commit 29771add317c1cfdebbd76dd611ddef525132100 Author: ModelHub XC Date: Fri Oct 23 19:34:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/shisa-7b-v1-sharegpt-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..434f5db --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +shisa-7b-v1-sharegpt.f16.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +shisa-7b-v1-sharegpt.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4d930f4 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: yentinglin/shisa-7b-v1-sharegpt +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- axolotl +- generated_from_trainer +--- +## About + + + + + + +static quants of https://huggingface.co/yentinglin/shisa-7b-v1-sharegpt + + +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/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q2_K.gguf) | Q2_K | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_S.gguf) | Q3_K_S | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.IQ4_XS.gguf) | IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.7 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_K_S.gguf) | Q4_K_S | 4.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q5_K_S.gguf) | Q5_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q6_K.gguf) | Q6_K | 6.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-7b-v1-sharegpt-GGUF/resolve/main/shisa-7b-v1-sharegpt.f16.gguf) | f16 | 16.0 | 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. + + diff --git a/shisa-7b-v1-sharegpt.IQ4_XS.gguf b/shisa-7b-v1-sharegpt.IQ4_XS.gguf new file mode 100644 index 0000000..21b1c59 --- /dev/null +++ b/shisa-7b-v1-sharegpt.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab09954713d082d4b4c47f1bab6ce7a249ab0312a220d29f004e2e00a591904 +size 4434277536 diff --git a/shisa-7b-v1-sharegpt.Q2_K.gguf b/shisa-7b-v1-sharegpt.Q2_K.gguf new file mode 100644 index 0000000..8551fd5 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e270d5cde027566cdfe6b076e1c0b938198c8d0f9bdf69dac7d41d44c71c0ab6 +size 3135853600 diff --git a/shisa-7b-v1-sharegpt.Q3_K_L.gguf b/shisa-7b-v1-sharegpt.Q3_K_L.gguf new file mode 100644 index 0000000..60354cf --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c051394ee725428379b0da77b313b6aff0360faa4e08c1599d42da5f314589b8 +size 4275274848 diff --git a/shisa-7b-v1-sharegpt.Q3_K_M.gguf b/shisa-7b-v1-sharegpt.Q3_K_M.gguf new file mode 100644 index 0000000..72df410 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c71809919b654a6b1c8ac2566db30c192a9bfd898fbe4b27cbce475b3eabe24 +size 3972236384 diff --git a/shisa-7b-v1-sharegpt.Q3_K_S.gguf b/shisa-7b-v1-sharegpt.Q3_K_S.gguf new file mode 100644 index 0000000..bd10541 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46abd38bb9ca84c044a46a46e3c8f8b08b7171fcc24c32cf47e185f50a853d8 +size 3617817696 diff --git a/shisa-7b-v1-sharegpt.Q4_0_4_4.gguf b/shisa-7b-v1-sharegpt.Q4_0_4_4.gguf new file mode 100644 index 0000000..7b8bfc4 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65baaa6518f9beb90762339a707ac87cd4c12a639a0a1a1b4a34937408337b84 +size 4610079136 diff --git a/shisa-7b-v1-sharegpt.Q4_K_M.gguf b/shisa-7b-v1-sharegpt.Q4_K_M.gguf new file mode 100644 index 0000000..87c078e --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30eae5fe5647b465a60faf9a12df5509f5df1e584104a5b5be9aecb307c32392 +size 4869601696 diff --git a/shisa-7b-v1-sharegpt.Q4_K_S.gguf b/shisa-7b-v1-sharegpt.Q4_K_S.gguf new file mode 100644 index 0000000..aedebf1 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10bb2c4181600545d592fdf6448ddfb26dc0133f71b80cf7ab64f1ef6cc3ee3d +size 4641536416 diff --git a/shisa-7b-v1-sharegpt.Q5_K_M.gguf b/shisa-7b-v1-sharegpt.Q5_K_M.gguf new file mode 100644 index 0000000..c3d1bb7 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70fe7f12aaac69fd39dcbd44e58de034c7915b4879708f6f4f3c99c28e680a2c +size 5677665696 diff --git a/shisa-7b-v1-sharegpt.Q5_K_S.gguf b/shisa-7b-v1-sharegpt.Q5_K_S.gguf new file mode 100644 index 0000000..260cb36 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8a28615bdb378bfbaefcd95536a3f65d91426eedde38569970f406010862ab +size 5543972256 diff --git a/shisa-7b-v1-sharegpt.Q6_K.gguf b/shisa-7b-v1-sharegpt.Q6_K.gguf new file mode 100644 index 0000000..35592fa --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69aabcef369e8cd18c305f449086bfd12b368e7ff3f6e363588b30b3c2876aff +size 6536233696 diff --git a/shisa-7b-v1-sharegpt.Q8_0.gguf b/shisa-7b-v1-sharegpt.Q8_0.gguf new file mode 100644 index 0000000..383bd99 --- /dev/null +++ b/shisa-7b-v1-sharegpt.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eecbfc7267fd574eac734bb8857aa8f9258b09ec713c18fb5c3e503821989e8 +size 8464765024 diff --git a/shisa-7b-v1-sharegpt.f16.gguf b/shisa-7b-v1-sharegpt.f16.gguf new file mode 100644 index 0000000..6b4f714 --- /dev/null +++ b/shisa-7b-v1-sharegpt.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeaa8cd15be9b635b51ddcf26529e9ad99cab374c235fee854bf9bfac84d6489 +size 15930047584