issues
search
mistralai
/
mistral-inference
Official inference library for Mistral models
https://mistral.ai/
Apache License 2.0
9.16k
stars
804
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[MISTRAL AI ERROR] Mistral AI responding with Unexpected role RoleEnum.tool error
#135
muhammadfaizan027915
closed
3 months ago
2
Mistral's tokenizer is not optimized
#134
Yarflam
opened
3 months ago
0
Evaluation Pipeline
#133
nikhil0360
opened
4 months ago
0
Friendly Reminder while Generating the output
#132
BadrinathMJ
opened
4 months ago
0
[Mistral 7B mistral-7b-instruct-v0.1.Q8_0.gguf] Wrong text "quoted" while presented as real
#131
SINAPSA-IC
opened
4 months ago
3
"evaluation pipeline" public?
#130
kijlk
opened
4 months ago
0
Add CPU support to one_file_ref.py (the one file implementation)
#129
kikirizki
opened
4 months ago
1
Mistral 7B v0.1 does not support optimum BetterTransformers for better and optimized Inference
#128
KaifAhmad1
opened
4 months ago
0
"official documentation" link points to a missing page (quickstart)
#127
dpkirchner
opened
4 months ago
1
Mixtral-8X7B-Instruct-v0.1 produces the context in Answer
#126
BadrinathMJ
opened
4 months ago
0
(question) moe for conversations
#125
Tom-Neverwinter
opened
4 months ago
0
Installation Problem
#124
jahbini
opened
4 months ago
3
Calling from Replicate - python error: issubclass() arg 1 must be a class
#123
bertello72
closed
5 months ago
0
BUG: API /completion endpoint returns 500 (server error) when sending "max_token" = 1
#122
MrXavier
opened
5 months ago
0
Is this architeture same as Mixtral-7x8B model?
#121
HuangJi1019
opened
5 months ago
0
Inquiry on unexpected behaviour of fine-tuned mistral-instruct model
#120
PhilipAmadasun
opened
5 months ago
0
Error while running tutorial: TypeError: 'mmap' is an invalid keyword argument for Unpickler()
#119
aurotripathy
opened
5 months ago
2
Mixtral sliding window
#118
tuyaao
opened
5 months ago
0
Cannot download latest image
#117
louispaulet
opened
5 months ago
2
Support for Python code generation
#116
kavyanshpandey
opened
5 months ago
0
#feature request# rope_scalling supprot
#115
Xingxiangrui
opened
6 months ago
0
how to finetune the mistral-moe with expert/data/pipeline parallel?
#114
marsggbo
opened
6 months ago
0
Update README.md
#113
eltociear
opened
6 months ago
0
Gate is Linear Layer?!?!
#112
Eran-BA
opened
6 months ago
1
Local embeddings model usage
#111
frankiedrake
opened
6 months ago
0
TinyMistral? small llm for phones and computers with no gpu?
#110
agonzalezm
opened
6 months ago
0
which model to use for what's the root of 256256?
#109
dcasota
closed
6 months ago
0
Parameter for returning `logprobs`
#108
StatsGary
closed
5 months ago
1
Non Latin Language support?
#107
ican24
opened
6 months ago
0
Update README.md for vllm & docker docs.
#106
slmatrix
opened
6 months ago
0
Update README.md: Fix page not found for link to guardrailing
#105
martin0258
opened
6 months ago
0
Fix typo
#104
moritztng
opened
6 months ago
0
What is the best way for the inference process in LORA in PEFT approach
#103
pradeepdev-1995
opened
6 months ago
0
Mistral input context length limitation
#102
DanYoto
opened
6 months ago
0
Minor typos
#101
sethupavan12
opened
6 months ago
0
Which is the actual way to store the Adapter after PEFT finetuning
#100
pradeepdev-1995
opened
6 months ago
0
vLLM Build Issue using the provided Dockerfile
#99
Good-Coffee
closed
6 months ago
4
Create Issue templates
#98
adityaraute
opened
6 months ago
0
Docs: Add tutorials for using Python client to generating embeddings and chat completion
#97
m-newhauser
opened
6 months ago
0
Fixing typos in MD
#96
Cassini-chris
opened
6 months ago
0
Has any thought been given to using LoRA to increase the number of experts (100x) with minimal memory?
#95
sixChar
opened
6 months ago
8
Fix typo/spelling in README.md
#94
GilesBathgate
opened
6 months ago
1
Mixtral Feedbacks
#93
titouandk
opened
6 months ago
0
Incomplete Output even with max_new_tokens
#92
pradeepdev-1995
opened
6 months ago
0
Building Mistral docker container results in OOM kill of the entire system
#91
codevbus
opened
6 months ago
0
wrong link in documentation
#90
Frank-Buss
opened
6 months ago
1
Adds attention mask with `model.forward(..., cache=None)`.
#89
andsteing
opened
6 months ago
0
Why does `cache=None` produce different outputs?
#88
andsteing
opened
6 months ago
0
Is the code up to date? Is the code the same for different model versions?
#87
zysNLP
opened
7 months ago
0
Inquiry on Implementing Sliding Window Attention for Custom Sequence Lengths
#86
yihong1120
opened
7 months ago
0
Previous
Next