commit c07057e6881d7d148cded48bdcd3bcc739d721c1 Author: ModelHub XC Date: Thu Jun 11 14:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5087c72 --- /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-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-7B-Base-SFT-ShareGPT-Vicuna.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.IQ4_XS.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.IQ4_XS.gguf new file mode 100644 index 0000000..1715a4b --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aa916b90c3ce5237f678dae204cbe379810c00a8cb72794309cbb52ff44f204 +size 3948691936 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q2_K.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q2_K.gguf new file mode 100644 index 0000000..e736683 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88fd3ccfe4ec03295df8064d53ba09c17d4f8427a02a21e9052c9a8017e3401 +size 2722902432 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_L.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_L.gguf new file mode 100644 index 0000000..d57584e --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2ed7446ee5086dc6f07724bc2a463624535c0a0739cb86cd0cfd46b0c966b8 +size 3826006464 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_M.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_M.gguf new file mode 100644 index 0000000..8f0c0a8 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9047a8c40bcad2ed3707b8d5bb47c4b230949028994a942000ff354c3f42b079 +size 3522968000 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_S.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_S.gguf new file mode 100644 index 0000000..07d6488 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88ecfecb67e8d8809a9443ccc40b5698d907293385a00cf85bcc9ea65b76fdba +size 3168549312 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_M.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_M.gguf new file mode 100644 index 0000000..accd767 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:790efdcf767a9bf33225836c206d14bd6ebcd340d09ee58bb1fff4df3ffb0d66 +size 4372841568 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_S.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_S.gguf new file mode 100644 index 0000000..0727aba --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eab1f8c1199a3598757b5449982239041598153e61502cd46d419fdb56e146a3 +size 4144776288 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_M.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_M.gguf new file mode 100644 index 0000000..0721514 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef231214b192dfc632ef8d8a345bd259143a97912b4db3f8720f613838d8d2f +size 5136207456 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_S.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_S.gguf new file mode 100644 index 0000000..f9726bd --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ad1af5a910b22db56e9f7ed769e2736e1f534787ca5141a54016b5884d9dec2 +size 5002514016 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q6_K.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q6_K.gguf new file mode 100644 index 0000000..43c5e57 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8062edbc847b33158bae0fb74baffd28c9cb882dad1fdf9c9fabbbb06ae474 +size 5947283712 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q8_0.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q8_0.gguf new file mode 100644 index 0000000..b3999e8 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58c03370ffcdf317f6947968162259a0573aa2786ee35ddc73bcb219695d2651 +size 7702609856 diff --git a/Mistral-7B-Base-SFT-ShareGPT-Vicuna.f16.gguf b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.f16.gguf new file mode 100644 index 0000000..29a8929 --- /dev/null +++ b/Mistral-7B-Base-SFT-ShareGPT-Vicuna.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc03f05a605cad792383a582da54651a526435f35a4f116f7503dd16c9811749 +size 14497420736 diff --git a/README.md b/README.md new file mode 100644 index 0000000..25ad25a --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: nyu-dice-lab/Mistral-7B-Base-SFT-ShareGPT-Vicuna +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/nyu-dice-lab/Mistral-7B-Base-SFT-ShareGPT-Vicuna + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-7B-Base-SFT-ShareGPT-Vicuna-GGUF/resolve/main/Mistral-7B-Base-SFT-ShareGPT-Vicuna.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. + +