| Quantization made by Richard Erkhov. | |
| [Github](https://github.com/RichardErkhov) | |
| [Discord](https://discord.gg/pvy7H8DZMG) | |
| [Request more models](https://github.com/RichardErkhov/quant_request) | |
| WizardLM-2-7B-abliterated - GGUF | |
| - Model creator: https://huggingface.co/fearlessdots/ | |
| - Original model: https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated/ | |
| | Name | Quant method | Size | | |
| | ---- | ---- | ---- | | |
| | [WizardLM-2-7B-abliterated.Q2_K.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q2_K.gguf) | Q2_K | 2.53GB | | |
| | [WizardLM-2-7B-abliterated.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | |
| | [WizardLM-2-7B-abliterated.IQ3_S.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.IQ3_S.gguf) | IQ3_S | 2.96GB | | |
| | [WizardLM-2-7B-abliterated.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | |
| | [WizardLM-2-7B-abliterated.IQ3_M.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.IQ3_M.gguf) | IQ3_M | 3.06GB | | |
| | [WizardLM-2-7B-abliterated.Q3_K.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q3_K.gguf) | Q3_K | 3.28GB | | |
| | [WizardLM-2-7B-abliterated.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | |
| | [WizardLM-2-7B-abliterated.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | |
| | [WizardLM-2-7B-abliterated.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | |
| | [WizardLM-2-7B-abliterated.Q4_0.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q4_0.gguf) | Q4_0 | 3.83GB | | |
| | [WizardLM-2-7B-abliterated.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | |
| | [WizardLM-2-7B-abliterated.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | |
| | [WizardLM-2-7B-abliterated.Q4_K.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q4_K.gguf) | Q4_K | 4.07GB | | |
| | [WizardLM-2-7B-abliterated.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | |
| | [WizardLM-2-7B-abliterated.Q4_1.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q4_1.gguf) | Q4_1 | 4.24GB | | |
| | [WizardLM-2-7B-abliterated.Q5_0.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q5_0.gguf) | Q5_0 | 4.65GB | | |
| | [WizardLM-2-7B-abliterated.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | |
| | [WizardLM-2-7B-abliterated.Q5_K.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q5_K.gguf) | Q5_K | 4.78GB | | |
| | [WizardLM-2-7B-abliterated.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | |
| | [WizardLM-2-7B-abliterated.Q5_1.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q5_1.gguf) | Q5_1 | 5.07GB | | |
| | [WizardLM-2-7B-abliterated.Q6_K.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q6_K.gguf) | Q6_K | 5.53GB | | |
| | [WizardLM-2-7B-abliterated.Q8_0.gguf](https://huggingface.co/RichardErkhov/fearlessdots_-_WizardLM-2-7B-abliterated-gguf/blob/main/WizardLM-2-7B-abliterated.Q8_0.gguf) | Q8_0 | 7.17GB | | |
| Original model description: | |
| --- | |
| license: apache-2.0 | |
| --- | |
| # WizardLM-2-7B-abliterated | |
| This is the **WizardLM-2-7B** model with orthogonalized bfloat16 safetensor weights, based on the implementation by `@failspy`. For more info: | |
| - Original paper preview presenting the methodology: <https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction> | |
| - Jupyter notebook containing a implementation of the methodology, by `@failspy`: <https://huggingface.co/failspy/llama-3-70B-Instruct-abliterated/blob/main/ortho_cookbook.ipynb> | |
| ## GGUF Files | |
| I will upload some GGUF files here: <https://huggingface.co/fearlessdots/WizardLM-2-7B-abliterated-GGUF> | |
| ## Prompt Template | |
| This model uses the prompt format from **Vicuna** and supports **multi-turn** conversation. | |
| --- | |
| # Original model card: | |
| <p style="font-size:20px;" align="center"> | |
| 🏠 <a href="https://wizardlm.github.io/WizardLM2" target="_blank">WizardLM-2 Release Blog</a> </p> | |
| <p align="center"> | |
| 🤗 <a href="https://huggingface.co/collections/microsoft/wizardlm-2-661d403f71e6c8257dbd598a" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/victorsungo/WizardLM/tree/main/WizardLM-2" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br> | |
| </p> | |
| <p align="center"> | |
| 👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a> | |
| </p> | |
| ## 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. | |
| <p align="center" width="100%"> | |
| <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/mtbench.png" alt="MTBench" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a> | |
| </p> | |
| **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. | |
| <p align="center" width="100%"> | |
| <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/winall.png" alt="Win" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a> | |
| </p> | |
| ## 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. | |
| <p align="center" width="100%"> | |
| <a ><img src="https://raw.githubusercontent.com/WizardLM/WizardLM2/main/static/images/exp_1.png" alt="Method" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a> | |
| </p> | |
| ## Usage | |
| ❗<b>Note for model system prompts usage:</b> | |
| <b>WizardLM-2</b> adopts the prompt format from <b>Vicuna</b> 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>...... | |
| ``` | |
| <b> Inference WizardLM-2 Demo Script</b> | |
| We provide a WizardLM-2 inference demo [code](https://github.com/nlpxucan/WizardLM/tree/main/demo) on our github. | |