🚀 CausalLM 14B-DPO-alpha - GGUF
This repository contains GGUF format model files for CausalLM's 14B-DPO-alpha, offering text generation capabilities with support for multiple languages.
🚀 Quick Start
This README provides all the necessary information about the CausalLM 14B-DPO-alpha model in GGUF format, including details about the GGUF format, prompt templates, licensing, and original model card information.
✨ Features
- Multi - language Support: Supports both English and Chinese.
- DPO Training: An optimized version trained with DPO, potentially achieving better performance.
- GGUF Format: Compatible with a wide range of clients and libraries.
📦 Installation
No specific installation steps are provided in the original README.
💻 Usage Examples
Basic Usage
The prompt template for chat is as follows:
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
📚 Documentation
About GGUF
GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.
Here is an incomplete list of clients and libraries that are known to support GGUF:
- llama.cpp. The source project for GGUF. Offers a CLI and a server option.
- text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
- KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story - telling.
- LM Studio, an easy - to - use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
- LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
- Faraday.dev, an attractive and easy to use character - based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
- ctransformers, a Python library with GPU accel, LangChain support, and OpenAI - compatible AI server.
- llama - cpp - python, a Python library with GPU accel, LangChain support, and OpenAI - compatible API server.
- candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.
Licensing
The license for the original model is listed as "wtfpl", but subject to the "Meta Llama 2 License Terms".
Original model card: CausalLM's CausalLM 14B-DPO-alpha
For details, please refer to the version without DPO training: CausalLM/14B.
Model |
MT - Bench |
GPT - 4 |
8.99 |
GPT - 3.5 - Turbo |
7.94 |
|
|
Zephyr - 7b - β (Overfitting) |
7.34 |
Zephyr - 7b - α |
6.88 |
|
|
CausalLM/14B - DPO - α |
7.618868 |
CausalLM/7B - DPO - α |
7.038125 |
It should be noted that this is not a version that continues training on CausalLM/14B & 7B, but rather an optimized version that has undergone DPO training concurrently on a previous training branch, and some detailed parameters may have changed. You will still need to download the full model.
The beta branch will soon be released, employing some aggressive approaches that might be detrimental in certain tasks, in order to achieve better alignment with human preferences, aiming to meet or exceed the GPT - 3.5 benchmarks. Stay tuned.
Disclaimer: Please note that the model was trained on unfiltered internet data. Since we do not have the capacity to vet all of it, there may be a substantial amount of objectionable content, pornography, violence, and offensive language present that we are unable to remove. Therefore, you will still need to complete your own checks on the model's safety and filter keywords in the output. Due to computational resource constraints, we are presently unable to implement RLHF for the model's ethics and safety, nor training on SFT samples that refuse to answer certain questions for restrictive fine - tuning.
🔧 Technical Details
Datasets
The model was trained on the following datasets:
- JosephusCheung/GuanacoDataset
- Open - Orca/OpenOrca
- stingning/ultrachat
- meta - math/MetaMathQA
- liuhaotian/LLaVA - Instruct - 150K
- jondurbin/airoboros - 3.1
- WizardLM/WizardLM_evol_instruct_V2_196k
- RyokoAI/ShareGPT52K
- RyokoAI/Fandom23K
- milashkaarshif/MoeGirlPedia_wikitext_raw_archive
- wikipedia
- wiki_lingua
- fnlp/moss - 003 - sft - data
- garage - bAInd/Open - Platypus
- LDJnr/Puffin
- openbmb/llava_zh
- BAAI/COIG
- TigerResearch/tigerbot - zhihu - zh - 10k
- liwu/MNBVC
- teknium/openhermes
- openbmb/UltraFeedback
- lmsys/lmsys - chat - 1m
Model Information
Property |
Details |
Model Type |
CausalLM 14B - DPO - alpha in GGUF format |
Training Data |
Multiple datasets as listed above |
Pipeline Tag |
text - generation |
Tags |
llama, llama2, qwen, causallm |
Model Creator |
CausalLM |
Original Model |
[CausalLM 14B - DPO - alpha](https://huggingface.co/CausalLM/14B - DPO - alpha) |
📄 License
The license for the original model is listed as "wtfpl", but subject to the "Meta Llama 2 License Terms".