commit 6d37dab06b43e1aa496b4b2697186e1179d99d08 Author: ModelHub XC Date: Tue Jun 16 00:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/shisa-v2-qwen2.5-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a54fbff --- /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 +shisa-v2-qwen2.5-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +shisa-v2-qwen2.5-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..295e45c --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: shisa-ai/shisa-v2-qwen2.5-7b +datasets: +- shisa-ai/shisa-v2-sharegpt +- shisa-ai/deepseekv3-ultrafeedback-armorm-dpo +language: +- ja +- en +library_name: transformers +license: apache-2.0 +model_name: shisa-v2-qwen2.5-7b +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/shisa-ai/shisa-v2-qwen2.5-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-i1-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/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/shisa-v2-qwen2.5-7b-GGUF/resolve/main/shisa-v2-qwen2.5-7b.f16.gguf) | f16 | 15.3 | 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-v2-qwen2.5-7b.IQ4_XS.gguf b/shisa-v2-qwen2.5-7b.IQ4_XS.gguf new file mode 100644 index 0000000..8436085 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:029a0e0eb3e44a355b7b78d9ff8e3c9fdc969b220a6da320548ee1b157332324 +size 4250299552 diff --git a/shisa-v2-qwen2.5-7b.Q2_K.gguf b/shisa-v2-qwen2.5-7b.Q2_K.gguf new file mode 100644 index 0000000..a4b2d90 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d523f953b6e6aa4d01099c4a8281a86be88d882b10d739632fc357a4fca0431 +size 3015941280 diff --git a/shisa-v2-qwen2.5-7b.Q3_K_L.gguf b/shisa-v2-qwen2.5-7b.Q3_K_L.gguf new file mode 100644 index 0000000..0acfe34 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fc409218164f0101a4d55d5011f3f707932667e1d4243c048ea3dd2ad92d0b +size 4088460448 diff --git a/shisa-v2-qwen2.5-7b.Q3_K_M.gguf b/shisa-v2-qwen2.5-7b.Q3_K_M.gguf new file mode 100644 index 0000000..4601024 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6610557bf9f2313ef514e6273309e6d67f6e91a408d9ba1c5c1e44ddccbf845b +size 3808392352 diff --git a/shisa-v2-qwen2.5-7b.Q3_K_S.gguf b/shisa-v2-qwen2.5-7b.Q3_K_S.gguf new file mode 100644 index 0000000..3f93ff9 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:478c638c3616add7ad927d296e0b1f9c2b606c11f22edb00ed7aa8409da1bcae +size 3492369568 diff --git a/shisa-v2-qwen2.5-7b.Q4_K_M.gguf b/shisa-v2-qwen2.5-7b.Q4_K_M.gguf new file mode 100644 index 0000000..b6b0e85 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a81cc7113e9dfbe14e65aabcea8399142ef582ec27807d9459b627e0acc2347 +size 4683074720 diff --git a/shisa-v2-qwen2.5-7b.Q4_K_S.gguf b/shisa-v2-qwen2.5-7b.Q4_K_S.gguf new file mode 100644 index 0000000..5061497 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8705db537b00ef8e90c4c713ee6631c0d2e55e8459c341ae4900f01f6b1892bb +size 4457770144 diff --git a/shisa-v2-qwen2.5-7b.Q5_K_M.gguf b/shisa-v2-qwen2.5-7b.Q5_K_M.gguf new file mode 100644 index 0000000..9e4118e --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5230244fde5eddeee2bad98fd9d35c895fd6b197d30a496fbfa05fa1dc2cca0b +size 5444832416 diff --git a/shisa-v2-qwen2.5-7b.Q5_K_S.gguf b/shisa-v2-qwen2.5-7b.Q5_K_S.gguf new file mode 100644 index 0000000..f9be8e6 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d522e28141ce6d0a7732046fa8d28aab8140601c69e0bc791053ab261d0814 +size 5315177632 diff --git a/shisa-v2-qwen2.5-7b.Q6_K.gguf b/shisa-v2-qwen2.5-7b.Q6_K.gguf new file mode 100644 index 0000000..3fa09ab --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca4fae04e28fd810ea1534fc1cfc8de6a09dc9c8ac840ea9d512f27fb2ca40c5 +size 6254199968 diff --git a/shisa-v2-qwen2.5-7b.Q8_0.gguf b/shisa-v2-qwen2.5-7b.Q8_0.gguf new file mode 100644 index 0000000..8bcff60 --- /dev/null +++ b/shisa-v2-qwen2.5-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f434727e908302d145044336fd8a8771ee10ca1fb9b464fa0b2b560a9d6796c +size 8098526368 diff --git a/shisa-v2-qwen2.5-7b.f16.gguf b/shisa-v2-qwen2.5-7b.f16.gguf new file mode 100644 index 0000000..16387dd --- /dev/null +++ b/shisa-v2-qwen2.5-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49ab3b0c8dd4cb0a05a2c4deb8f9f34ad8e2e2ac6f0db70e6b113146dd453a1a +size 15237854368