mistralai/Mistral-7B-Instruct-v0.2

#96 opened 7 months ago by

XIX181

Is the model down?

#95 opened 7 months ago by

hvkkvh

How do I successfully merge adater weights to this base model correctly? And then siccessfulyl convert to GGUF

#94 opened 7 months ago by

uyiosa

Cannot access gated repo You must be authenticated to access it.

42

#93 opened 7 months ago by

liketheflower

deepspeed inference tensor parallelism memory footprint doesn't decrease with deepspeed tp_size increase.

6

#92 opened 7 months ago by

jiangtaozh

why put MistralRotaryEmbedding in each attention layer instead of putting only once before the first attention layer?

#91 opened 7 months ago by

liougehooa

How to use this model in next js?

#90 opened 8 months ago by

shreyassihasane

Model doesn't stop generation after answering the user question.

#88 opened 8 months ago by

jerinjude

How does v0.2 manages to support 32k token context without Sliding Window Attention?

#85 opened 8 months ago by

Andriy

will Mistral-7B-Instruct-v0.2 let me generate a response of around 8k tokens in one go?

#84 opened 8 months ago by

akshat1311

How to prune layers in AutoModelForCausalModel

5

#83 opened 8 months ago by

badri369

[AUTOMATED] Model Memory Requirements

#82 opened 8 months ago by

model-sizer-bot

Update README.md

#81 opened 8 months ago by

Austinc2003

Quantized version taking too long with CPU's

#80 opened 8 months ago by

SukanyaM

Model inconsistency Issue

#79 opened 8 months ago by

adityar23

LangChain Agent with Mistral-7B-Instruct-v0.2

12

#78 opened 8 months ago by

deeplearner123

Training Data difference from v0.1

#77 opened 8 months ago by

tsavage68

Update README.md

#76 opened 8 months ago by

mixxz

Why was Sliding-Window Attention deprecated?

#75 opened 8 months ago by

matrixssy

Update config.json to accurately reflect the 32k context window.

#73 opened 8 months ago by

Kearm

Was this model based of Mistral-7B-v0.2 from the start?

#72 opened 8 months ago by

stduhpf

Can someone from Mistral comment on what the knowledge cutoff is?

#69 opened 8 months ago by

MarginallyEffective

Mistral-7B-Instruct-v0.2 loopy text generation with custom chat template

#68 opened 8 months ago by

ercanucan

User input repetition after finetuning

#67 opened 8 months ago by

nuratamton

What is the max context length of this model?

#66 opened 9 months ago by

flexwang

Inference API

#65 opened 9 months ago by

Shivkumar27

cm_test

#64 opened 9 months ago by

chenmin2001

FIne tuned model generating both user and assistant dialogues during inference

#63 opened 9 months ago by

sabber

Has anybody gotten this example to work for converting string data into valid JSON?

#62 opened 9 months ago by

capnchat

Is mistral7b instruct v0.2 down for everybody?

#61 opened 9 months ago by

SzymonSt2808

Friendly Reminder

#60 opened 9 months ago by

AnzaniAI

Is it possible to see embeddinges once you have fine tuned it ??

#59 opened 9 months ago by

RikoteMaster

ValueError: Bfloat16 is only supported on GPUs with compute capability of at least 8.0

#58 opened 9 months ago by

itod

instruction fine tuning template

#57 opened 9 months ago by

Iamexperimenting

sliding_window appears to be None. TypeError: bad operand type for unary -: 'NoneType'

#56 opened 9 months ago by

narai

value for sliding_window in config.json updated

#55 opened 9 months ago by

manaschauhan

Fix the command format of "Installing transformers from source"

#53 opened 9 months ago by

musfiqdehan

System prompt

#52 opened 9 months ago by

VladimirNGIT

Process finished with exit code -1073741819 (0xC0000005)

#51 opened 9 months ago by

aminev

Is there any vllm support for this version?

9

#49 opened 10 months ago by

Aloukik21

Mistral does not finish the answers

9

#48 opened 10 months ago by

expiderman

Special token( </s>) not generating in the model.generate() method

7

#47 opened 10 months ago by

Pradeep1995

Can we save the finetuned Mistral model by exporting to TorchScript