Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) microsoft_WizardLM-2-7B - GGUF - Model creator: https://huggingface.co/lucyknada/ - Original model: https://huggingface.co/lucyknada/microsoft_WizardLM-2-7B/ | Name | Quant method | Size | | ---- | ---- | ---- | | [microsoft_WizardLM-2-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q2_K.gguf) | Q2_K | 2.53GB | | [microsoft_WizardLM-2-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [microsoft_WizardLM-2-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.IQ3_S.gguf) | IQ3_S | 2.96GB | | [microsoft_WizardLM-2-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [microsoft_WizardLM-2-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.IQ3_M.gguf) | IQ3_M | 3.06GB | | [microsoft_WizardLM-2-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q3_K.gguf) | Q3_K | 3.28GB | | [microsoft_WizardLM-2-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [microsoft_WizardLM-2-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [microsoft_WizardLM-2-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [microsoft_WizardLM-2-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q4_0.gguf) | Q4_0 | 3.83GB | | [microsoft_WizardLM-2-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [microsoft_WizardLM-2-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [microsoft_WizardLM-2-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q4_K.gguf) | Q4_K | 4.07GB | | [microsoft_WizardLM-2-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [microsoft_WizardLM-2-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q4_1.gguf) | Q4_1 | 4.24GB | | [microsoft_WizardLM-2-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q5_0.gguf) | Q5_0 | 4.65GB | | [microsoft_WizardLM-2-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [microsoft_WizardLM-2-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q5_K.gguf) | Q5_K | 4.78GB | | [microsoft_WizardLM-2-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [microsoft_WizardLM-2-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q5_1.gguf) | Q5_1 | 5.07GB | | [microsoft_WizardLM-2-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_WizardLM-2-7B.Q6_K.gguf) | Q6_K | 5.53GB | | [microsoft_WizardLM-2-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/lucyknada_-_microsoft_WizardLM-2-7B-gguf/blob/main/microsoft_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](https://wizardlm.github.io/WizardLM2) and upcoming paper. ## Model Details * **Model name**: WizardLM-2 7B * **Developed by**: WizardLM@Microsoft AI * **Base model**: [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) * **Parameters**: 7B * **Language(s)**: Multilingual * **Blog**: [Introducing WizardLM-2](https://wizardlm.github.io/WizardLM2) * **Repository**: [https://github.com/nlpxucan/WizardLM](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.

MTBench

**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.

Win

## Method Overview We built a **fully AI powered synthetic training system** to train WizardLM-2 models, please refer to our [blog](https://wizardlm.github.io/WizardLM2) for more details of this system.

Method

## 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. USER: Who are you? ASSISTANT: I am WizardLM....... ``` Inference WizardLM-2 Demo Script We provide a WizardLM-2 inference demo [code](https://github.com/nlpxucan/WizardLM/tree/main/demo) on our github.