mistralai/Codestral-22B-v0.1

add AIBOM

#56 opened 9 months ago by

sabato-nocera

🚩 Report: Not working

1

#55 opened about 1 year ago by

garbagedog2

Why is Codestral 25.01 only local for enterprise?

1

#54 opened about 1 year ago by

Doctor-Chad-PhD

test

#53 opened over 1 year ago by

yangwei999

Update tokenizer's chat template to support assistant masks

#52 opened over 1 year ago by

leleogere

How to use [REFERENCE_DOC_x] in fill-in-the-middle tasks?

#51 opened over 1 year ago by

JimZhang

Facing NoneType for metadata while creating pipeline for codestral-22b

#50 opened over 1 year ago by

sivajyothi82

Request for access to Codestral-22B-v0.1

#49 opened over 1 year ago by

sivajyothi82

can we use this model for production?

1

#48 opened over 1 year ago by

Bebish

how to use huggingface-transformers for FIM task

#47 opened over 1 year ago by

aa327chenge

Deployment to SageMaker - instance type?

1

#46 opened over 1 year ago by

MavWolverine

Hardware requirements to use mistralai/Codestral-22B-v0.1

2

#44 opened over 1 year ago by

tzak86

Add chat_template to tokenizer_config.json

👍 4

1

#39 opened almost 2 years ago by

Albhebvvsbbe

Run Codestral on Google Colab or Kaggle

#38 opened almost 2 years ago by

mohammad1998

Update config.json

1

#36 opened almost 2 years ago by

rameshjhar480

Optimizing with the transformers library

#35 opened almost 2 years ago by

Taylor658

Why "Mistral Inference" and why your own tokenizer formats?

👍 5

#34 opened almost 2 years ago by

winddude

NS1

#33 opened almost 2 years ago by

nishan3000

test2

2

#32 opened almost 2 years ago by

yangwei999

Knowledge cutoff date

2

#30 opened almost 2 years ago by

aravindsr

Sample code using HF

1

#29 opened almost 2 years ago by

vanshils

Update README.md

👍 1

1

#28 opened almost 2 years ago by

Criztov

How to convert the weight to HF compatible?

🔥 1

7

#26 opened almost 2 years ago by

salaki

Question about consolidated.safetensors vs model*.safetensors

👍 6

#25 opened almost 2 years ago by

JineLD

New tokenizer.json doesn't match tokenizer.model.v3, there's no [SUFFIX], [MIDDLE] and [PREFIX] tokens.

👀 1

1

#24 opened almost 2 years ago by

mukel

can inference with vllm?

1

#21 opened almost 2 years ago by

amosxy

Why does this have 518 likes without any download, inference api or spaces?

3

#20 opened almost 2 years ago by

GPT007

How to load in multi-gpu instance ?

6

#19 opened almost 2 years ago by

aastha6

1111

1

#18 opened almost 2 years ago by

GLSS

Is it a pretrained/base model or instruct model?

👀👍 5

2

#17 opened almost 2 years ago by

Sinsauzero

how to fine tune this model?

4

#16 opened almost 2 years ago by

leo009

What is the context size on this model? And it does not appear to deal with JSON, function calling well.

1

#15 opened almost 2 years ago by

BigDeeper

Can I use the model's output code to develop software for a commercial website? (I am a MERN stack developer working in a company)

1

#14 opened almost 2 years ago by

nib12345

Disclosing training data

👀 2

1

#13 opened almost 2 years ago by

Vipitis

Fill in the Middle evaluation benchmark

1

#12 opened almost 2 years ago by

phqtuyen

No [PREFIX] and [SUFFIX] in tokenizer vocab

❤️ 2

5

#10 opened almost 2 years ago by

Vokturz

Update README.md

👍 1

1

#9 opened almost 2 years ago by

machinez

License

🤯 4

3

#8 opened almost 2 years ago by

mrfakename

How to convert to HF format?

➕👀 8

5

#6 opened almost 2 years ago by

ddh0

What does the tokenization for fill-in-the-middle requests look like?

2

#5 opened almost 2 years ago by

XeIaso

bpmn modeling

👍 2

#4 opened almost 2 years ago by

alibama

We are so back

❤️👍 22

5

#3 opened almost 2 years ago by

nanowell