--- base_model: perlthoughts/Falkor-8x7B-MoE inference: false license: apache-2.0 model_creator: Ray Hernandez model_name: Falkor 8X7B MoE model_type: mixtral prompt_template: ': {prompt} : ' 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)


# Falkor 8X7B MoE - GGUF - Model creator: [Ray Hernandez](https://huggingface.co/perlthoughts) - Original model: [Falkor 8X7B MoE](https://huggingface.co/perlthoughts/Falkor-8x7B-MoE) ## Description This repo contains GGUF format model files for [Ray Hernandez's Falkor 8X7B MoE](https://huggingface.co/perlthoughts/Falkor-8x7B-MoE). ### 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. ### Mixtral GGUF Support for Mixtral was merged into Llama.cpp on December 13th. These Mixtral GGUFs are known to work in: * llama.cpp as of December 13th * KoboldCpp 1.52 as later * LM Studio 0.2.9 and later * llama-cpp-python 0.2.23 and later Other clients/libraries, not listed above, may not yet work. ## Repositories available * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF) * [Ray Hernandez's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/perlthoughts/Falkor-8x7B-MoE) ## Prompt template: human-bot ``` : {prompt} : ``` ## Compatibility These Mixtral GGUFs are compatible with llama.cpp from December 13th onwards. Other clients/libraries may not work yet. ## Explanation of quantisation methods
Click to see details The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw Refer to the Provided Files table below to see what files use which methods, and how.
## Provided files | Name | Quant method | Bits | Size | Max RAM required | Use case | | ---- | ---- | ---- | ---- | ---- | ----- | | [falkor-8x7b-moe.Q2_K.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q2_K.gguf) | Q2_K | 2 | 15.64 GB| 18.14 GB | smallest, significant quality loss - not recommended for most purposes | | [falkor-8x7b-moe.Q3_K_M.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q3_K_M.gguf) | Q3_K_M | 3 | 20.36 GB| 22.86 GB | very small, high quality loss | | [falkor-8x7b-moe.Q4_0.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q4_0.gguf) | Q4_0 | 4 | 26.44 GB| 28.94 GB | legacy; small, very high quality loss - prefer using Q3_K_M | | [falkor-8x7b-moe.Q4_K_M.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q4_K_M.gguf) | Q4_K_M | 4 | 26.44 GB| 28.94 GB | medium, balanced quality - recommended | | [falkor-8x7b-moe.Q5_0.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q5_0.gguf) | Q5_0 | 5 | 32.23 GB| 34.73 GB | legacy; medium, balanced quality - prefer using Q4_K_M | | [falkor-8x7b-moe.Q5_K_M.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q5_K_M.gguf) | Q5_K_M | 5 | 32.23 GB| 34.73 GB | large, very low quality loss - recommended | | [falkor-8x7b-moe.Q6_K.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q6_K.gguf) | Q6_K | 6 | 38.38 GB| 40.88 GB | very large, extremely low quality loss | | [falkor-8x7b-moe.Q8_0.gguf](https://huggingface.co/TheBloke/Falkor-8x7B-MoE-GGUF/blob/main/falkor-8x7b-moe.Q8_0.gguf) | Q8_0 | 8 | 49.63 GB| 52.13 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. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: TheBloke/Falkor-8x7B-MoE-GGUF and below it, a specific filename to download, such as: falkor-8x7b-moe.Q4_K_M.gguf. Then click Download. ### 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/Falkor-8x7B-MoE-GGUF falkor-8x7b-moe.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/Falkor-8x7B-MoE-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/Falkor-8x7B-MoE-GGUF falkor-8x7b-moe.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 commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m falkor-8x7b-moe.Q4_K_M.gguf --color -c 32768 --temp 0.7 --repeat_penalty 1.1 -n -1 -p ": {prompt}\n:" ``` 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` Note that text-generation-webui may not yet be compatible with Mixtral GGUFs. Please check compatibility first. Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) version 0.2.23 and later. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./falkor-8x7b-moe.Q4_K_M.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( ": {prompt}\n:", # Prompt max_tokens=512, # Generate up to 512 tokens stop=[""], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./falkor-8x7b-moe.