Rodri Mora's picture

Rodri Mora

bullerwins

·

AI & ML interests

Gen AI, MLOps, Fine tuning and Quantizing models

Recent Activity

new activity 3 days ago

neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic:Calibration dataset

new activity 4 days ago

bullerwins/DeepSeek-V3-GGUF:Add pipeline tag and library name

updated a model 6 days ago

bullerwins/Qwen2.5-7B-Instruct-GGUF

View all activity

Organizations

bullerwins's activity

New activity in neuralmagic/DeepSeek-R1-Distill-Llama-70B-FP8-dynamic 3 days ago

Calibration dataset

#1 opened 3 days ago by

New activity in bullerwins/DeepSeek-V3-GGUF 4 days ago

Add pipeline tag and library name

#9 opened 4 days ago by

New activity in bullerwins/DeepSeek-V3-GGUF about 2 months ago

quantization request

#1 opened about 2 months ago by

Please quantize base model too

#3 opened about 2 months ago by

Q4 potentially broken

#2 opened about 2 months ago by

New activity in DBMe/EVA-Qwen2.5-72B-v0.2-4.48bpw-h6-exl2 about 2 months ago

Update README.md

#1 opened about 2 months ago by

New activity in deepseek-ai/DeepSeek-V3 about 2 months ago

minimum vram?

#9 opened about 2 months ago by

New activity in unsloth/llama-3-8b-Instruct-bnb-4bit 3 months ago

It is needed to use bnb 4bit?

#3 opened 9 months ago by

New activity in bullerwins/DeepSeek-V2.5-GGUF 5 months ago

one part

#1 opened 5 months ago by

New activity in bullerwins/Reflection-Llama-3.1-70B-GGUF 6 months ago

Thanks for the Update

#1 opened 6 months ago by

New activity in mattshumer/Reflection-Llama-3.1-70B 6 months ago

Update config.json

#6 opened 6 months ago by

New activity in turboderp/Llama-3.1-70B-Instruct-exl2 6 months ago

The tokenizer has changed just fyi

#2 opened 7 months ago by

New activity in bullerwins/Meta-Llama-3.1-8B-Instruct-exl2_8.0bpw 6 months ago

Proper exllamav2 github branch

#1 opened 6 months ago by

New activity in hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4 6 months ago

8 bit version

#3 opened 7 months ago by

New activity in bullerwins/Meta-Llama-3.1-8B-Instruct-GGUF 7 months ago

Wrong number of tensors when loading the model.

#3 opened 7 months ago by

No "No Virus" label

#2 opened 7 months ago by

New activity in hugging-quants/Meta-Llama-3.1-8B-Instruct-GPTQ-INT4 7 months ago

Examples dataset used for GPTQ Calibration

#4 opened 7 months ago by

New activity in hugging-quants/Meta-Llama-3.1-70B-Instruct-GPTQ-INT4 7 months ago

8 bit version

#3 opened 7 months ago by

New activity in bullerwins/Meta-Llama-3.1-70B-Instruct-GGUF 7 months ago

Why is this model crashing my game?

#1 opened 7 months ago by

New activity in hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4 7 months ago

How to use INT4 with vLLM?

#8 opened 7 months ago by