 'rope_scaling' while loading model

#122 opened 11 months ago by

gandhipratik65j

Kernel crashed while loading checkpoint shards

#121 opened 11 months ago by

clemennntt

Is there any way to increase the vocabulary of the tokenizer and use it fine tune the model on the new language

#120 opened 12 months ago by

Tejaswi006

I hope he can respond according to the language used by the user

#118 opened 12 months ago by

poarpeak

Fix context length in config

#117 opened 12 months ago by

imone

Finetuning with PEFT - Some weights of MistralForSequenceClassification were not initialized from the model

6

#116 opened about 1 year ago by

RobbieTheRobot

Data collator removing eos token

#115 opened about 1 year ago by

MaBrThesis2023

Thanks to Mistral for making our dream a reality

1

#114 opened about 1 year ago by

Muhammadreza

Is SWA used during pertaining?

#113 opened about 1 year ago by

EarthWorm001

FT Mistral Generate Slowly

#112 opened about 1 year ago by

yixliu1

PEFT based Fine Tuned model hallucinates values from the fine tuning training data while inferencing.

7

#111 opened about 1 year ago by

Pradeep1995

should we follow the same mistral prompt structure while finetuning time?

#110 opened about 1 year ago by

Pradeep1995

npz file for apple MLX

#109 opened about 1 year ago by

joy2000

Error in config.json

#108 opened about 1 year ago by

sohamghoshml

Incomplete Output even with max_new_tokens

12

#107 opened about 1 year ago by

Pradeep1995

can't generate embedding vector

#106 opened about 1 year ago by

philgrey

Maximum number of input tokens ?

1

#104 opened about 1 year ago by

Kirolos

Mistral Custom Chatbot Code Sample

#100 opened about 1 year ago by

unixguru2k

how to increase response max token size

#99 opened about 1 year ago by

philgrey

Huggingface.com

#98 opened about 1 year ago by

Khalid776826

How to remember conversation history (prior prompts and responses)

#97 opened about 1 year ago by

TheBacteria

Why is this 7B model only showing 5GB of gpu ram allocation?

#96 opened about 1 year ago by

shayak

Add Flax checkpoints

#95 opened about 1 year ago by

ksmcg

Update README.md

#93 opened about 1 year ago by

AzerOuerghi

can i use mistral as embedding model?

8

#92 opened about 1 year ago by

raynWest

Adding `safetensors` variant of this model

#91 opened about 1 year ago by

lcahill

Adding Evaluation Results

#90 opened about 1 year ago by

leaderboard-pr-bot

Embeddings API

#88 opened about 1 year ago by

priamai

Update config.json

#86 opened about 1 year ago by

PlanetDOGE

Create xx

#83 opened about 1 year ago by

joey1895

Create README.md

#80 opened about 1 year ago by

joey1895

Keyerror "Mistral"

7

#79 opened about 1 year ago by

lakshmiu

Korean data rate in pretraining datasets.

#78 opened about 1 year ago by

Korabbit

Model outputs only <unk> tokens after training on my data

#77 opened about 1 year ago by

Fico

MemGPT, Function Calling and Mistral-7b-v0.1

#76 opened about 1 year ago by

Joseph717171

I create a site for someone want full guide of this model

#72 opened about 1 year ago by

gstarwd

Can you give an example of a good prompt template?

#70 opened about 1 year ago by

iplayfast

Hosting Mistral 7B API

#69 opened about 1 year ago by

wahab12

ImportError: Using `load_in_8bit=True` requires Accelerate

#68 opened about 1 year ago by

ubermenchh

Update README.md

#67 opened about 1 year ago by

Enoughking

Suggested Architecture for Small Mistral Model

#66 opened about 1 year ago by

mnitin73

Does Mistral support accelerate library?

#65 opened about 1 year ago by

Sp1der

The attention mask and the pad token id were not set.

#64 opened about 1 year ago by

victor314159

[AUTOMATED] Model Memory Requirements

#63 opened about 1 year ago by

model-sizer-bot

If I trained a model on mistral already, do I need to start from scratch due to difficulties of fine-tuning?