commit 17742d63028e1ca158cfc5ea2198f16c586d4a65 Author: ModelHub XC Date: Wed Sep 9 00:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: DaveGergern/LLaMA2-13B-Psyfighter2-Erebus3-DareTies-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..916f8b5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow 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 +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +psyfighter-erebus-dareties.fp16.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama2-13b-psyfighter2-erebus3-dareties.fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9bfb785 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +pipeline_tag: text-generation +tags: +- not-for-all-audiences +- GGUF +- KoboldAI/LLaMA2-13B-Psyfighter2 +- KoboldAI/LLaMA2-13B-Erebus-v3 +model_type: llama2 +model_name: 13B-Psyfighter2-Erebus3-DareTies +quantized_by: DaveGergern +base_model: DaveGergern/13B-Psyfighter2-Erebus3-DareTies +license: llama2 +--- + +## Description + +This repo contains GGUF format model files for [13B-Psyfighter2-Erebus3-DareTies](https://huggingface.co/DaveGergern/13B-Psyfighter2-Erebus3-DareTies). + + + +### 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 incomplete 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. +* [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. +* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. +* [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. +* [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. +* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. + + + +## Prompt template: Alpaca-Tiefighter + +``` +### Instruction: +{prompt} +### Response: + +``` + + + +## 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 + +| File | Quantize | Size | +|------|----------|------| +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-fp16.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-fp16.gguf) | fp16 | 26GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q2_K.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q2_K.gguf) | Q2_K | 1.8GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_L.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_L.gguf) | Q3_K_L | 6.9GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_M.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_M.gguf) | Q3_K_M | 6.3GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_S.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q3_K_S.gguf) | Q3_K_S | 5.6GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q4_K_M.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q4_K_M.gguf) | Q4_K_M | 7.8GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q4_K_S.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q4_K_S.gguf) | Q4_K_S | 7.4GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q5_K_M.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q5_K_M.gguf) | Q5_K_M | 9.2GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q5_K_S.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q5_K_S.gguf) | Q5_K_S | 8.9GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q6_K.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q6_K.gguf) | Q6_K | 10GiB | +| [LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q8_0.gguf](LLaMA2-13B-Psyfighter2-Erebus3-DareTies-Q8_0.gguf) | Q8_0 | 13GiB | \ No newline at end of file diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q2_K.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q2_K.gguf new file mode 100644 index 0000000..ab1f85f --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5060354a89e8ebff66ecd88e6ca433cf10ccb7f5dd2bca4c71f22ccd8e43e27 +size 4854270048 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_L.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_L.gguf new file mode 100644 index 0000000..5dc710b --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9047974d9491e7955d5a08ea7b29ffb43185cec7fdcf7521df89b5b1b03350 +size 6929559648 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_M.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_M.gguf new file mode 100644 index 0000000..8aea0a9 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f256e2a36cf4d482ead7f371330e07f884aa7d52fcc9a5a5878f669f4f0b3174 +size 6337769568 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_S.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_S.gguf new file mode 100644 index 0000000..246dc27 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8341e3ab212a1569c1ea0854bd1a38c9e99d09658db3f7ff5eb886ad8802425 +size 5658980448 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_M.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_M.gguf new file mode 100644 index 0000000..f09f36e --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594fef4c6c0790cc0dc4a15cea83a3d41f46ca4ae1c006f3930913fec060dedf +size 7865956448 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_S.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_S.gguf new file mode 100644 index 0000000..a9eb168 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46c2b42525d333b21ac0a1089157dec80e7782ae4e6b1f958f71a7c5a5e707e +size 7423178848 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_M.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_M.gguf new file mode 100644 index 0000000..8283b2e --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e66935f3b4492e34cf7965e3f8d248dbef71a0aa58ffd08e263f0d5a07d5ffd +size 9229924448 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_S.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_S.gguf new file mode 100644 index 0000000..d21c601 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472be59f373a7829a3c60b7327628daa41300ed02c33cc379044d7686446fbc7 +size 8972286048 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q6_K.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q6_K.gguf new file mode 100644 index 0000000..267d327 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d5c6909814b7f2bf12de2aaf07328a0a426963b35054427ec730bbbca700f1 +size 10679140448 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.Q8_0.gguf b/llama2-13b-psyfighter2-erebus3-dareties.Q8_0.gguf new file mode 100644 index 0000000..ef57b7a --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:192039a8d5d9a15c3bf835c2a8c848a311f72ebcb612959c61bee9e45335cec0 +size 13831319648 diff --git a/llama2-13b-psyfighter2-erebus3-dareties.fp16.gguf b/llama2-13b-psyfighter2-erebus3-dareties.fp16.gguf new file mode 100644 index 0000000..3862ec4 --- /dev/null +++ b/llama2-13b-psyfighter2-erebus3-dareties.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef9f41bd9fd78eac66e877ff8ba3cf148b9e8cbf50393e18e9ec42a9ae04db9d +size 26033303616