10 175 292

Chmielewski

Eryk-Chmielewski

AI & ML interests

None yet

Recent Activity

liked a model 1 day ago

meta-llama/Llama-4-Maverick-17B-128E-Original

liked a model 1 day ago

meta-llama/Llama-4-Maverick-17B-128E-Instruct-Original

liked a model 1 day ago

meta-llama/Llama-4-Scout-17B-16E-Original

View all activity

Organizations

Eryk-Chmielewski's activity

New activity in unsloth/Qwen2.5-VL-32B-Instruct-unsloth-bnb-4bit 10 days ago

Doesn't work with vLLM

#2 opened 10 days ago by

Eryk-Chmielewski

New activity in MISHANM/google-gemma-3-27b-it-fp8 14 days ago

problem with model configuration on vllm

#3 opened 14 days ago by

Eryk-Chmielewski

New activity in ModelCloud/DeepSeek-R1-Distill-Qwen-7B-gptqmodel-4bit-vortex-v1 2 months ago

Answers without <think> tag

#2 opened 2 months ago by

Eryk-Chmielewski

New activity in neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8-dynamic 3 months ago

Sparse Instruct model

#2 opened 3 months ago by

Eryk-Chmielewski

New activity in ruliad/deepthought-8b-llama-v0.01-alpha 4 months ago

Add Deepthought chat template

#2 opened 4 months ago by

alpindale

New activity in Qwen/Qwen2.5-Coder-32B-Instruct 5 months ago

How to run speculative decoding of this model with 0.5B model.

#18 opened 5 months ago by

Eryk-Chmielewski

New activity in facebook/MobileLLM-125M 5 months ago

Unable to run with default instructions on Colab

#3 opened 5 months ago by

rahulmanuwas

New activity in AXCXEPT/EZO-Qwen2.5-72B-Instruct 6 months ago

4bit version

#1 opened 6 months ago by

Eryk-Chmielewski

New activity in AXCXEPT/EZO-AutoCoTRAG-Qwen2.5-72B-Instruct_q4 6 months ago

Model architectures ['CustomQwen2Model'] are not supported for now

#1 opened 6 months ago by

Eryk-Chmielewski