commit 2cadebe17967b61c26aafe0abb5d509f9dc280d7 Author: ModelHub XC Date: Wed Apr 22 14:49:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Swallow-7b-plus-hf-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e212313 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Swallow-7b-plus-hf.f16.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Swallow-7b-plus-hf.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..29c840b --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: tokyotech-llm/Swallow-7b-plus-hf +language: +- en +- ja +library_name: transformers +license: llama2 +model_type: llama +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/tokyotech-llm/Swallow-7b-plus-hf + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Swallow-7b-plus-hf-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/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.IQ3_XS.gguf) | IQ3_XS | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.IQ3_S.gguf) | IQ3_S | 3.1 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.IQ3_M.gguf) | IQ3_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Swallow-7b-plus-hf-GGUF/resolve/main/Swallow-7b-plus-hf.f16.gguf) | f16 | 13.8 | 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/Swallow-7b-plus-hf.IQ3_M.gguf b/Swallow-7b-plus-hf.IQ3_M.gguf new file mode 100644 index 0000000..e2d9707 --- /dev/null +++ b/Swallow-7b-plus-hf.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf0a5d1ab2451598f0c7503c0ab6ef0b137c6453d13f86d97f36a215384aaac +size 3172341056 diff --git a/Swallow-7b-plus-hf.IQ3_S.gguf b/Swallow-7b-plus-hf.IQ3_S.gguf new file mode 100644 index 0000000..c8b9f54 --- /dev/null +++ b/Swallow-7b-plus-hf.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5511903bbbac9d0eabfa45c5926795c1aa7b58c6af85523212b366550fe704c5 +size 3005781312 diff --git a/Swallow-7b-plus-hf.IQ3_XS.gguf b/Swallow-7b-plus-hf.IQ3_XS.gguf new file mode 100644 index 0000000..36176e0 --- /dev/null +++ b/Swallow-7b-plus-hf.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9197f368513ebb60245514301f779bad02b7acda1555f59fd10fcdb063a34e +size 2853999936 diff --git a/Swallow-7b-plus-hf.IQ4_XS.gguf b/Swallow-7b-plus-hf.IQ4_XS.gguf new file mode 100644 index 0000000..bf2dd2a --- /dev/null +++ b/Swallow-7b-plus-hf.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81982c1c7bf1d8d85100362d054caf0679c333406f36c9b662da5a69e15cbd2d +size 3709642304 diff --git a/Swallow-7b-plus-hf.Q2_K.gguf b/Swallow-7b-plus-hf.Q2_K.gguf new file mode 100644 index 0000000..b7dd888 --- /dev/null +++ b/Swallow-7b-plus-hf.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf2b35ec518395ec9f5118826794531f7a90d12fefdcdd318488b55cc7567b6 +size 2585691200 diff --git a/Swallow-7b-plus-hf.Q3_K_L.gguf b/Swallow-7b-plus-hf.Q3_K_L.gguf new file mode 100644 index 0000000..38befa0 --- /dev/null +++ b/Swallow-7b-plus-hf.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d69554e976f5f78d720f81d9ea17643d5f5887945fdc45b2ac91f644e2eb117 +size 3654587712 diff --git a/Swallow-7b-plus-hf.Q3_K_M.gguf b/Swallow-7b-plus-hf.Q3_K_M.gguf new file mode 100644 index 0000000..46b2538 --- /dev/null +++ b/Swallow-7b-plus-hf.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5509c76d635f75e6b68517da55e05aa451d4ef9536a4126c79ffe85763d2dadd +size 3355481408 diff --git a/Swallow-7b-plus-hf.Q3_K_S.gguf b/Swallow-7b-plus-hf.Q3_K_S.gguf new file mode 100644 index 0000000..4b0fa9c --- /dev/null +++ b/Swallow-7b-plus-hf.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22c7fa6753b277c83ef4b6c9da7da82af6441acbec7a988a46a951cc8cbbb957 +size 3005781312 diff --git a/Swallow-7b-plus-hf.Q4_K_M.gguf b/Swallow-7b-plus-hf.Q4_K_M.gguf new file mode 100644 index 0000000..1f863ba --- /dev/null +++ b/Swallow-7b-plus-hf.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79850a1c63e5071eb2bc0277ffd226f0414082ae5aeda5ddcc60279389cc3617 +size 4144560704 diff --git a/Swallow-7b-plus-hf.Q4_K_S.gguf b/Swallow-7b-plus-hf.Q4_K_S.gguf new file mode 100644 index 0000000..69bd2cf --- /dev/null +++ b/Swallow-7b-plus-hf.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88a2ff6563c962a59a6d836e69af98c82f6cd72882e2918a1bd2227cf867dceb +size 3920296512 diff --git a/Swallow-7b-plus-hf.Q5_K_M.gguf b/Swallow-7b-plus-hf.Q5_K_M.gguf new file mode 100644 index 0000000..2cc759a --- /dev/null +++ b/Swallow-7b-plus-hf.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98623dd3d205f6e9b4ddebc23edcaeb3ddf26564f2457cbc1a5f774f032c36f2 +size 4852435520 diff --git a/Swallow-7b-plus-hf.Q5_K_S.gguf b/Swallow-7b-plus-hf.Q5_K_S.gguf new file mode 100644 index 0000000..c8dac03 --- /dev/null +++ b/Swallow-7b-plus-hf.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8fccb02fca534a7a2db035331375bf4188244ebce0094335ddf7bfb8e42c5c +size 4720970304 diff --git a/Swallow-7b-plus-hf.Q6_K.gguf b/Swallow-7b-plus-hf.Q6_K.gguf new file mode 100644 index 0000000..43fc9b9 --- /dev/null +++ b/Swallow-7b-plus-hf.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4be6680f60081616b53483829ec50885466862c7481e8b87c37a77fa886cf26 +size 5604552512 diff --git a/Swallow-7b-plus-hf.Q8_0.gguf b/Swallow-7b-plus-hf.Q8_0.gguf new file mode 100644 index 0000000..a7eb917 --- /dev/null +++ b/Swallow-7b-plus-hf.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b1c93374f4890a36d6e17897f8aae0ee1a32751b2390a4019ae08db0745e15f +size 7258621248 diff --git a/Swallow-7b-plus-hf.f16.gguf b/Swallow-7b-plus-hf.f16.gguf new file mode 100644 index 0000000..a550969 --- /dev/null +++ b/Swallow-7b-plus-hf.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99fe9e415ada995c78677a902a057c4ca56f500d5145b5d2d23d2ea5bb84d55a +size 13661467968