Dementor oassist adapters
Collection
Complete set of Llama-3.1-8B LoRA adapters (40 SFT + 36 DPO) trained on OpenAssistant to imitate other models. • 76 items • Updated
Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
dementor-research/oasst-llama-3.1-8b-as-nemotron-nano-sft-seed43
This model was fine-tuned from meta-llama/Llama-3.1-8B-Instruct using Tinker and tinker-cookbook.
Model details
- Base model: meta-llama/Llama-3.1-8B-Instruct
- Format: LoRA adapter (PEFT)
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base, "dementor-research/oasst-llama-3.1-8b-as-nemotron-nano-sft-seed43")
Framework versions
- tinker-cookbook: 0.4.1
- transformers: 5.5.3
- torch: 2.12.0
- Downloads last month
- 15
Model tree for dementor-research/oasst-llama-3.1-8b-as-nemotron-nano-sft-seed43
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct