RichardErkhov/dreamgen_-_WizardLM-2-7B-gguf

Quantization made by Richard Erkhov.

WizardLM-2-7B - GGUF

Model creator: https://huggingface.co/dreamgen/
Original model: https://huggingface.co/dreamgen/WizardLM-2-7B/

Name	Quant method	Size
WizardLM-2-7B.Q2_K.gguf	Q2_K	2.53GB
WizardLM-2-7B.IQ3_XS.gguf	IQ3_XS	2.81GB
WizardLM-2-7B.IQ3_S.gguf	IQ3_S	2.96GB
WizardLM-2-7B.Q3_K_S.gguf	Q3_K_S	2.95GB
WizardLM-2-7B.IQ3_M.gguf	IQ3_M	3.06GB
WizardLM-2-7B.Q3_K.gguf	Q3_K	3.28GB
WizardLM-2-7B.Q3_K_M.gguf	Q3_K_M	3.28GB
WizardLM-2-7B.Q3_K_L.gguf	Q3_K_L	3.56GB
WizardLM-2-7B.IQ4_XS.gguf	IQ4_XS	3.67GB
WizardLM-2-7B.Q4_0.gguf	Q4_0	3.83GB
WizardLM-2-7B.IQ4_NL.gguf	IQ4_NL	3.87GB
WizardLM-2-7B.Q4_K_S.gguf	Q4_K_S	3.86GB
WizardLM-2-7B.Q4_K.gguf	Q4_K	4.07GB
WizardLM-2-7B.Q4_K_M.gguf	Q4_K_M	4.07GB
WizardLM-2-7B.Q4_1.gguf	Q4_1	4.24GB
WizardLM-2-7B.Q5_0.gguf	Q5_0	4.65GB
WizardLM-2-7B.Q5_K_S.gguf	Q5_K_S	4.65GB
WizardLM-2-7B.Q5_K.gguf	Q5_K	4.78GB
WizardLM-2-7B.Q5_K_M.gguf	Q5_K_M	4.78GB
WizardLM-2-7B.Q5_1.gguf	Q5_1	5.07GB
WizardLM-2-7B.Q6_K.gguf	Q6_K	5.53GB
WizardLM-2-7B.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0

🏠 WizardLM-2 Release Blog

🤗 HF Repo •🐱 Github Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder] • 📃 [WizardMath]

👋 Join our Discord

News 🔥🔥🔥 [2024/04/15]

We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent. New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.

WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works and consistently outperforms all the existing state-of-the-art opensource models.
WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.

For more details of WizardLM-2 please read our release blog post and upcoming paper.

Model Details

Model name: WizardLM-2 7B
Developed by: WizardLM@Microsoft AI
Base model: mistralai/Mistral-7B-v0.1
Parameters: 7B
Language(s): Multilingual
Blog: Introducing WizardLM-2
Repository: https://github.com/nlpxucan/WizardLM
Paper: WizardLM-2 (Upcoming)
License: Apache2.0

Model Capacities

MT-Bench

We also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. The WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. Meanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.

Human Preferences Evaluation

We carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. We report the win:loss rate without tie:

WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.
WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.
WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.

Method Overview

We built a fully AI powered synthetic training system to train WizardLM-2 models, please refer to our blog for more details of this system.

Usage

❗Note for model system prompts usage:

WizardLM-2 adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, 
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......

Inference WizardLM-2 Demo Script

We provide a WizardLM-2 inference demo code on our github.