GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ludocomito
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
ludocomito
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-3B-Instructcheckpoint-500.65713387727737430.6417140785385581models/dpo_lora_bestThe DPO preference pairs were built from generated candidates scored by the TRIBE-derived reward. Higher-scoring candidates were used as chosen responses and lower-scoring candidates as rejected responses, with a minimum adjusted reward margin of 0.12.
This is an experimental research adapter for probing whether a brain-model-derived reward can steer a small instruction model toward poetic / affective text. It is not a general-purpose writing model and should be treated as a research artifact.
Example loading:
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "Qwen/Qwen2.5-3B-Instruct"adapter_id = "ludocomito/qwen2.5-3b-tribe-dpo-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)model = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id)The run used 1,024 scored generated candidates, balanced as 4 candidates for each of 256 prompts. The full 2,048 generated candidates were preserved locally, but only the balanced subset was scored by TRIBE for the final DPO run.
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_id = "Qwen/Qwen2.5-3B-Instruct"adapter_id = "ludocomito/qwen2.5-3b-tribe-dpo-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)model = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id)