Downloads · 30 days
0
saketgarodia1/llama2-7b-guanaco-qlora-adapter
llama2-7b-guanaco-qlora-adapter is a machine learning model from saketgarodia1. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This repository contains a PEFT LoRA adapter trained with QLoRA (4-bit NF4) for meta-llama/Llama-2-7b-chat-hf using a cleaned English-only subset of Guanaco-style instruction data.
Downloads · 30 days
0
Access
Public
Updated Dec 14, 2025
Repo size
160 MB
Likes
0
Public
Click a slice to open those files.
.safetensors160 MB · 97%
From the Hugging Face model README
This repository contains a PEFT LoRA adapter trained with QLoRA (4-bit NF4) for meta-llama/Llama-2-7b-chat-hf using a cleaned English-only subset of Guanaco-style instruction data.
✅ Important: This is NOT a full standalone model. It is only the adapter weights + config (+ tokenizer files).
To use it, you must load the base model and then apply this adapter.
adapter_model.safetensors — LoRA adapter weights (~160 MB)adapter_config.json — PEFT configuration (r, alpha, target_modules, etc.)tokenizer.json, tokenizer.model, tokenizer_config.json, special_tokens_map.json, chat_template.jinja) for conveniencemeta-llama/Llama-2-7b-chat-hfsaketgarodia1/guanaco-llama2-chat-entext fieldtrl.SFTTrainerr = 16lora_alpha = 32lora_dropout = 0.05target_modules = [q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj]Final eval (token-level cross-entropy on held-out eval set):
exp(eval_loss))Best checkpoint (selected by lowest eval loss):
checkpoint-400Note: Loss/perplexity measure how well the model predicts the next token on this dataset distribution. They do not fully capture helpfulness or instruction-following quality.
pip install -U transformers peft accelerate bitsandbytes