erebus-v2-1.5b-instruct

Erebus v2 1.5B - Instruct

A 1.5B parameter chat model fine-tuned from erebus-v2-1.5b-base on SmolTalk for instruction following.

Training

Known Limitations

• Repetition: The model tends to repeat phrases and sentences, especially in longer outputs. Greedy decoding amplifies this. Using repetition_penalty=1.2 helps.
• No stop control: The model often doesn't know when to stop generating, producing verbose responses that loop.
• Weak reasoning: GSM8K score is ~1.4% (flexible) / 0.08% (strict). Multi-step math reasoning is essentially absent due to the small pretraining budget (5.5B tokens vs 18T for Qwen2.5).
• Code: Can produce simple correct functions (e.g. is_prime) but explanations degenerate into repetition.

These are primarily a consequence of the small pretraining token budget, not the architecture or SFT data.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "soyrsoyr/erebus-v2-1.5b-instruct",
    torch_dtype="bfloat16",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("soyrsoyr/erebus-v2-1.5b-instruct")

messages = [{"role": "user", "content": "What is the capital of France?"}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200, repetition_penalty=1.2)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))

Variants

License

Apache 2.0