Views
No views yet
⚠️ Preview release. Underperforms Wind Edge 1.6 by roughly 50% across benchmarks. Not recommended for any practical use.
| Task | Score | Notes |
|---|---|---|
| MMLU (boosted) | 0.08 / 1.00 | Boosted eval with few-shot scaffolding |
On MMLU: 0.08 on a boosted protocol means near-random performance even with prompt engineering assistance. Raw 0-shot will score lower. Wind Edge 1.6 scores roughly 2× this across comparable tasks. This model is not competitive.
1from transformers import AutoModelForCausalLM, AutoTokenizer
2
3model = AutoModelForCausalLM.from_pretrained("arthu1/wind-arc-1-5-preview")
4tokenizer = AutoTokenizer.from_pretrained("arthu1/wind-arc-1-5-preview")
5
6inputs = tokenizer("You are Wind Arc, a helpful AI assistant.\nUser: ", return_tensors="pt")
7output = model.generate(**inputs, max_new_tokens=512, temperature=0.6, top_p=0.9)
8print(tokenizer.decode(output[0], skip_special_tokens=True))<|im_start|>system
You are Wind-Arc-1.5, a compact AI assistant model. You are not a human.<|im_end|>
<|im_start|>user
{your message}<|im_end|>
<|im_start|>assistant
<think>
</think>| Property | Value |
|---|---|
| Architecture | Causal LM (decoder-only) |
| Status | Preview / Experimental |
| Org | north-ml1 |