Tinyllama 1.1B Chat V0.6 GGUF

🚀 TinyLlama/TinyLlama-1.1B-Chat-v0.6-GGUF

Quantized GGUF model files for TinyLlama-1.1B-Chat-v0.6 from TinyLlama. This project provides quantized models to optimize resource usage and enhance performance.

🚀 Quick Start

Model Information

Quantized Model Files

✨ Features

Original Model Goals

The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, it can achieve this within a span of "just" 90 days using 16 A100 - 40G GPUs 🚀🚀. The training started on 2023 - 09 - 01.

Model Advantages

• Compatibility: It adopted exactly the same architecture and tokenizer as Llama 2, which means TinyLlama can be plugged and played in many open - source projects built upon Llama.
• Compactness: TinyLlama is compact with only 1.1B parameters, allowing it to cater to a multitude of applications demanding a restricted computation and memory footprint.

This Model's Training

• Finetuning Base: This is the chat model finetuned on top of TinyLlama/TinyLlama-1.1B-intermediate-step-955k-2T.
• Training Recipe: It follows HF's Zephyr's training recipe. The model was initially fine - tuned on a variant of the UltraChat dataset, which contains a diverse range of synthetic dialogues generated by ChatGPT. Then it was further aligned with 🤗 TRL's DPOTrainer on the openbmb/UltraFeedback dataset, which contains 64k prompts and model completions that are ranked by GPT - 4.

💻 Usage Examples

Basic Usage

# Install transformers from source - only needed for versions <= v4.34
# pip install git+https://github.com/huggingface/transformers.git
# pip install accelerate

import torch
from transformers import pipeline

pipe = pipeline("text-generation", model="TinyLlama/TinyLlama-1.1B-Chat-v0.6", torch_dtype=torch.bfloat16, 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",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
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|>
# ...

📚 Documentation

Prerequisites

You will need transformers>=4.34. Do check the TinyLlama github page for more information.

Original Model Card

You can find more details about the original model at TinyLlama-1.1B.

Model Training Details

This model is a chat - finetuned version based on TinyLlama/TinyLlama-1.1B-intermediate-step-955k-2T. The training process involves multiple steps and datasets, as described above.

📄 License

This project is under the apache - 2.0 license.