--- license: other model_name: Vicuna 33B V1.3 base_model: lmsys/vicuna-33b-v1.3 inference: false model_creator: Large Model Systems Organization model_type: llama prompt_template: '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: {prompt} ASSISTANT: ' 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)


# Vicuna 33B V1.3 - GGML - Model creator: [Large Model Systems Organization](https://huggingface.co/lmsys) - Original model: [Vicuna 33B V1.3](https://huggingface.co/lmsys/vicuna-33b-v1.3) ## Description This repo contains GGML format model files for [LmSys' Vicuna 33B 1.3](https://huggingface.co/lmsys/vicuna-33b-v1.3). ### Important note regarding GGML files. The GGML format has now been superseded by GGUF. As of August 21st 2023, [llama.cpp](https://github.com/ggerganov/llama.cpp) no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support. Please use the GGUF models instead. ### About GGML GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as: * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most popular web UI. Supports NVidia CUDA GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling. * [LM Studio](https://lmstudio.ai/), a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with CUDA GPU acceleration via the c_transformers backend. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. ## Repositories available * [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/vicuna-33B-AWQ) * [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/vicuna-33B-GPTQ) * [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/vicuna-33B-GGUF) * [Large Model Systems Organization's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/lmsys/vicuna-33b-v1.3) ## Prompt template: Vicuna ``` 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: {prompt} ASSISTANT: ``` ## Compatibility These quantised GGML files are compatible with llama.cpp between June 6th (commit `2d43387`) and August 21st 2023. For support with latest llama.cpp, please use GGUF files instead. The final llama.cpp commit with support for GGML was: [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future. ## Explanation of the new k-quant 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 * GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type. 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 | | ---- | ---- | ---- | ---- | ---- | ----- | | [vicuna-33b.ggmlv3.q2_K.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q2_K.bin) | q2_K | 2 | 13.71 GB| 16.21 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. | | [vicuna-33b.ggmlv3.q3_K_S.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q3_K_S.bin) | q3_K_S | 3 | 14.06 GB| 16.56 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors | | [vicuna-33b.ggmlv3.q3_K_M.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q3_K_M.bin) | q3_K_M | 3 | 15.72 GB| 18.22 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [vicuna-33b.ggmlv3.q3_K_L.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q3_K_L.bin) | q3_K_L | 3 | 17.28 GB| 19.78 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K | | [vicuna-33b.ggmlv3.q4_0.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q4_0.bin) | q4_0 | 4 | 18.30 GB| 20.80 GB | Original quant method, 4-bit. | | [vicuna-33b.ggmlv3.q4_K_S.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q4_K_S.bin) | q4_K_S | 4 | 18.36 GB| 20.86 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors | | [vicuna-33b.ggmlv3.q4_K_M.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q4_K_M.bin) | q4_K_M | 4 | 19.62 GB| 22.12 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K | | [vicuna-33b.ggmlv3.q4_1.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q4_1.bin) | q4_1 | 4 | 20.33 GB| 22.83 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. | | [vicuna-33b.ggmlv3.q5_0.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q5_0.bin) | q5_0 | 5 | 22.37 GB| 24.87 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. | | [vicuna-33b.ggmlv3.q5_K_S.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q5_K_S.bin) | q5_K_S | 5 | 22.40 GB| 24.90 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors | | [vicuna-33b.ggmlv3.q5_K_M.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q5_K_M.bin) | q5_K_M | 5 | 23.05 GB| 25.55 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K | | [vicuna-33b.ggmlv3.q5_1.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q5_1.bin) | q5_1 | 5 | 24.40 GB| 26.90 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. | | [vicuna-33b.ggmlv3.q6_K.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q6_K.bin) | q6_K | 6 | 26.69 GB| 29.19 GB | New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization | | [vicuna-33b.ggmlv3.q8_0.bin](https://huggingface.co/TheBloke/vicuna-33B-GGML/blob/main/vicuna-33b.ggmlv3.q8_0.bin) | q8_0 | 8 | 34.56 GB| 37.06 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. | **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 run in `llama.cpp` Make sure you are using `llama.cpp` from commit [dadbed99e65252d79f81101a392d0d6497b86caa](https://github.com/ggerganov/llama.cpp/commit/dadbed99e65252d79f81101a392d0d6497b86caa) or earlier. For compatibility with latest llama.cpp, please use GGUF files instead. ``` ./main -t 10 -ngl 32 -m vicuna-33b.ggmlv3.Q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "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: {prompt} ASSISTANT:" ``` Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`. Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 2048` to the desired sequence length for this model. For example, `-c 4096` for a Llama 2 model. For models that use RoPE, add `--rope-freq-base 10000 --rope-freq-scale 0.5` for doubled context, or `--rope-freq-base 10000 --rope-freq-scale 0.25` for 4x context. 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` Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md). ## 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**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov Thank you to all my generous patrons and donaters! And thank you again to a16z for their generous grant. # Original model card: LmSys' Vicuna 33B 1.3 # Vicuna Model Card ## Model Details Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. - **Developed by:** [LMSYS](https://lmsys.org/) - **Model type:** An auto-regressive language model based on the transformer architecture. - **License:** Non-commercial license - **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971). ### Model Sources - **Repository:** https://github.com/lm-sys/FastChat - **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/ - **Paper:** https://arxiv.org/abs/2306.05685 - **Demo:** https://chat.lmsys.org/ ## Uses The primary use of Vicuna is research on large language models and chatbots. The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. ## How to Get Started with the Model - Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. - APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. ## Training Details Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. The training data is around 125K conversations collected from ShareGPT.com. See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). ## Evaluation Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard). ## Difference between different versions of Vicuna See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md)