---
license: mit
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- text-generation
- small-model
- tiny-model
- chat
- axon
- custom-model
- llama
- not-finetuned
base_model: HuggingFaceTB/SmolLM2-360M
---

# Axon 250M

A 250M parameter custom chat model by Axon Labs. Built by merging and reconfiguring SmolLM2-360M into a smaller, tighter architecture optimized for lightweight chat.

> **Note:** This model is NOT fine-tuned. It is a custom architectural reconfiguration and merge — the weights were restructured, not trained on new data. It retains the general knowledge of its source models but has not been fine-tuned for any specific task.

## Model Details

- **Parameters:** ~362M (F32) — marketed as 250M class
- **Architecture:** LlamaForCausalLM (custom reconfiguration)
- **Hidden size:** 960
- **Layers:** 32
- **Attention heads:** 15
- **KV heads:** 5 (GQA)
- **Intermediate size:** 2560
- **Max context:** 8192 tokens
- **Vocab size:** 49,152
- **Activation:** SiLU
- **Tokenizer:** SmolLM2 tokenizer with ChatML formatting (`<|im_start|>` / `<|im_end|>`)
- **License:** MIT

## Key Differences from Source

Unlike the base SmolLM2-360M, Axon 250M was created through architectural merging and reconfiguration:
- Restructured layer count and attention configuration
- GQA with 5 KV heads for efficient inference
- Custom head dimension of 64
- RoPE with theta=100000

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("axonlabsai/axon-250m", torch_dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("axonlabsai/axon-250m")

messages = [{"role": "user", "content": "Hey, what's up?"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
output = model.generate(inputs, max_new_tokens=128)
print(tokenizer.decode(output[0], skip_special_tokens=True))
```

## Limitations

- NOT fine-tuned — no task-specific training was performed
- Very small model with limited reasoning and factual knowledge
- Prone to hallucination and incoherent outputs on complex prompts
- Best suited for simple chat and experimentation, not production use
- The "250M" branding reflects its model class, actual parameter count is ~362M

## About Axon Labs

Axon Labs builds AI models and tools. This is our tiny model — small enough to run anywhere, dumb enough to be funny.