277 lines
4.8 KiB
Markdown
277 lines
4.8 KiB
Markdown
|
|
---
|
|
license: apache-2.0
|
|
language:
|
|
- en
|
|
library_name: transformers
|
|
pipeline_tag: text-generation
|
|
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
|
tags:
|
|
- llm
|
|
- chatbot
|
|
- text-generation
|
|
- causal-lm
|
|
- harness
|
|
- algosciencelab
|
|
- vlsi
|
|
- coding
|
|
- reasoning
|
|
- pytorch
|
|
widget:
|
|
- example_title: Python Example
|
|
messages:
|
|
- role: system
|
|
content: You are Harness, an AI assistant created by Algo Science Lab.
|
|
- role: user
|
|
content: Write a Python function that calculates the factorial of a number.
|
|
---
|
|
|
|
<div align="center">
|
|
|
|
# Harness-1B
|
|
|
|
### Developed by Algo Science Lab
|
|
|
|
**Author:** Shahrear Hossain
|
|
|
|
**Hugging Face:** https://huggingface.co/algoscienceacademy
|
|
|
|
</div>
|
|
|
|
---
|
|
|
|
# Harness-1B
|
|
|
|
Harness-1B is a lightweight large language model developed by **Algo Science Lab** for instruction following, coding assistance, reasoning, mathematics, electronics, semiconductor engineering, VLSI design, and general conversational AI.
|
|
|
|
The model contains approximately **1 billion parameters**, making it suitable for local deployment while providing strong performance for everyday AI tasks.
|
|
|
|
Harness-1B has been fine-tuned to provide accurate, helpful, and concise responses across a wide variety of technical and general domains.
|
|
|
|
---
|
|
|
|
# Features
|
|
|
|
- General conversation
|
|
- Code generation
|
|
- Python programming
|
|
- C programming
|
|
- C++ programming
|
|
- Rust programming
|
|
- Java programming
|
|
- JavaScript
|
|
- TypeScript
|
|
- Verilog HDL
|
|
- SystemVerilog
|
|
- VHDL
|
|
- RTL Design
|
|
- FPGA Development
|
|
- ASIC Design
|
|
- CMOS Digital Design
|
|
- Semiconductor Engineering
|
|
- VLSI Design
|
|
- Mathematics
|
|
- Electronics
|
|
- Physics
|
|
- Problem Solving
|
|
- Technical Documentation
|
|
- AI Research Assistance
|
|
|
|
---
|
|
|
|
# Model Details
|
|
|
|
| Property | Value |
|
|
|----------|-------|
|
|
| Model Name | Harness-1B |
|
|
| Organization | Algo Science Lab |
|
|
| Hugging Face Username | algoscienceacademy |
|
|
| Parameters | ~1 Billion |
|
|
| Architecture | Llama-based |
|
|
| Model Type | Causal Language Model |
|
|
| Context Length | 2048 Tokens *(or your trained context size)* |
|
|
| Precision | FP16 / BF16 / GGUF |
|
|
| Framework | PyTorch |
|
|
| License | Apache-2.0 |
|
|
|
|
---
|
|
|
|
# Intended Uses
|
|
|
|
Harness-1B is designed for:
|
|
|
|
- AI Chatbots
|
|
- Programming Assistant
|
|
- Educational Applications
|
|
- Research
|
|
- Embedded AI
|
|
- Local AI Deployment
|
|
- Engineering Assistance
|
|
- Electronics Design
|
|
- FPGA Development
|
|
- ASIC/VLSI Workflow
|
|
- RTL Development
|
|
- Automation
|
|
- Documentation
|
|
|
|
---
|
|
|
|
# Example
|
|
|
|
```python
|
|
from transformers import pipeline
|
|
|
|
pipe = pipeline(
|
|
"text-generation",
|
|
model="algoscienceacademy/Harness-1B",
|
|
device_map="auto"
|
|
)
|
|
|
|
messages = [
|
|
{
|
|
"role": "system",
|
|
"content": "You are Harness, an AI assistant created by Algo Science Lab."
