mistralai/Mistral-7B-Instruct-v0.3

#71 opened over 1 year ago by

Saicy

Delete config.json

#67 opened over 1 year ago by

titiyu

My "silly" experiment.

#66 opened over 1 year ago by

ZeroWw

Problem with inference endpoint.

#64 opened over 1 year ago by

goporo

My alternative quantizations.

#61 opened over 1 year ago by

ZeroWw

Space in chat_template

#60 opened over 1 year ago by

ThangLD201

Update README.md

#59 opened over 1 year ago by

pys11

Command Line mistral-chat performs better than ChatCompletionRequest on the same text ?

#58 opened over 1 year ago by

maniiii

Conversation roles must alternate user/assistant/user/assistant/...

👍 1

3

#57 opened over 1 year ago by

akanksh-bc

Inconsistent Response Format for Inference Chat Completion Endpoint

#56 opened over 1 year ago by

MrGeniusProgrammer

Permission error for Mistral-7B-Instruct-v0.3

#54 opened over 1 year ago by

ladn-ghasemi

Deploying a fine-tuned model with custom inference code

3

#53 opened over 1 year ago by

maz-qualtrics

plz want

#52 opened over 1 year ago by

dnehate2022

Loss is increasing while finetuning

#50 opened over 1 year ago by

abpani1994

MistralTokenizer with HuggingFacePipeline.from_model_id

#47 opened over 1 year ago by

jsemrau

How to do batch processing with Mistral 7B?

👍 2

#43 opened over 1 year ago by

hyperiontau

Is this model open weight or open source

5

#42 opened over 1 year ago by

Shreyas94

Please check these quantizations.

#40 opened over 1 year ago by

ZeroWw

default parameters for model.generate

#39 opened over 1 year ago by

christinagottsch

Support tool_use chat_template

8

#38 opened over 1 year ago by

madroid

Tool calling is supported by ChatLLM.cpp

#36 opened over 1 year ago by

J22

Support tool calling in Transformers

#35 opened over 1 year ago by

Rocketknight1

Direct Hugging Face Inference API function calling

#34 opened over 1 year ago by

lamdao

tokenizer.default_chat_template containing "true == false"

#33 opened over 1 year ago by

maumar

Mistral-Inference package

#32 opened over 1 year ago by

swtb

Unconsolidated tensors

#31 opened over 1 year ago by

T9ALXD9

How to enable streaming?

#30 opened over 1 year ago by

Alexander-Minushkin

Thank you for the powerful open source model, but I would like to know how to use function_call in Transformers

#29 opened over 1 year ago by

NSSSJSS

This model is censored, don't bother with it.

😔 👍 6

8

#28 opened over 1 year ago by

seedmanc

Update README.md

#27 opened over 1 year ago by

Cordobian

Hallucinating function calls

#26 opened over 1 year ago by

SebastianS

Inconsistent parallel function calling

#25 opened over 1 year ago by

SebastianS

problems when use mistral-chat

#24 opened over 1 year ago by

jinglishi0206

Limited (truncated) response with inference API

#23 opened over 1 year ago by

RobertTaylor

Slow tokenizer problem.

➕ 1

5

#22 opened over 1 year ago by

bradhutchings

feat/tools-in-chat-template

❤️ 1

6

#21 opened over 1 year ago by

lcahill

Not generating [TOOL_CALLS]

3

#20 opened over 1 year ago by

ShukantP

Problems deploying to SageMaker

#19 opened over 1 year ago by

liam-smith

Is the model uncensored?

9

#18 opened over 1 year ago by

jujutechnology

thanks and question function-calling.

10

#17 opened over 1 year ago by

NickyNicky

tokenizer.model and tokenizer.model.v3 are identical

👍 8

#15 opened over 1 year ago by

wolfram

no system message?

10

#14 opened over 1 year ago by

mclassHF2023

Update README.md

#13 opened over 1 year ago by

dejanseo

Which PAD token can be used?

#11 opened over 1 year ago by

VlSav

how to fine-tuning?

7

#10 opened over 1 year ago by

leo009

String for the Function Calling Token