Patrick von Platen's picture

Patrick von Platen

patrickvonplaten

·

patrickvonplaten

AI & ML interests

Language Generation, NLP, ASR

Recent Activity

new activity 16 days ago

mistral-community/Pixtral-Large-Instruct-2411:🚩 Report: Legal issue(s)

new activity 19 days ago

mistralai/Ministral-8B-Instruct-2410:Ragged attention supported in vLLM

updated a model about 1 month ago

mistralai/Ministral-8B-Instruct-2410

View all activity

Articles

Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e

Optimizing your LLM in production

Fine-tuning MMS Adapter Models for Multi-Lingual ASR

Running IF with 🧨 diffusers on a Free Tier Google Colab

ControlNet in Diffusers 🧨

Stable Diffusion in JAX/Flax 🚀

Stable Diffusion with 🧨 Diffusers

Supercharged Customer Service with Machine Learning

Don't repeat yourself - 🤗 Transformers Design Philosophy

Boost Wav2Vec2 with n-gram LM in 🤗 Transformers

Fine-tuning XLS-R for Multi-Lingual ASR with 🤗 Transformers

Fine-Tune Wav2Vec2 for English ASR with 🤗 Transformers

Leveraging Pre-trained Language Model Checkpoints for Encoder-Decoder Models

Transformer-based Encoder-Decoder Models

The Reformer - Pushing the limits of language modeling

How to generate text: using different decoding methods for language generation with Transformers

Organizations

patrickvonplaten's activity

New activity in mistral-community/Pixtral-Large-Instruct-2411 16 days ago

🚩 Report: Legal issue(s)

#1 opened 16 days ago by

patrickvonplaten

New activity in mistralai/Ministral-8B-Instruct-2410 19 days ago

Ragged attention supported in vLLM

#18 opened about 1 month ago by

patrickvonplaten

New activity in mistralai/Pixtral-Large-Instruct-2411 about 1 month ago

Explicitly set lang adapter bias to False

#7 opened about 1 month ago by

patrickvonplaten

New activity in mistralai/Mistral-Large-Instruct-2411 about 1 month ago

The curse of the Consolidated Safetensors strikes again...

#4 opened about 1 month ago by

New activity in mistralai/Pixtral-Large-Instruct-2411 about 1 month ago

Add config_format and load_format to vLLM args

#5 opened about 1 month ago by

Update config.json to use null for sliding_window

#4 opened about 1 month ago by

Update README.md

#2 opened about 1 month ago by

devendrachaplot

New activity in TIGER-Lab/MMLU-Pro about 2 months ago

Ministral 3B results seem off

#3 opened about 2 months ago by

patrickvonplaten

New activity in mistral-community/pixtral-12b 2 months ago

Why is the Pixtral activation function "gelu" when the reference code uses "silu"?

#10 opened 2 months ago by

New activity in mistralai/Mistral-7B-Instruct-v0.2 3 months ago

Expose metadata link to next version of the model

#161 opened 3 months ago by

New activity in mistralai/Mistral-Small-Instruct-2409 3 months ago

Please consider changing the instruct format!

#10 opened 3 months ago by

MarinaraSpaghetti

New activity in mistralai/Pixtral-12B-2409 3 months ago

Fix readme

#14 opened 3 months ago by

patrickvonplaten

New activity in mistralai/Mamba-Codestral-7B-v0.1 4 months ago

Upload HF format weights for Mamba2ForCausalLM

#9 opened 5 months ago by

New activity in mistralai/Mixtral-8x22B-Instruct-v0.1 4 months ago

Tokenizer broken after last commit

#53 opened 4 months ago by

New activity in mistralai/Mistral-7B-Instruct-v0.3 4 months ago

Broken tokenizer

#77 opened 4 months ago by

New activity in mistralai/Mistral-Large-Instruct-2407 5 months ago

Fix references to missing model

#6 opened 5 months ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

mistral-chat doesn't work

#12 opened 5 months ago by

New activity in mistralai/Mistral-Nemo-Base-2407 5 months ago

Set `clean_up_tokenization_spaces` to false

#8 opened 5 months ago by

New activity in mistralai/Mistral-Nemo-Instruct-2407 5 months ago

Set `clean_up_tokenization_spaces` to false

#13 opened 5 months ago by

Do not add eos token by default

#8 opened 5 months ago by