--- base_model: mistralai/Mixtral-8x7B-Instruct-v0.1 inference: false language: - fr - it - de - es - en license: apache-2.0 model_creator: Mistral AI_ model_name: Mixtral 8X7B Instruct v0.1 model_type: mixtral prompt_template: '[INST] {prompt} [/INST] ' quantized_by: TheBloke ---
TheBlokeAI

Chat & support: TheBloke's Discord server

Want to contribute? TheBloke's Patreon page

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)


# Mixtral 8X7B Instruct v0.1 - GGUF - Model creator: [Mistral AI_](https://huggingface.co/mistralai) - Original model: [Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) ## Description This repo contains **EXPERIMENTAL** GGUF format model files for [Mistral AI_'s Mixtral 8X7B Instruct v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1). ## EXPERIMENTAL - REQUIRES LLAMA.CPP PR These are experimental GGUF files, created using a llama.cpp PR found here: https://github.com/ggerganov/llama.cpp/pull/4406. THEY WILL NOT WORK WITH LLAMA.CPP FROM `main`, OR ANY DOWNSTREAM LLAMA.CPP CLIENT - such as LM Studio, llama-cpp-python, text-generation-webui, etc. To test these GGUFs, please build llama.cpp from the above PR. I have tested CUDA acceleration and it works great. I have not yet tested other forms of GPU acceleration. ## Repositories available * AWQ: coming soon * GPTQ: coming soon * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF) * [Mistral AI_'s original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) ## Prompt template: Mistral ``` [INST] {prompt} [/INST] ``` ## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [mixtral-8x7b-instruct-v0.1.Q2_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes | | [mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss | | [mixtral-8x7b-instruct-v0.1.Q4_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended | | [mixtral-8x7b-instruct-v0.1.Q5_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended | | [mixtral-8x7b-instruct-v0.1.Q6_K.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss | | [mixtral-8x7b-instruct-v0.1.Q8_0.gguf](https://huggingface.co/TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF/blob/main/mixtral-8x7b-instruct-v0.1.Q8_0.gguf) | Q8_0 | 8 | 49.62 GB| 52.12 GB | very large, extremely low quality loss - not recommended | **Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ```
More advanced huggingface-cli download usage (click to read) You can also download multiple files at once with a pattern: ```shell huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install hf_transfer ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command.
## Example `llama.cpp` command Make sure you are using `llama.cpp` from [PR 4406](https://github.com/ggerganov/llama.cpp/pull/4406) ```shell ./main -ngl 35 -m mixtral-8x7b-instruct-v0.1.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "{prompt}" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 32768` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p ` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Not currently supported. ## How to run from Python code Not currently supported. ## Discord For further support, and discussions on these models and AI in general, join us at: [TheBloke AI's Discord server](https://discord.gg/theblokeai) ## Thanks, and how to contribute Thanks to the [chirper.ai](https://chirper.ai) team! Thanks to Clay from [gpus.llm-utils.org](llm-utils)! I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects. Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. * Patreon: https://patreon.com/TheBlokeAI * Ko-Fi: https://ko-fi.com/TheBlokeAI **Special thanks to**: Aemon Algiz. **Patreon special mentions**: Michael Levine, 阿明, Trailburnt, Nikolai Manek, John Detwiler, Randy H, Will Dee, Sebastain Graf, NimbleBox.ai, Eugene Pentland, Emad Mostaque, Ai Maven, Jim Angel, Jeff Scroggin, Michael Davis, Manuel Alberto Morcote, Stephen Murray, Robert, Justin Joy, Luke @flexchar, Brandon Frisco, Elijah Stavena, S_X, Dan Guido, Undi ., Komninos Chatzipapas, Shadi, theTransient, Lone Striker, Raven Klaugh, jjj, Cap'n Zoog, Michel-Marie MAUDET (LINAGORA), Matthew Berman, David, Fen Risland, Omer Bin Jawed, Luke Pendergrass, Kalila, OG, Erik Bjäreholt, Rooh Singh, Joseph William Delisle, Dan