mike dikka's picture

mike dikka

fgdrfgrgrdgdr

·

AI & ML interests

None yet

Recent Activity

liked a model 4 days ago

calcuis/hunyuan-gguf

liked a model 5 days ago

prithivMLmods/Llama-8B-Distill-CoT

reacted to lewtun's post with 🔥 5 days ago

We are reproducing the full DeepSeek R1 data and training pipeline so everybody can use their recipe. Instead of doing it in secret we can do it together in the open! 🧪 Step 1: replicate the R1-Distill models by distilling a high-quality reasoning corpus from DeepSeek-R1. 🧠 Step 2: replicate the pure RL pipeline that DeepSeek used to create R1-Zero. This will involve curating new, large-scale datasets for math, reasoning, and code. 🔥 Step 3: show we can go from base model -> SFT -> RL via multi-stage training. Follow along: https://github.com/huggingface/open-r1

View all activity

Organizations

None yet

fgdrfgrgrdgdr's activity

New activity in aoxo/flux.1dev-abliterated 13 days ago

Quick questions

#1 opened 13 days ago by

New activity in nyanko7/flux-dev-de-distill about 1 month ago

Could you share the de-distill training scripts?

#6 opened 4 months ago by

New activity in mergekit-community/sexeh_time_testing about 1 month ago

How to evaluate this/test this properly?

#1 opened about 1 month ago by

New activity in ggml-org/gguf-my-repo 2 months ago

Error quantizing: b'/bin/sh: 1: ./llama.cpp/llama-quantize: not found\n'

#136 opened 3 months ago by

New activity in Gourieff/ReActor 3 months ago

4 files marked as unsafe?

#2 opened 3 months ago by

New activity in fffiloni/consistent-character 3 months ago

Edit Text Prompt not Work

#20 opened 3 months ago by

New activity in comfyanonymous/flux_dev_scaled_fp8_test 3 months ago

Works great - Will you release how you did this?

#6 opened 3 months ago by

New activity in Comfy-Org/stable-diffusion-3.5-fp8 3 months ago

What means "scaled"? fp8 model only?

#4 opened 3 months ago by

What means "scaled"? fp8 model only?

#4 opened 3 months ago by