← Explore by area/LLM Fine-tuning & Parameter-Efficient Adaptation

Cluster 637235

36 repos

Python · 12

lora ·211,320

peft ·211,320

llm ·211,302

moe ·181,252

llama ·181,218

fine-tuning ·179,520

transformers ·178,386

qlora ·156,455

deepseek ·151,048

qwen ·151,048

Related clusters

Cluster 63723427 LoRA and PEFT for Language Models8 LLM fine-tuning and parameter-efficient adaptation7 LLM Fine-tuning and Parameter Efficiency9 Mistral-based Text Generation Models35 Cluster 63674811

tomg-group-umd/LoRI-D_safety_llama3_rank_32

Model

Model Card for LoRI-D_safety_llama3_rank_32

6 commits

Madhurprash/Devstral-Small-2-24B-Instruct-2512-SFT-LoRA-OpenThoughts

Model

Model Card for devstral-sft

3 commits

RampPublic/portal-mistral-7b

Model

PorTAL refit for Mistral 7B v0.3

3 commits

RampPublic/portal-qwen3-4b

Model

PorTAL for Qwen3-4B

3 commits

RampPublic/portal-qwen3-1.7b

Model

PorTAL for Qwen3-1.7B

3 commits

RampPublic/portal-qwen3-8b

Model

PorTAL refit for Qwen3-8B

3 commits

RampPublic/portal-inkling

Model

PorTAL refit for Inkling

3 commits

RampPublic/portal-gemma-3-4b

Model

PorTAL cross-family refit for Gemma 3 4B

3 commits

RampPublic/portal-gemma-4-e2b

Model

PorTAL refit for Gemma 4 E2B

3 commits

mzhaoshuai/Llama-2-7b-hf-conf-sft

Model

RefAlign: RL with Similarity-based Rewards

11 commits

tuggspeedman-ai/SmolLM3-3B-summarize-dpo-lora

Model

SmolLM3-3B-summarize-dpo-lora

6 commits

tuggspeedman-ai/SmolLM3-3B-summarize-sft-lora

Model

SmolLM3-3B-summarize-sft-lora

4 commits

zhang-manyi/ProjAtlas-xLAM2-8B-FunctionCalling-lora

Model

ProjAtlas-xLAM2-8B-FunctionCalling-lora

4 commits

solanaclawd/clawd-solana-masterpiece-qwen15-lora

Model

Solana Clawd LoRA

4 commits

huggingface/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Python

21,691

1,857 commits

mzhaoshuai/Mistral-7B-v0.1-conf-refalign

Model

RefAlign: RL with Similarity-based Rewards

6 commits

tuggspeedman-ai/SmolVLM2-2.2B-chartqa-lora

Model

SmolVLM2-2.2B-chartqa-lora

6 commits

ArjunShukla/PromptForge-Optimizer

Model

PromptForge-Optimizer

6 commits

khudgins/Ornith-1.0-35B-ThinkingCap

Model

Ornith-1.0-35B — Thinking-Cap

4 commits

khudgins/Ornith-1.0-9B-ThinkingCap

Model

Ornith-1.0-9B — Thinking-Cap

5 commits

solanaclawd/solana-nvidia-trading-factory-8b-lora

Model

Solana NVIDIA Trading Factory LoRA

4 commits

solanaclawd/solana-clawd-core-ai-1.5b-lora

Model

Solana Clawd Core AI 1.5B LoRA

5 commits

harsha-gouru/peft-hybrid-paper

Research paper: LoRA placement determines continual learning outcomes in hybrid SSM-attention…

Python

2 commits

Shannon-Labs/shannon-control-unit

Shannon Control Unit: Adaptive regularization via control theory for LLM training

Python

1 commits

paritok/paritok-4b-v1

Model

Compresses individual long files to as little as 5% of their original size (typical content…

17 commits

evilfreelancer/ruGPT-3.5-13B-lora

Model

ruGPT-3.5 13B LoRA: Adapter-Only Version

12 commits

hiyouga/LlamaFactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python

74,837

3,065 commits

hiyouga/LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Python

74,837

3,070 commits

tomg-group-umd/LoRI-D_code_llama3_rank_32

Model

Model Card for LoRI-D_code_llama3_rank_32

6 commits

wuwangzhang1216/abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular…

Python

238

143 commits

modelscope/swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3,…

Python

15,659

3,634 commits

modelscope/ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3,…

Python

15,659

3,653 commits

jackaduma/Vicuna-LoRA-RLHF-PyTorch

A full pipeline to finetune Vicuna LLM with LoRA and RLHF on consumer hardware. Implementation of…

Python

220

21 commits

whitecircle/halo

Halo is an open-source framework built by White Circle for training large language and multimodal…

Python

16 commits

AutoArk/TinyEngram

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

Python

1,374

42 commits

MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

Python

6,759

961 commits