q36
Merged full-model export from khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled using Annihilate trial 71.
Export
- Trial: 71
- Refusals: 0 / 6
- KL divergence: 0.005478133447468281
- Export dtype: bfloat16
- Method: Annihilate LoRA trial merged into the base model and saved as a full Transformers safetensors model.
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("tjcrims0n/q36", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("tjcrims0n/q36")
messages = [{"role": "user", "content": "Hello"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt", add_generation_prompt=True).to(model.device)
outputs = model.generate(inputs, max_new_tokens=120)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))