Best french model embedder for retriever LangChain?
2
#61 opened almost 2 years ago
by
cfrancois7

token limit exceeded
4
#60 opened almost 2 years ago
by
nidabijapure
a=2, b=3, n=a+b, n=?
3
#59 opened almost 2 years ago
by
marc47marc47
Request: Please Make a LLAVA-Like Model from Mistral-7B - It Would be Amazing 🤩
❤️
1
6
#57 opened almost 2 years ago
by
Joseph717171
Open-Ko-LLM Leaderboard - Thanks for Uploading!
#55 opened almost 2 years ago
by
hunkim

Can't load tokenizer for 'bert-base-uncased'.
2
#54 opened almost 2 years 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 almost 2 years ago
by
Ayush8120
Unrecognized configuration class <class 'transformers.models.mistral.configuration_mistral.MistralConfig'>
3
#50 opened almost 2 years ago
by
zeio

requests.exceptions.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
6
#49 opened almost 2 years ago
by
Jenad1kr
Problems with tokenizer
1
#48 opened almost 2 years ago
by
abdurnawaz
QLORA fine tuning with longer length of sequence (max_length=2048, padding=True) cause RuntimeError: CUDA error: device-side assert triggered; shorten length to 512 works !
#46 opened almost 2 years ago
by
nps798
MCQ Question Answering
👍
5
#45 opened almost 2 years ago
by
Ayush8120
Is `added_tokens.json` intended to be here?
4
#43 opened almost 2 years ago
by
xzuyn
Adding `safetensors` variant of this model
❤️
4
4
#42 opened almost 2 years ago
by
nth-attempt
Adding `safetensors` variant of this model
#41 opened almost 2 years ago
by
nth-attempt
Mistral en français ?
👍
3
6
#40 opened almost 2 years ago
by
Giroud
Question answering
11
#39 opened almost 2 years ago
by
codegood
Tensorflow-variant coming?
1
#37 opened almost 2 years ago
by
areinh
Default template and configuration for local run with GPU
🤝
1
#33 opened almost 2 years ago
by
brunoedcf

still throws refusals
🤯
🤗
1
1
#31 opened almost 2 years ago
by
Phoenixalight
Has a massive repetition problem
14
#29 opened almost 2 years ago
by
Delcos

Which Mistral datacenter was used for training ?
2
#25 opened almost 2 years ago
by
niko32

ValueError: Please specify `target_modules` in `peft_config`
3
#23 opened almost 2 years ago
by
Tapendra
13b in the future?
👍
9
9
#21 opened almost 2 years ago
by
deleted
Architectural difference with Llama
1
#20 opened almost 2 years ago
by
imone

How to deploy the model to local?
4
#19 opened almost 2 years ago
by
chao0524
Quantized version of Mistral 7B (4bit or 8 bit)
3
#18 opened almost 2 years ago
by
ianuvrat
FlashAttention support for Mistral HF Implementation
👍
5
1
#17 opened almost 2 years ago
by
mxxtsai
what r the datasets used to train the model?
❤️
1
1
#10 opened almost 2 years ago
by
rv2307
Training data?
👍
16
12
#8 opened almost 2 years ago
by
dkgaraujo
Safetensor weights
👍
4
#6 opened almost 2 years ago
by
ghvandoorn
Dataset contamination tests
👍
5
1
#1 opened almost 2 years ago
by
imone
