diff --git a/.gitattributes b/.gitattributes index 53d7257..c5a62c2 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1,47 +1,47 @@ *.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text -*.bin.* filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text -*.zstandard filter=lfs diff=lfs merge=lfs -text -*.tfevents* filter=lfs diff=lfs merge=lfs -text -*.db* filter=lfs diff=lfs merge=lfs -text -*.ark* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text -**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.gguf* filter=lfs diff=lfs merge=lfs -text -*.ggml filter=lfs diff=lfs merge=lfs -text -*.llamafile* filter=lfs diff=lfs merge=lfs -text -*.pt2 filter=lfs diff=lfs merge=lfs -text -*.mlmodel filter=lfs diff=lfs merge=lfs -text -*.npy filter=lfs diff=lfs merge=lfs -text -*.npz filter=lfs diff=lfs merge=lfs -text -*.pickle filter=lfs diff=lfs merge=lfs -text -*.pkl filter=lfs diff=lfs merge=lfs -text -*.tar filter=lfs diff=lfs merge=lfs -text -*.wasm filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file +*tfevents* filter=lfs diff=lfs merge=lfs -text +llama-30b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-30b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md index 582d896..b14a503 100644 --- a/README.md +++ b/README.md @@ -1,47 +1,286 @@ --- -license: Apache License 2.0 +base_model: https://ai.meta.com/blog/large-language-model-llama-meta-ai +inference: false +license: other +model_creator: Meta +model_name: LLaMA 33B +model_type: llama +prompt_template: '{prompt} -#model-type: -##如 gpt、phi、llama、chatglm、baichuan 等 -#- gpt - -#domain: -##如 nlp、cv、audio、multi-modal -#- nlp - -#language: -##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa -#- cn - -#metrics: -##如 CIDEr、Blue、ROUGE 等 -#- CIDEr - -#tags: -##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 -#- pretrained - -#tools: -##如 vllm、fastchat、llamacpp、AdaSeq 等 -#- vllm + ' +quantized_by: TheBloke --- -### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 -#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 -SDK下载 -```bash -#安装ModelScope -pip install modelscope + + +
+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)

+
+ + +# LLaMA 33B - GGUF +- Model creator: [Meta](https://huggingface.co/none) +- Original model: [LLaMA 33B](https://ai.meta.com/blog/large-language-model-llama-meta-ai) + + +## Description + +This repo contains GGUF format model files for [Meta's LLaMA 30b](https://ai.meta.com/blog/large-language-model-llama-meta-ai). + + + +### 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. + +Here is an incomplate list of clients and libraries that are known to support GGUF: + +* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. +* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. +* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. +* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. +* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. +* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. +* [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. +* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. + + + +## Repositories available + +* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/LLaMA-30b-AWQ) +* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/LLaMA-30b-GPTQ) +* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/LLaMA-30b-GGUF) +* [Meta's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/huggyllama/llama-30b) + + + +## Prompt template: None + ``` +{prompt} + +``` + + + + + +## Compatibility + +These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) + +They are also compatible with many third party UIs and libraries - please see the list at the top of this README. + +## 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 | +| ---- | ---- | ---- | ---- | ---- | ----- | +| [llama-30b.Q2_K.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q2_K.gguf) | Q2_K | 2 | 13.50 GB| 16.00 GB | smallest, significant quality loss - not recommended for most purposes | +| [llama-30b.Q3_K_S.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q3_K_S.gguf) | Q3_K_S | 3 | 14.06 GB| 16.56 GB | very small, high quality loss | +| [llama-30b.Q3_K_M.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q3_K_M.gguf) | Q3_K_M | 3 | 15.76 GB| 18.26 GB | very small, high quality loss | +| [llama-30b.Q3_K_L.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q3_K_L.gguf) | Q3_K_L | 3 | 17.28 GB| 19.78 GB | small, substantial quality loss | +| [llama-30b.Q4_0.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q4_0.gguf) | Q4_0 | 4 | 18.36 GB| 20.86 GB | legacy; small, very high quality loss - prefer using Q3_K_M | +| [llama-30b.Q4_K_S.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q4_K_S.gguf) | Q4_K_S | 4 | 18.44 GB| 20.94 GB | small, greater quality loss | +| [llama-30b.Q4_K_M.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q4_K_M.gguf) | Q4_K_M | 4 | 19.62 GB| 22.12 GB | medium, balanced quality - recommended | +| [llama-30b.Q5_0.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q5_0.gguf) | Q5_0 | 5 | 22.40 GB| 24.90 GB | legacy; medium, balanced quality - prefer using Q4_K_M | +| [llama-30b.Q5_K_S.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q5_K_S.gguf) | Q5_K_S | 5 | 22.40 GB| 24.90 GB | large, low quality loss - recommended | +| [llama-30b.Q5_K_M.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q5_K_M.gguf) | Q5_K_M | 5 | 23.05 GB| 25.55 GB | large, very low quality loss - recommended | +| [llama-30b.Q6_K.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q6_K.gguf) | Q6_K | 6 | 26.69 GB| 29.19 GB | very large, extremely low quality loss | +| [llama-30b.Q8_0.gguf](https://huggingface.co/TheBloke/LLaMA-30b-GGUF/blob/main/llama-30b.Q8_0.gguf) | Q8_0 | 8 | 34.57 GB| 37.07 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/LLaMA-30b-GGUF and below it, a specific filename to download, such as: llama-30b.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/LLaMA-30b-GGUF llama-30b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False +``` + +
