SagaLM-slm1.1 (LoRA adapter)

LoRA adapter for SagaLM-slm1.1, fine-tuned on Qwen/Qwen2.5-3B-Instruct.

Training Data

Identity reinforcement samples (SagaLM identity)
Databricks Dolly 15k (general capability)

Identity Reinforcement

Identity-focused training samples ensure the model consistently identifies as SagaLM (not Qwen or any other model).

How to use

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct", device_map="auto")
model = PeftModel.from_pretrained(base, "venkateshchsagalm/SagaLM-slm1.1")
tokenizer = AutoTokenizer.from_pretrained("venkateshchsagalm/SagaLM-slm1.1")

Downloads last month: 19

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for venkateshchsagalm/SagaLM-slm1.1

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1365)

this model