Lewis, TL, John Villwock, AzureBlack, Brad, Pedro Madruga, Caitlyn Gatomon, K, jinyuan sun, Mano Prime, Alex, Jeffrey Morgan, Alicia Loh, Illia Dulskyi, Chadd, transmissions 11, fincy, Rainer Wilmers, ReadyPlayerEmma, knownsqashed, Mandus, biorpg, Deo Leter, Brandon Phillips, SuperWojo, Sean Connelly, Iucharbius, Jack West, Harry Royden McLaughlin, Nicholas, terasurfer, Vitor Caleffi, Duane Dunston, Johann-Peter Hartmann, David Ziegler, Olakabola, Ken Nordquist, Trenton Dambrowitz, Tom X Nguyen, Vadim, Ajan Kanaga, Leonard Tan, Clay Pascal, Alexandros Triantafyllidis, JM33133, Xule, vamX, ya boyyy, subjectnull, Talal Aujan, Alps Aficionado, wassieverse, Ari Malik, James Bentley, Woland, Spencer Kim, Michael Dempsey, Fred von Graf, Elle, zynix, William Richards, Stanislav Ovsiannikov, Edmond Seymore, Jonathan Leane, Martin Kemka, usrbinkat, Enrico Ros Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. # Original model card: Mistral AI_'s Mixtral 8X7B Instruct v0.1 # Model Card for Mixtral-8x7B The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks we tested. For full details of this model please read our [release blog post](https://mistral.ai/news/mixtral-of-experts/). ## Warning This repo contains weights that are compatible with [vLLM](https://github.com/vllm-project/vllm) serving of the model as well as Hugging Face [transformers](https://github.com/huggingface/transformers) library. It is based on the original Mixtral [torrent release](magnet:?xt=urn:btih:5546272da9065eddeb6fcd7ffddeef5b75be79a7&dn=mixtral-8x7b-32kseqlen&tr=udp%3A%2F%http://2Fopentracker.i2p.rocks%3A6969%2Fannounce&tr=http%3A%2F%http://2Ftracker.openbittorrent.com%3A80%2Fannounce), but the file format and parameter names are different. Please note that model cannot (yet) be instantiated with HF. ## Instruction format This format must be strictly respected, otherwise the model will generate sub-optimal outputs. The template used to build a prompt for the Instruct model is defined as follows: ``` [INST] Instruction [/INST] Model answer [INST] Follow-up instruction [/INST] ``` Note that `` and `` are special tokens for beginning of string (BOS) and end of string (EOS) while [INST] and [/INST] are regular strings. As reference, here is the pseudo-code used to tokenize instructions during fine-tuning: ```python def tokenize(text): return tok.encode(text, add_special_tokens=False) [BOS_ID] + tokenize("[INST]") + tokenize(USER_MESSAGE_1) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_1) + [EOS_ID] + … tokenize("[INST]") + tokenize(USER_MESSAGE_N) + tokenize("[/INST]") + tokenize(BOT_MESSAGE_N) + [EOS_ID] ``` In the pseudo-code above, note that the `tokenize` method should not add a BOS or EOS token automatically, but should add a prefix space. ## Run the model ```python from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained(model_id) text = "Hello my name is" inputs = tokenizer(text, return_tensors="pt") outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ``` By default, transformers will load the model in full precision. Therefore you might be interested to further reduce down the memory requirements to run the model through the optimizations we offer in HF ecosystem: ### In half-precision Note `float16` precision only works on GPU devices
Click to expand ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16).to(0) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ```
### Lower precision using (8-bit & 4-bit) using `bitsandbytes`
Click to expand ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ```
### Load the model with Flash Attention 2
Click to expand ```diff + import torch from transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mistralai/Mixtral-8x7B-Instruct-v0.1" tokenizer = AutoTokenizer.from_pretrained(model_id) + model = AutoModelForCausalLM.from_pretrained(model_id, use_flash_attention_2=True) text = "Hello my name is" + inputs = tokenizer(text, return_tensors="pt").to(0) outputs = model.generate(**inputs, max_new_tokens=20) print(tokenizer.decode(outputs[0], skip_special_tokens=True)) ```
## Limitations The Mixtral-8x7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs. # The Mistral AI Team Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.