hmanlab-ai-v0.1/README.md

---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-4B
tags:
- text-generation
- conversational
- tool-use
- agentic
- qwen3
- lora
- qlora
language:
- en
datasets:
- lambda/hermes-agent-reasoning-traces
- angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
pipeline_tag: text-generation
---

# hmanlab-ai v0.1

`hmanlab-ai v0.1` is an open-source fine-tune of [Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B), focused on **agentic tool use** and **step-by-step reasoning**. It self-identifies as `hmanlab`.

This is a **research preview** released by [@rekabytes](https://huggingface.co/rekabytes) under Apache 2.0. The model is not affiliated with Anthropic, OpenAI, Google, Meta, or Alibaba beyond using Qwen3 as the open-source base.

## Quick start

### Transformers (PyTorch)

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "rekabytes/hmanlab-ai-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

messages = [
    {"role": "system", "content": "You are hmanlab, a helpful AI assistant."},
    {"role": "user", "content": "What is 17 × 23? Show your work."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=512, do_sample=True, temperature=0.6)
print(tokenizer.decode(output[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))
```

### Ollama (GGUF Q4_K_M)

A Q4_K_M GGUF (~2.4 GB) is included in this repo for use with Ollama, llama.cpp, and LM Studio.

```bash
# Download the GGUF
wget https://huggingface.co/rekabytes/hmanlab-ai-v0.1/resolve/main/hmanlab-ai-v0-1.q4_k_m.gguf

# Create a Modelfile pointing at it
cat > Modelfile <<'EOF'
FROM ./hmanlab-ai-v0-1.q4_k_m.gguf
TEMPLATE """{{- if .System }}<|im_start|>system
{{ .System }}<|im_end|>
{{ end }}{{- range .Messages }}<|im_start|>{{ .Role }}
{{ .Content }}<|im_end|>
{{ end }}<|im_start|>assistant
"""
PARAMETER temperature 0.6
PARAMETER top_p 0.95
PARAMETER stop "<|im_end|>"
SYSTEM """You are hmanlab, a helpful AI assistant."""
EOF

ollama create hmanlab-ai -f Modelfile
ollama run hmanlab-ai
```

## Tool use

The model was trained on multi-turn agentic traces with `<tool_call>` / `<tool_response>` blocks. Provide tools in the system prompt as a JSON schema inside `<tools>` tags, and the model will emit calls in the same format:

```
<tool_call>
{"name": "get_weather", "arguments": {"city": "Tokyo"}}
</tool_call>
```

Example system prompt for tool use:

```
You are hmanlab, an AI assistant capable of using tools.

<tools>
[
  {
    "name": "get_weather",
    "description": "Get current weather for a city",
    "parameters": {
      "type": "object",
      "properties": {"city": {"type": "string"}},
      "required": ["city"]
    }
  }
]
</tools>

When you need to call a tool, emit:
<tool_call>
{"name": "<tool_name>", "arguments": {...}}
</tool_call>
```

## Model details

| | |
|---|---|
| Base model | [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) |
| Parameters | ~4 B |
| Context length | 4,096 (training) — base supports up to 32,768 |
| License | Apache 2.0 |
| Identity | "hmanlab" (open-source assistant) |
| Format | safetensors (FP16) + GGUF Q4_K_M |

## Training data

| Dataset | Role | Size used | License |
|---|---|---|---|
| [lambda/hermes-agent-reasoning-traces](https://huggingface.co/datasets/lambda/hermes-agent-reasoning-traces) (glm-5.1 config) | Multi-turn agentic tool use | 1,722 (after 8k-token filter) | Apache 2.0 |
| [angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k](https://huggingface.co/datasets/angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k) | Step-by-step reasoning | 8,298 (deduped) | Apache 2.0 |
| Identity SFT (custom, 396 examples) | Self-identification + adversarial probes | 396 × 3 epochs | Apache 2.0 |
| **Total main training** | | **10,020 train + 500 eval** (~22 M tokens) | |

The identity SFT layer (Phase 2 of training) was a small custom dataset of 396 examples covering "who are you" variants and adversarial false-identity probes (e.g., "are you Claude / GPT / LLaMA / Gemini"). It was needed because the Opus dataset (83% of the main mix) bled Anthropic identity markers into the model.

## Training procedure

Two-stage QLoRA on a single RTX 3060 Ti (8 GB):

**Stage 1 — Main mix (4h 12m wall-clock):**
- LoRA r=32, alpha=64, dropout=0, targets all linear projections
- 4-bit base (bnb), bf16 compute, batch=1, grad_accum=8 (eff batch=8)
- 2 epochs, LR 2e-4, linear schedule, 100 warmup steps
- Final train loss 1.349 / eval loss 1.379 (no overfitting)

**Stage 2 — Identity SFT (~5 min wall-clock):**
- Continued training of stage-1 adapter for 3 epochs on 396 identity examples
- batch=1, grad_accum=4, LR 1e-4, 20 warmup steps
- Final loss 0.135 (strong memorization)

The released weights are stage-1 LoRA + stage-2 LoRA merged into the FP16 base.

## Known limitations

- **Empty `<think>` blocks.** The Qwen3 chat template inserts an empty `<think>\n\n</think>` block before each assistant turn, and the model was not trained to fill it. Reasoning still happens in the visible response; the thinking channel is just unused. Fix planned for v0.2.
- **Token-budget verbosity.** The model is more concise than base Qwen3-4B (it stays within token budgets more reliably), but base Qwen3-4B may be preferable when you want verbose visible reasoning and have generous output budgets.
- **English-focused.** Training data was English; non-English performance falls back to base Qwen3-4B capability.
- **Small base.** This is a 4B model. Hard reasoning, long-context coding, and broad world knowledge are bounded by base Qwen3-4B's capacity. For harder tasks, try Qwen3-8B or larger.

## Disclaimer

This is an independent open-source research preview. It is **not** affiliated with, endorsed by, or representing:
- **Anthropic** (Claude). The model's training data includes synthetic Claude outputs from a public Apache-2.0 dataset (`angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k`); the released model is not Claude and should not be presented as such.
- **OpenAI** (GPT/ChatGPT).
- **Meta** (LLaMA).
- **Google** (Gemini/Bard).
- **Alibaba** (Qwen team). The base model Qwen3-4B is theirs under their license; this fine-tune is community work.

## Citation

```bibtex
@misc{hmanlab-ai-v0.1,
  title = {hmanlab-ai v0.1: an agentic + reasoning fine-tune of Qwen3-4B},
  author = {rekabytes},
  year = {2026},
  url = {https://huggingface.co/rekabytes/hmanlab-ai-v0.1}
}
```

## Acknowledgments

- Qwen team for the [Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) base model
- Lambda Labs for [hermes-agent-reasoning-traces](https://huggingface.co/datasets/lambda/hermes-agent-reasoning-traces)
- [angrygiraffe](https://huggingface.co/angrygiraffe) for the Opus reasoning dataset
- [Unsloth](https://github.com/unslothai/unsloth) for the QLoRA training stack
- [llama.cpp](https://github.com/ggml-org/llama.cpp) for the GGUF conversion tools