+ More advanced huggingface-cli download usage + +You can also download multiple files at once with a pattern: + +```shell +huggingface-cli download TheBloke/LLaMA-30b-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/LLaMA-30b-GGUF llama-30b.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 32 -m llama-30b.Q4_K_M.gguf --color -c 2048 --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 2048` 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. + +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). + +## 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) or [ctransformers](https://github.com/marella/ctransformers) libraries. + +### How to load this model in Python code, using ctransformers + +#### First install the package + +Run one of the following commands, according to your system: + +```shell +# Base ctransformers with no GPU acceleration +pip install ctransformers +# Or with CUDA GPU acceleration +pip install ctransformers[cuda] +# Or with AMD ROCm GPU acceleration (Linux only) +CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers +# Or with Metal GPU acceleration for macOS systems only +CT_METAL=1 pip install ctransformers --no-binary ctransformers +``` + +#### Simple ctransformers example code + ```python -#SDK模型下载 -from modelscope import snapshot_download -model_dir = snapshot_download('TheBloke/LLaMA-30b-GGUF') -``` -Git下载 -``` -#Git模型下载 -git clone https://www.modelscope.cn/TheBloke/LLaMA-30b-GGUF.git +from ctransformers import AutoModelForCausalLM + +# 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 = AutoModelForCausalLM.from_pretrained("TheBloke/LLaMA-30b-GGUF", model_file="llama-30b.Q4_K_M.gguf", model_type="llama", gpu_layers=50) + +print(llm("AI is going to")) ``` -

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file +## 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) +* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) + + + + + +## 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: Meta's LLaMA 30b + + +This contains the weights for the LLaMA-30b model. This model is under a non-commercial license (see the LICENSE file). +You should only use this repository if you have been granted access to the model by filling out [this form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform?usp=send_form) but either lost your copy of the weights or got some trouble converting them to the Transformers format. + + + diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/llama-30b.Q2_K.gguf b/llama-30b.Q2_K.gguf new file mode 100644 index 0000000..a8749ed --- /dev/null +++ b/llama-30b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d12653f16fd8c7d4ae7430991a0a41eb9f808b60d912e0f6f4db5f675b4f153 +size 13502545312 diff --git a/llama-30b.Q3_K_L.gguf b/llama-30b.Q3_K_L.gguf new file mode 100644 index 0000000..d5477ea --- /dev/null +++ b/llama-30b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d651b9d0f1a8e56abe39f7c9b6827c62fa3272357758f3712bc7d2bb8b939d3f +size 17279758752 diff --git a/llama-30b.Q3_K_M.gguf b/llama-30b.Q3_K_M.gguf new file mode 100644 index 0000000..eb71acc --- /dev/null +++ b/llama-30b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519bb7675ae7165146836cbf797e1e95d5017e30858a8c7f6676dedb4857ec9d +size 15761551776 diff --git a/llama-30b.Q3_K_S.gguf b/llama-30b.Q3_K_S.gguf new file mode 100644 index 0000000..c8a4fae --- /dev/null +++ b/llama-30b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0014dc2831c47b340d84b16bd0bd6e6330fd354d074b3a35a9dedcd021ab37e +size 14064112032 diff --git a/llama-30b.Q4_0.gguf b/llama-30b.Q4_0.gguf new file mode 100644 index 0000000..3502fcd --- /dev/null +++ b/llama-30b.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beeb177972a24d31ce240eb26ae1f014e2bc1c37d695441173727b6056654b4b +size 18355967392 diff --git a/llama-30b.Q4_K_M.gguf b/llama-30b.Q4_K_M.gguf new file mode 100644 index 0000000..5d28482 --- /dev/null +++ b/llama-30b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f91e4d96ba527fcba5bfd25149969e5d9da0e751e8102d4e5e79e26d1e39d31 +size 19621139872 diff --git a/llama-30b.Q4_K_S.gguf b/llama-30b.Q4_K_S.gguf new file mode 100644 index 0000000..642460c --- /dev/null +++ b/llama-30b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a234580e71077fcde84aac166b86211828802d2017a93aac6ec27fc9c0a6dbf1 +size 18437756320 diff --git a/llama-30b.Q5_0.gguf b/llama-30b.Q5_0.gguf new file mode 100644 index 0000000..bf01b25 --- /dev/null +++ b/llama-30b.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80bbac2747a6cf4d0ab2c2129405e27ab1143299ade89cd5593a4a792145ba5 +size 22395360672 diff --git a/llama-30b.Q5_K_M.gguf b/llama-30b.Q5_K_M.gguf new file mode 100644 index 0000000..6413039 --- /dev/null +++ b/llama-30b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:068f4e97c62d02b8a5c71675b9f33e8fca9d1baa6d9c45ecb354df14d0d679b0 +size 23047116192 diff --git a/llama-30b.Q5_K_S.gguf b/llama-30b.Q5_K_S.gguf new file mode 100644 index 0000000..595869b --- /dev/null +++ b/llama-30b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961cb2f5ddc7bb49741ea8ad740e0ad6a193739cf3e59a4c176b3f0951cb66bc +size 22395360672 diff --git a/llama-30b.Q6_K.gguf b/llama-30b.Q6_K.gguf new file mode 100644 index 0000000..c2580ff --- /dev/null +++ b/llama-30b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fcad3fb06326629ac5372ca37268f7b1cb24ced7ada0b58555ddd40134ee871 +size 26687216032 diff --git a/llama-30b.Q8_0.gguf b/llama-30b.Q8_0.gguf new file mode 100644 index 0000000..e996be3 --- /dev/null +++ b/llama-30b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d066fea7c1b4cf87fb55a0492930538e2b64dcada355d4a008d2ea780b163ca0 +size 34565124512