Downloads · 30 days
8
9% of all-time downloads
SagaLM-slm1
venkateshchsagalm/SagaLM-slm1
SagaLM-slm1 is a machine learning model from venkateshchsagalm. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
LoRA adapter for SagaLM-slm1, fine-tuned on Qwen/Qwen2.5-3B-Instruct.
All-time downloads
86
Public
Repo size
491 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pt240 MB · 65%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jul 20, 2026
- Updated
- Jul 28, 2026
- SHA
- 55e39e83
Base models
Model card
From the Hugging Face model README
SagaLM-slm1 (LoRA adapter)
LoRA adapter for SagaLM-slm1, fine-tuned on Qwen/Qwen2.5-3B-Instruct.
Training Data (12 sources, long-form filtered)
- OpenHermes 2.5, UltraChat 200k, OpenOrca, MetaMathQA,
- Function Calling (hypervariance), Open-Platypus,
- Glaive Code Assistant, Dolly 15k, ShareGPT GPT-4,
- Alpaca-GPT4, SlimOrca, MathInstruct
Only samples with detailed, long assistant answers were kept, training the model to always respond comprehensively.
Identity Reinforcement
5 identity-focused training samples were injected to ensure the model consistently identifies as SagaLM (not Qwen or any other model).
LoRA Configuration
- r = 16
- lora_alpha = 32
- lora_dropout = 0.05
- target_modules = ['up_proj', 'q_proj', 'down_proj', 'k_proj', 'gate_proj', 'v_proj', 'o_proj']
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")
tokenizer = AutoTokenizer.from_pretrained("venkateshchsagalm/SagaLM-slm1")
- Library
- peft
- Created
- Jul 20, 2026
- Updated
- Jul 28, 2026