|
|
},
|
|
{
|
|
"role": "user",
|
|
"content": "Write a Python program to print Fibonacci numbers."
|
|
}
|
|
]
|
|
|
|
prompt = pipe.tokenizer.apply_chat_template(
|
|
messages,
|
|
tokenize=False,
|
|
add_generation_prompt=True
|
|
)
|
|
|
|
output = pipe(
|
|
prompt,
|
|
max_new_tokens=256,
|
|
temperature=0.7,
|
|
)
|
|
|
|
print(output[0]["generated_text"])
|
|
```
|
|
|
|
---
|
|
|
|
# GGUF Usage
|
|
|
|
Harness-1B is also available in GGUF format for:
|
|
|
|
- llama.cpp
|
|
- LM Studio
|
|
- Jan
|
|
- Open WebUI
|
|
- KoboldCpp
|
|
- Ollama (after conversion)
|
|
|
|
Example:
|
|
|
|
```bash
|
|
./main \
|
|
-m Harness-1B-Q4_K_M.gguf \
|
|
-p "Explain CMOS Inverter."
|
|
```
|
|
|
|
---
|
|
|
|
# Training
|
|
|
|
Harness-1B is trained and fine-tuned using open-source datasets and instruction-following techniques.
|
|
|
|
Possible data sources include:
|
|
|
|
- SlimPajama
|
|
- StarCoderData
|
|
- UltraChat
|
|
- UltraFeedback
|
|
|
|
Additional custom datasets may have been used during supervised fine-tuning.
|
|
|
|
---
|
|
|
|
# Capabilities
|
|
|
|
Harness-1B can:
|
|
|
|
- Answer questions
|
|
- Explain concepts
|
|
- Generate code
|
|
- Debug code
|
|
- Write documentation
|
|
- Solve mathematics
|
|
- Explain algorithms
|
|
- Assist with VLSI
|
|
- Help with FPGA design
|
|
- Generate Verilog
|
|
- Generate SystemVerilog
|
|
- Produce technical reports
|
|
|
|
---
|
|
|
|
# Limitations
|
|
|
|
Harness-1B may:
|
|
|
|
- Produce incorrect information.
|
|
- Generate outdated knowledge.
|
|
- Make reasoning mistakes.
|
|
- Require verification for safety-critical applications.
|
|
- Require human review for production environments.
|
|
|
|
---
|
|
|
|
# Hardware Requirements
|
|
|
|
Recommended:
|
|
|
|
- 8 GB RAM (Q4 GGUF)
|
|
- 12 GB RAM (Q6 GGUF)
|
|
- 16 GB RAM (FP16)
|
|
- CUDA GPU recommended but optional
|
|
|
|
---
|
|
|
|
# Citation
|
|
|
|
```bibtex
|
|
@misc{Harness1B,
|
|
title={Harness-1B},
|
|
author={Algo Science Lab},
|
|
year={2026},
|
|
publisher={Hugging Face},
|
|
howpublished={https://huggingface.co/algoscienceacademy/Harness-1B}
|
|
}
|
|
```
|
|
|
|
---
|
|
|
|
# License
|
|
|
|
Apache License 2.0
|
|
|
|
---
|
|
|
|
# Acknowledgements
|
|
|
|
Harness-1B builds upon open-source language model research and would not be possible without the work of the open-source AI community, including:
|
|
|
|
- Meta AI (Llama Architecture)
|
|
- TinyLlama Project
|
|
- Hugging Face
|
|
- PyTorch
|
|
- Transformers
|
|
- llama.cpp
|
|
|
|
---
|
|
|
|
# Contact
|
|
|
|
**Organization:** Algo Science Lab
|
|
|
|
**Hugging Face:** https://huggingface.co/algoscienceacademy
|
|
|
|
---
|
|
|
|
Made with ❤️ by Algo Science Lab. |