Downloads · 30 days
6
15% of all-time downloads
llama2-7b-qlora-guanaco
abdur-rahman77/llama2-7b-qlora-guanaco
llama2-7b-qlora-guanaco is a text generation model from abdur-rahman77. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama2.
LoRA adapter for NousResearch/Llama-2-7b-chat-hf, fine-tuned with QLoRA (4-bit NF4, double-quant, bf16) on mlabonne/guanaco-llama2-1k (1,000 multilingual instructions, Llama-2 chat format). Final training loss 1.47 (f…
All-time downloads
39
Public
Repo size
67.6 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors67.1 MB · 94%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- llama2
- Access
- Public
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026
- SHA
- b80b8a35
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
Llama-2-7B Chat - QLoRA adapter (Guanaco-1k)
LoRA adapter for NousResearch/Llama-2-7b-chat-hf, fine-tuned with QLoRA (4-bit NF4, double-quant, bf16) on mlabonne/guanaco-llama2-1k (1,000 multilingual instructions, Llama-2 chat format). Final training loss 1.47 (from 2.06), 1 epoch / 125 steps.
Training
- LoRA r/alpha/dropout: 32/16/0.05, targets q_proj,v_proj
- Effective batch 8, lr 0.0002 cosine, max_seq_len 256
- paged_adamw_32bit, Kaggle T4
- transformers 4.56, trl 0.21, peft 0.15, bitsandbytes 0.47
Load the adapter on top of the base model with peft.PeftModel.from_pretrained.
- Task
- Text Generation
- Library
- peft
- License
- llama2
- Created
- Aug 31, 2026
- Updated
- Aug 31, 2026