mistralai/Mistral-7B-v0.1

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

#118 opened 10 months ago by

poarpeak

Fix context length in config

#117 opened 10 months ago by

imone

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

6

#116 opened 10 months ago by

RobbieTheRobot

Data collator removing eos token

#115 opened 10 months ago by

MaBrThesis2023

Thanks to Mistral for making our dream a reality

1

#114 opened 10 months ago by

Muhammadreza

Is SWA used during pertaining?

#113 opened 10 months ago by

EarthWorm001

FT Mistral Generate Slowly

#112 opened 10 months ago by

yixliu1

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

7

#111 opened 10 months ago by

Pradeep1995

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

#110 opened 10 months ago by

Pradeep1995

npz file for apple MLX

2

#109 opened 10 months ago by

joy2000

Error in config.json

3

#108 opened 10 months ago by

sohamghoshml

Incomplete Output even with max_new_tokens

12

#107 opened 10 months ago by

Pradeep1995

can't generate embedding vector

#106 opened 10 months ago by

philgrey

Maximum number of input tokens ?

1

#104 opened 10 months ago by

Kirolos

Mistral Custom Chatbot Code Sample

4

#100 opened 11 months ago by

unixguru2k

how to increase response max token size

#99 opened 11 months ago by

philgrey

Huggingface.com

#98 opened 11 months ago by

Khalid776826

How to remember conversation history (prior prompts and responses)

2

#97 opened 11 months ago by

TheBacteria

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

3

#96 opened 11 months ago by

shayak

Add Flax checkpoints

#95 opened 11 months ago by

ksmcg

Update README.md

#93 opened 11 months ago by

AzerOuerghi

can i use mistral as embedding model?

8

#92 opened 11 months ago by

raynWest

Adding `safetensors` variant of this model

2

#91 opened 11 months ago by

lcahill

Adding Evaluation Results

#90 opened 11 months ago by

leaderboard-pr-bot

Embeddings API

3

#88 opened 11 months ago by

priamai

Update config.json

#86 opened 12 months ago by

PlanetDOGE

Create xx

#83 opened 12 months ago by

joey1895

Create README.md

#80 opened 12 months ago by

joey1895

Keyerror "Mistral"

7

#79 opened 12 months ago by

lakshmiu

Korean data rate in pretraining datasets.

3

#78 opened 12 months ago by

Korabbit

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

#77 opened 12 months ago by

Fico

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

#76 opened 12 months ago by

Joseph717171

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

#72 opened 12 months ago by

gstarwd

Can you give an example of a good prompt template?

3

#70 opened 12 months ago by

iplayfast

Hosting Mistral 7B API

2

#69 opened 12 months ago by

wahab12

ImportError: Using `load_in_8bit=True` requires Accelerate

4

#68 opened 12 months ago by

ubermenchh

Update README.md

#67 opened 12 months ago by

Enoughking

Suggested Architecture for Small Mistral Model

#66 opened 12 months ago by

mnitin73

Does Mistral support accelerate library?

4

#65 opened about 1 year ago by

Sp1der

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

2

#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?

2

#62 opened about 1 year ago by

brando

Best french model embedder for retriever LangChain?

2

#61 opened about 1 year ago by

cfrancois7

token limit exceeded

3

#60 opened about 1 year ago by

nidabijapure

a=2, b=3, n=a+b, n=?

3

#59 opened about 1 year ago by

marc47marc47

AI专家

1

#58 opened about 1 year ago by

sun95

Request: Please Make a LLAVA-Like Model from Mistral-7B - It Would be Amazing 🤩

6

#57 opened about 1 year ago by

Joseph717171

Open-Ko-LLM Leaderboard - Thanks for Uploading!

#55 opened about 1 year ago by

hunkim

Can't load tokenizer for 'bert-base-uncased'.

2

#54 opened about 1 year ago by

Momoxiao111

A decoder-only architecture is being used, but right-padding was detected! For correct generation results, please set `padding_side='left'` when initializing the tokenizer.

5

#51 opened about 1 year ago by

Ayush8120