commit 93f5b586108f53a3dd2c99d9dfa7f9e5034a7dc2 Author: ModelHub XC Date: Tue Jul 21 14:51:38 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-LLaMA-Fusion-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21e5dfc --- /dev/null +++ b/.gitattributes @@ -0,0 +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 +*.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 +Mistral-LLaMA-Fusion.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.f16.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-LLaMA-Fusion.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-LLaMA-Fusion.IQ4_XS.gguf b/Mistral-LLaMA-Fusion.IQ4_XS.gguf new file mode 100644 index 0000000..31ace4f --- /dev/null +++ b/Mistral-LLaMA-Fusion.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89a48f0ba8827bea0aced7f42d428a9895bca6638320c8c9b68bb24c0b3cd8d +size 3944389792 diff --git a/Mistral-LLaMA-Fusion.Q2_K.gguf b/Mistral-LLaMA-Fusion.Q2_K.gguf new file mode 100644 index 0000000..cff9365 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea496bd0cbb6db408741c0d855d2b2d2b51b61bd471c3a1eb3b6ef99c180e4b +size 2719243424 diff --git a/Mistral-LLaMA-Fusion.Q3_K_L.gguf b/Mistral-LLaMA-Fusion.Q3_K_L.gguf new file mode 100644 index 0000000..223c3e4 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf930f6c7d915654a56319a49ac107624740c77b4bd3c5058cec3e87779198a +size 3822025888 diff --git a/Mistral-LLaMA-Fusion.Q3_K_M.gguf b/Mistral-LLaMA-Fusion.Q3_K_M.gguf new file mode 100644 index 0000000..7640e43 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180e1ed008be3b132bb00a39eab675c2a29bbf5e23539fb0d7b1ada4e8d1aaf2 +size 3518987424 diff --git a/Mistral-LLaMA-Fusion.Q3_K_S.gguf b/Mistral-LLaMA-Fusion.Q3_K_S.gguf new file mode 100644 index 0000000..8014f96 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bf3be8e4ce9b81caef984a57b9d8ab5a8393f0e51dc134f0b6e07bceee7a217 +size 3164568736 diff --git a/Mistral-LLaMA-Fusion.Q4_K_M.gguf b/Mistral-LLaMA-Fusion.Q4_K_M.gguf new file mode 100644 index 0000000..5944dd1 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8505378a08bb0e022bbf9a455315ff8015694d5f5f0abd28c207fbfe986692a5 +size 4368440480 diff --git a/Mistral-LLaMA-Fusion.Q4_K_S.gguf b/Mistral-LLaMA-Fusion.Q4_K_S.gguf new file mode 100644 index 0000000..d57cb01 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c1d689229916850ee18161d38d41edc28dccfdec08bddebaf670cb4ce37036 +size 4140375200 diff --git a/Mistral-LLaMA-Fusion.Q5_K_M.gguf b/Mistral-LLaMA-Fusion.Q5_K_M.gguf new file mode 100644 index 0000000..426b5c7 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75192ce95e015c416835adfc31c1d52f4ab7bf7bfb7fe3009ac5bfdc81a851f0 +size 5131410592 diff --git a/Mistral-LLaMA-Fusion.Q5_K_S.gguf b/Mistral-LLaMA-Fusion.Q5_K_S.gguf new file mode 100644 index 0000000..92cf626 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cec0cc1513cb3ea92f67e08f7f0d959c3921f10ab34bb338ae74f07ffcabe1 +size 4997717152 diff --git a/Mistral-LLaMA-Fusion.Q6_K.gguf b/Mistral-LLaMA-Fusion.Q6_K.gguf new file mode 100644 index 0000000..d4176aa --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fcf81b756a68570d9b82af283f86fb480a981d66f5eba09342ac8ae75e20c8a +size 5942066336 diff --git a/Mistral-LLaMA-Fusion.Q8_0.gguf b/Mistral-LLaMA-Fusion.Q8_0.gguf new file mode 100644 index 0000000..43f44a0 --- /dev/null +++ b/Mistral-LLaMA-Fusion.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac3bdb631d5fcdec8faa78f29c789248da03c03a37a27f31817dd587ff3a5157 +size 7695858848 diff --git a/Mistral-LLaMA-Fusion.f16.gguf b/Mistral-LLaMA-Fusion.f16.gguf new file mode 100644 index 0000000..a6a1ae6 --- /dev/null +++ b/Mistral-LLaMA-Fusion.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db66851a6f533e83226ae1cc328e399b204e1b5f0a55ea0dfe90e4f9efe2a00 +size 14484733088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..255bc93 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: MatteoKhan/Mistral-LLaMA-Fusion +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +no_imatrix: 'ggml-quants.c:4453: GGML_ASSERT(besti1 >= 0 && besti2 >= 0 && best_k + >= 0) failed' +quantized_by: mradermacher +tags: +- mergekit +- merged-model +- mistral +- llama2 +- language-model +--- +## About + + + + + + +static quants of https://huggingface.co/MatteoKhan/Mistral-LLaMA-Fusion + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-LLaMA-Fusion-GGUF).*** + +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-LLaMA-Fusion-GGUF/resolve/main/Mistral-LLaMA-Fusion.f16.gguf) | f16 | 14.6 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +