Long-Context GRPO (unsloth.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of unsloth.ai: Long-Context GRPO

First screen, captured 1 year ago.

Looks similar

Screenshot of unsloth.ai: Phi-4 Bug Fixes

Phi-4 Bug Fixes (unsloth.ai)

171 points by danielhanchen 1 year ago | 50 comments

Screenshot of unsloth.ai: Fine-tune Google's Gemma 3

Fine-tune Google's Gemma 3 (unsloth.ai)

208 points by tomdekan 1 year ago | 68 comments

Screenshot of unsloth.ai: Run DeepSeek R1 Dynamic 1.58-bit

Run DeepSeek R1 Dynamic 1.58-bit (unsloth.ai)

701 points by noch 1 year ago | 308 comments

Unsloth blog post describing dynamic 1.58-bit quantization of DeepSeek-R1 671B, shrinking it to 131GB so users can run it locally.

deepseek-r1 quantization unsloth llm

Screenshot of unsloth.ai: Making LLM Training Faster with Unsloth and NVIDIA

Making LLM Training Faster with Unsloth and NVIDIA (unsloth.ai)

96 points by segmenta 5 months ago | 15 comments

Screenshot of unsloth.ai: Unsloth Dynamic 2.0 GGUFs

Unsloth Dynamic 2.0 GGUFs (unsloth.ai)

222 points by tosh 8 months ago | 61 comments

Screenshot of lmsys.org: How long can open-source LLMs truly promise on context length?

How long can open-source LLMs truly promise on context length?(lmsys.org)

174 points by dacheng2 3 years ago | 58 comments