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) ## 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: Ray Hernandez's Falkor 8X7B MoE # Falkor 7B MoE 8x7B Experts Model merge between Chupacabra, openchat, and dragon-mistral-7b-v0. - ---> [Theme Song](https://www.youtube.com/watch?v=lHytjEj7B9g) <--- # Original Model Card for dragon-mistral-7b-v0 dragon-mistral-7b-v0 part of the dRAGon ("Delivering RAG On ...") model series, RAG-instruct trained on top of a Mistral-7B base model. DRAGON models have been fine-tuned with the specific objective of fact-based question-answering over complex business and legal documents with an emphasis on reducing hallucinations and providing short, clear answers for workflow automation. ### Benchmark Tests Evaluated against the benchmark test: [RAG-Instruct-Benchmark-Tester](https://www.huggingface.co/datasets/llmware/rag_instruct_benchmark_tester) Average of 2 Test Runs with 1 point for correct answer, 0.5 point for partial correct or blank / NF, 0.0 points for incorrect, and -1 points for hallucinations. --**Accuracy Score**: **96.50** correct out of 100 --Not Found Classification: 92.50% --Boolean: 97.50% --Math/Logic: 81.25% --Complex Questions (1-5): 4 (Medium-High - table-reading, multiple-choice, causal) --Summarization Quality (1-5): 4 (Coherent, extractive) --Hallucinations: No hallucinations observed in test runs. For test run results (and good indicator of target use cases), please see the files ("core_rag_test" and "answer_sheet" in this repo). ### Model Description - **Developed by:** llmware - **Model type:** Mistral-7B - **Language(s) (NLP):** English - **License:** Apache 2.0 - **Finetuned from model:** Mistral-7B-Base ### Direct Use DRAGON is designed for enterprise automation use cases, especially in knowledge-intensive industries, such as financial services, legal and regulatory industries with complex information sources. DRAGON models have been trained for common RAG scenarios, specifically: question-answering, key-value extraction, and basic summarization as the core instruction types without the need for a lot of complex instruction verbiage - provide a text passage context, ask questions, and get clear fact-based responses. ## Bias, Risks, and Limitations Any model can provide inaccurate or incomplete information, and should be used in conjunction with appropriate safeguards and fact-checking mechanisms. ## How to Get Started with the Model The fastest way to get started with dRAGon is through direct import in transformers: from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dragon-mistral-7b-v0") model = AutoModelForCausalLM.from_pretrained("dragon-mistral-7b-v0") Please refer to the generation_test .py files in the Files repository, which includes 200 samples and script to test the model. The **generation_test_llmware_script.py** includes built-in llmware capabilities for fact-checking, as well as easy integration with document parsing and actual retrieval to swap out the test set for RAG workflow consisting of business documents. The dRAGon model was fine-tuned with a simple "\ and \ wrapper", so to get the best results, wrap inference entries as: full_prompt = ": " + my_prompt + "\n" + ":" The BLING model was fine-tuned with closed-context samples, which assume generally that the prompt consists of two sub-parts: 1. Text Passage Context, and 2. Specific question or instruction based on the text passage To get the best results, package "my_prompt" as follows: my_prompt = {{text_passage}} + "\n" + {{question/instruction}} If you are using a HuggingFace generation script: # prepare prompt packaging used in fine-tuning process new_prompt = ": " + entries["context"] + "\n" + entries["query"] + "\n" + ":" inputs = tokenizer(new_prompt, return_tensors="pt") start_of_output = len(inputs.input_ids[0]) # temperature: set at 0.3 for consistency of output # max_new_tokens: set at 100 - may prematurely stop a few of the summaries outputs = model.generate( inputs.input_ids.to(device), eos_token_id=tokenizer.eos_token_id, pad_token_id=tokenizer.eos_token_id, do_sample=True, temperature=0.3, max_new_tokens=100, ) output_only = tokenizer.decode(outputs[0][start_of_output:],skip_special_tokens=True) ## Model Card Contact Darren Oberst & llmware team