beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
LIVE──────── · ──:──:── UTCabout
beam
beam
Discover
PulseActivityAnalyticsBest forMapOrgs
Niches
AgentsMCPRAGCoding AssistantsInference & ServingVector DBs
Personal
WatchlistCompareWeekly report
?
Sign in
magic link · no password
All niches
Nichefine-tuning

Fine-Tuning

[TOOLS_TRACKED]81
[ACCELERATING]0
[DYING]0
[AVG_VELOCITY]0.14/10
See our pick → Best Fine-Tuning
[ACCELERATING]

Accelerating

0

No accelerating tools right now.

[STABLE]

Stable

6
Tool
Velocity
Trend 30d
Δ 7d
Stars
Class
  • hiyouga/LlamaFactoryUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
    1.83↑ +19072kStable
  • unslothai/unslothUnsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
    1.62↑ +51067kStable
  • modelscope/ms-swiftUse PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).
    1.16↑ +5315kStable
  • datawhalechina/self-llm《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
    1.08↑ +7731kStable
  • axolotl-ai-cloud/axolotlGo ahead and axolotl questions
    1.03↑ +2312kStable
  • ludwig-ai/ludwigLow-code framework for building custom LLMs, neural networks, and other AI models
    0.48↑ +412kStable
[STALLING]

Stalling and dying

3
Tool
Velocity
Trend 30d
Δ 7d
Stars
Class
  • AI-Hypercomputer/maxtextA simple, performant and scalable Jax LLM!
    1.20↑ +52.3kStalling
  • NVIDIA-NeMo/CuratorScalable data pre processing and curation toolkit for LLMs
    1.00↑ +61.6kStalling
  • rasbt/reasoning-from-scratchImplement a reasoning LLM in PyTorch from scratch, step by step
    0.48↑ +294.6kStalling
LIVE──────── · ──:──:── UTCabout