Resources

View closed (7)

Fastest way for inference?

#28 opened about 19 hours ago by

psycy

Left side padding

#27 opened about 22 hours ago by

asarvazyan

Add pad token to tokenizer_config.json

#26 opened about 22 hours ago by

asarvazyan

Getting shape mismatch while loading saved Pixtral model

#24 opened 3 days ago by

ss007

Quantized Model config file

#23 opened 22 days ago by

endeavorXx

Is the chat template correct? (issue for vLLM)

#22 opened about 1 month ago by

MichaelAI23

Does the licensing for this model incorporate or depend on the licenses for LLaVA and LLaMA?

#20 opened about 2 months ago by

Skylark

Include user license

#19 opened about 2 months ago by

singhami

Fine tuning scripts for pixtral-12b

#18 opened 2 months ago by

2U1

Find solution to use this version with text and image : fake_image ;)

#17 opened 3 months ago by

martossien

Estimation of hardware requirements to finetune Pixtral models

#16 opened 3 months ago by deleted

Ask for guilding batch inference

#15 opened 4 months ago by

nguyen-brat

Update model weight

#13 opened 4 months ago by

nguyen-brat

Any leads on how to fine-tune Pixtral on custom dataset for reference?

#12 opened 4 months ago by deleted

Update tokenizer_config.json with chat_template

#11 opened 4 months ago by

mgoin

Multiple local images

#9 opened 4 months ago by

chiauho

How can i use the full 24GB model instead of this separated safetensors files?

#8 opened 5 months ago by

Valadaro

Converting back to Mistral/vLLM format

#4 opened 5 months ago by

RonanMcGovern

How to use safetensors?

#3 opened 5 months ago by

prathi1729

lamma cpp ht to gguf not working

#2 opened 5 months ago by

RameshRajamani

Local image input?

#1 opened 5 months ago by

sukays