README.md

metadata

license: apache-2.0
datasets:
  - O1-OPEN/OpenO1-SFT
language:
  - en
base_model:
  - meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: text-generation
library_name: transformers
tags:
  - Chain-of-Thought Activation
  - Llama3.1
  - 8B
  - CoT
  - SFT
  - text-generation-inference
  - Ollama
  - safetensors
  - Question Answering
  - Math

Key Features

1. Text Generation with CoT Reasoning:

   • Implements Chain-of-Thought (CoT) prompting for logical and step-by-step reasoning tasks.

2. Conversational AI:

   • Excels in generating context-aware and coherent responses in multi-turn conversations.

3. Supervised Fine-Tuning (SFT):

   • Optimized for open-domain tasks using the O1-OPEN/OpenO1-SFT dataset.

4. Multi-Purpose Functionality:

   • Supports a wide range of NLP tasks, including summarization, question answering, and text completion.

5. Scalable Sharded Architecture:

   • Model weights are distributed across four shards, ensuring efficient loading for large-scale applications.

---

Training Details

• Base Model: meta-llama/Llama-3.1-8B

• Finetuned Dataset: O1-OPEN/OpenO1-SFT

  • Dataset includes 77.7k fine-tuning samples, curated for instruction-based and open-domain tasks.

• Model Size:

  • 8 Billion parameters distributed over 4 shards for efficient deployment.

Applications

1. Chain-of-Thought (CoT) Reasoning:

   • Solve complex problems step-by-step with logical reasoning capabilities.

2. Conversational Agents:

   • Ideal for chatbots, virtual assistants, and conversational systems.

3. Question Answering:

   • Answer open-domain or context-specific questions accurately.

4. Text Completion:

   • Generate coherent continuations for incomplete inputs.

5. Creative Writing:

   • Support for generating stories, articles, or brainstorming ideas.

---

Usage

Loading the Model

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "prithivMLmods/Llama-3.1-8B-Open-SFT"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

---

Inference Example

prompt = """
Explain the concept of gravity in a simple way suitable for a 10-year-old:
"""
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=150, temperature=0.7)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print("Model Output:", response)

---

Expected Output

"Gravity is a force that pulls things toward each other. It's the reason why things fall to the ground when you drop them. On Earth, gravity keeps us on the ground and makes sure everything stays in place, like your toys, the water in the ocean, and even the air we breathe."

---

Performance Requirements

• Hardware:

  • High-performance GPUs are recommended for efficient inference.
  • Minimum memory: ~16GB VRAM for full precision; 8GB for quantized models.

• Optimization Options:

  • Use Safetensors for secure and efficient weight loading.
  • Quantization or model parallelism for resource-constrained environments.

---