LoRA Speedrun – a public wall-clock leaderboard for fine-tuning techniques
GitHub repository Saivineeth147/lora-speedrun enables speedrunning LoRA fine-tuning for the Qwen2.5-1.5B model on a single L40S GPU, aiming for ≥ 57% accuracy on GSM8K. The project features a frozen task and hardware setup, with a public leaderboard that requires independent verification of timing runs conducted on Modal's sandbox using free compute credits.
github.com
6 min
7/20/2026
Fine-tuning an LLM to write docs like it's 1995
Fine-tuning an LLM can enable it to generate documentation in a style reminiscent of 1995. Local deployment of specialized LLMs is anticipated to become more common among tech writers by 2030, although current powerful connected models dominate.
passo.uno
11 min
6/5/2026
Qwen3.5 Fine-Tuning Guide – Unsloth Documentation
Qwen3.5 can be fine-tuned locally with Unsloth, supporting both vision and text fine-tuning for model sizes ranging from 0.8B to 122B. Unsloth enables Qwen3.5 to train 1.5× faster and use 50% less VRAM compared to FA2 setups, with specific VRAM requirements for bf16 LoRA across different model sizes.
unsloth.ai
4 min
3/4/2026
LoRA Speedrun – a public wall-clock leaderboard for fine-tuning techniques
GitHub repository Saivineeth147/lora-speedrun enables speedrunning LoRA fine-tuning for the Qwen2.5-1.5B model on a single L40S GPU, aiming for ≥ 57% accuracy on GSM8K. The project features a frozen task and hardware setup, with a public leaderboard that requires independent verification of timing runs conducted on Modal's sandbox using free compute credits.
github.com
6 min
7/20/2026
Qwen3.5 Fine-Tuning Guide – Unsloth Documentation
Qwen3.5 can be fine-tuned locally with Unsloth, supporting both vision and text fine-tuning for model sizes ranging from 0.8B to 122B. Unsloth enables Qwen3.5 to train 1.5× faster and use 50% less VRAM compared to FA2 setups, with specific VRAM requirements for bf16 LoRA across different model sizes.
unsloth.ai
4 min
3/4/2026
Fine-tuning an LLM to write docs like it's 1995
Fine-tuning an LLM can enable it to generate documentation in a style reminiscent of 1995. Local deployment of specialized LLMs is anticipated to become more common among tech writers by 2030, although current powerful connected models dominate.
passo.uno
11 min
6/5/2026
LoRA Speedrun – a public wall-clock leaderboard for fine-tuning techniques
GitHub repository Saivineeth147/lora-speedrun enables speedrunning LoRA fine-tuning for the Qwen2.5-1.5B model on a single L40S GPU, aiming for ≥ 57% accuracy on GSM8K. The project features a frozen task and hardware setup, with a public leaderboard that requires independent verification of timing runs conducted on Modal's sandbox using free compute credits.
github.com
6 min
7/20/2026
Fine-tuning an LLM to write docs like it's 1995
Fine-tuning an LLM can enable it to generate documentation in a style reminiscent of 1995. Local deployment of specialized LLMs is anticipated to become more common among tech writers by 2030, although current powerful connected models dominate.
passo.uno
11 min
6/5/2026
Qwen3.5 Fine-Tuning Guide – Unsloth Documentation
Qwen3.5 can be fine-tuned locally with Unsloth, supporting both vision and text fine-tuning for model sizes ranging from 0.8B to 122B. Unsloth enables Qwen3.5 to train 1.5× faster and use 50% less VRAM compared to FA2 setups, with specific VRAM requirements for bf16 LoRA across different model sizes.
unsloth.ai
4 min
3/4/2026
No more articles to load