---
license: apache-2.0
language:
  - en
tags:
  - sft
  - causal-lm
  - qwen3
  - erebus
  - chat
  - instruct
library_name: transformers
pipeline_tag: text-generation
base_model: soyrsoyr/erebus-v2-1.5b-base
---

# Erebus v2 1.5B - Instruct

A 1.5B parameter chat model fine-tuned from [erebus-v2-1.5b-base](https://huggingface.co/soyrsoyr/erebus-v2-1.5b-base) on SmolTalk for instruction following.

## Training

| | |
|---|---|
| **Base model** | erebus-v2-1.5b-base (5.5B token pretrain) |
| **SFT dataset** | HuggingFaceTB/smoltalk (~1M examples) |
| **Epochs** | 1 |
| **LR** | 2e-5 (cosine decay) |
| **Batch** | 4 per device x 4 GPUs x 4 grad accum = 64 |
| **Steps** | 16,245 |
| **Time** | 34.5 hours on 4x A100-SXM4-80GB |
| **Final loss** | ~1.85 |

## 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

```python
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

| Variant | Description | Link |
|---|---|---|
| **Base** | Pretrained model | [soyrsoyr/erebus-v2-1.5b-base](https://huggingface.co/soyrsoyr/erebus-v2-1.5b-base) |
| **Instruct** | SFT on SmolTalk (this) | [soyrsoyr/erebus-v2-1.5b-instruct](https://huggingface.co/soyrsoyr/erebus-v2-1.5b-instruct) |
| **Tool** | SFT on xLAM for function calling | [soyrsoyr/erebus-v2-1.5b-tool](https://huggingface.co/soyrsoyr/erebus-v2-1.5b-tool) |

## License

Apache 2.0