LLM EXPLORER 66,613 MODELS INDEXED

Qlora Flan 65B by timdettmers

By timdettmers · 0 downloads
HF Repo ↗ Copy URL

Qlora Flan 65B is an open-source language model by timdettmers. Features: 65b LLM, VRAM: 3.2GB, LLM Explorer Score: 0.07.

  Arxiv:2302.13971   Arxiv:2305.14314   Adapter   Finetuned   Lora   Region:us
Model Card on HF 🤗: https://huggingface.co/timdettmers/qlora-flan-65b 

Qlora Flan 65B Parameters and Internals

Model Type 
causal language model
Use Cases 
Areas:
research
Additional Notes 
Models utilize NormalFloat4 datatype for base model and LoRA adapters on all linear layers with BFloat16 for computation.
Training Details 
Data Sources:
Alpaca, HH-RLHF, Unnatural Instr., Chip2, Longform, Self-Instruct, FLAN v2
Methodology:
Quantized Low-Rank Adapter (QLoRA) tuning
Model Architecture:
LoRA adapters on top of LLaMA models
Input Output 
Input Format:
Expected as text prompts formatted for dialogue.
Accepted Modalities:
text
Output Format:
Textual responses as a language model.
Performance Tips:
Loading in 16-bit may improve inference speed. Active development for efficient 4-bit inference kernels.
LLM NameQlora Flan 65B
Repository 🤗https://huggingface.co/timdettmers/qlora-flan-65b 
Model Size65b
Required VRAM3.2 GB
Updated2026-08-04
Maintainertimdettmers
Model Files  3.2 GB
Model ArchitectureAdapter
Is Biasednone
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesgate_proj|down_proj|up_proj|q_proj|k_proj|v_proj|o_proj
LoRA Alpha16
LoRA Dropout0.05
R Param64

Best Alternatives to Qlora Flan 65B

Best Alternatives
Context / RAM
Downloads
Likes
Airoboros 65B Gpt4 1.4 Peft0K / 1.6 GB120
Alpaca Lora 65B En Pt Es Ca0K / 0.1 GB02
...os 65B Gpt4 1.4.1 PI 8192 Peft0K / 1.6 GB01
Enterredaas 65B QLoRA0K / 1.6 GB04
Saiga 65b Lora0K / 0.3 GB06
Guanaco 65B0K / 3.2 GB088
VicUnlocked Alpaca 65B QLoRA0K / 1.6 GB016
Qlora Self Instruct 65B0K / 3.2 GB02
Alpaca Lora 65B0K / 0.1 GB025
Alpaca 65B0K / 0.1 GB017
Note: green Score (e.g. "73.2") means that the model is better than timdettmers/qlora-flan-65b.