Update README.md

README.md

@@ -1,66 +1,277 @@
+
 ---
 license: apache-2.0
-datasets:
-- cerebras/SlimPajama-627B
-- bigcode/starcoderdata
-- HuggingFaceH4/ultrachat_200k
-- HuggingFaceH4/ultrafeedback_binarized
 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: Fibonacci (Python)
+  - example_title: Python Example
     messages:
-    - role: system
-      content: You are a chatbot who can help code!
-    - role: user
-      content: Write me a function to calculate the first 10 digits of the fibonacci sequence in Python and print it out to the CLI.
+      - 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">
 
-# TinyLlama-1.1B
+# Harness-1B
+
+### Developed by Algo Science Lab
+
+**Author:** Shahrear Hossain
+
+**Hugging Face:** https://huggingface.co/algoscienceacademy
+
 </div>
 
-https://github.com/jzhang38/TinyLlama
+---
 
-The TinyLlama project aims to **pretrain** a **1.1B Llama model on 3 trillion tokens**. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01. 
+# 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.
 
-We adopted exactly the same architecture and tokenizer as Llama 2. This means TinyLlama can be plugged and played in many open-source projects built upon Llama. Besides, TinyLlama is compact with only 1.1B parameters. This compactness allows it to cater to a multitude of applications demanding a restricted computation and memory footprint.
+The model contains approximately **1 billion parameters**, making it suitable for local deployment while providing strong performance for everyday AI tasks.
 
-#### This Model
-This is the chat model finetuned on top of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T). **We follow [HF's Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-alpha)'s training recipe.** The model was " initially fine-tuned on a variant of the [`UltraChat`](https://huggingface.co/datasets/stingning/ultrachat) dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. 
-We then further aligned the model with [🤗 TRL's](https://github.com/huggingface/trl) `DPOTrainer` on the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, which contain 64k prompts and model completions that are ranked by GPT-4." 
+Harness-1B has been fine-tuned to provide accurate, helpful, and concise responses across a wide variety of technical and general domains.
 
+---
 
-#### How to use
-You will need the transformers>=4.34
-Do check the [TinyLlama](https://github.com/jzhang38/TinyLlama) github page for more information.
+# Features
 
-```python
-# Install transformers from source - only needed for versions <= v4.34
-# pip install git+https://github.com/huggingface/transformers.git
-# pip install accelerate
+- 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
 
-import torch
+```python
 from transformers import pipeline
 
-pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v1.0", torch_dtype=torch.bfloat16, device_map="auto")
+pipe = pipeline(
+    "text-generation",
+    model="algoscienceacademy/Harness-1B",
+    device_map="auto"
+)
 
-# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
 messages = [
     {
         "role": "system",
-        "content": "You are a friendly chatbot who always responds in the style of a pirate",
+        "content": "You are Harness, an AI assistant created by Algo Science Lab."
     },
-    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
+    {
+        "role": "user",
+        "content": "Write a Python program to print Fibonacci numbers."
+    }
 ]
-prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
-print(outputs[0]["generated_text"])
-# <|system|>
-# You are a friendly chatbot who always responds in the style of a pirate.</s>
-# <|user|>
-# How many helicopters can a human eat in one sitting?</s>
-# <|assistant|>
-# ...
-```
+
+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.