commit 23e796fca52c0cb51db36f8188bbdb2ef8b95ac9 Author: ModelHub XC Date: Sat May 2 15:08:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/writer-8b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6817c0b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +writer-8b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8b2a37c --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: underwoods/writer-8b +datasets: +- RyokoAI/ScribbleHub17K +- RyokoExtra/FallingThroughTheSkies-592k +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- llama +- not-for-all-audiences +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/underwoods/writer-8b + + +static quants are available at https://huggingface.co/mradermacher/writer-8b-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/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/writer-8b-i1-GGUF/resolve/main/writer-8b.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..4df97df --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4585ab12ad0b514c30c103bd068d6e65ad5c5a3d1cac57b38f71b7cc89d07808 +size 4988157 diff --git a/writer-8b.i1-IQ1_M.gguf b/writer-8b.i1-IQ1_M.gguf new file mode 100644 index 0000000..39df257 --- /dev/null +++ b/writer-8b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb29c847e7b2cbdb60d90f5d3d4acb1bc10e23111d9a7f7b4687948d6325fdc2 +size 2161972192 diff --git a/writer-8b.i1-IQ1_S.gguf b/writer-8b.i1-IQ1_S.gguf new file mode 100644 index 0000000..8457d93 --- /dev/null +++ b/writer-8b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c79fd262a19dfaa0f8154c1747380312fc023f42899370bd5914a7d8cc43a8c +size 2019628000 diff --git a/writer-8b.i1-IQ2_M.gguf b/writer-8b.i1-IQ2_M.gguf new file mode 100644 index 0000000..ca39aac --- /dev/null +++ b/writer-8b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a78c528c3eda45f92cd095990fc2667e80bd286ecebf92094fb90f7d1044680 +size 2948281312 diff --git a/writer-8b.i1-IQ2_S.gguf b/writer-8b.i1-IQ2_S.gguf new file mode 100644 index 0000000..b3c8570 --- /dev/null +++ b/writer-8b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44db636e087c0f960082b098ed2aec3ae7ff231562977f4af3cb5f1799ee2003 +size 2758489056 diff --git a/writer-8b.i1-IQ2_XS.gguf b/writer-8b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..443d138 --- /dev/null +++ b/writer-8b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f539d34129a7ab8695931c297fafc1385e1513a4cc4410e9ff6ec89faa30ac4 +size 2605781984 diff --git a/writer-8b.i1-IQ2_XXS.gguf b/writer-8b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..37d7519 --- /dev/null +++ b/writer-8b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f18ee85d33be08a7d61af714da79f8067979aabe237a4626c4bf0c858184b8f +size 2399212512 diff --git a/writer-8b.i1-IQ3_M.gguf b/writer-8b.i1-IQ3_M.gguf new file mode 100644 index 0000000..655861a --- /dev/null +++ b/writer-8b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84558580d9c8017d1d5fb6323628fe5bb83ccec7a6afa918c74037070271cbe5 +size 3784823776 diff --git a/writer-8b.i1-IQ3_S.gguf b/writer-8b.i1-IQ3_S.gguf new file mode 100644 index 0000000..3b728df --- /dev/null +++ b/writer-8b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0fbfcb3eada9a79e9d4cba6f81365040f0b4c2a020cedfaf75c25fa3a9b615a +size 3682325472 diff --git a/writer-8b.i1-IQ3_XS.gguf b/writer-8b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9ab7fff --- /dev/null +++ b/writer-8b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e857bdc5adf921d1d3e268a6f79ca14acd7f5361e65890c63912fc49490c4afa +size 3518747616 diff --git a/writer-8b.i1-IQ3_XXS.gguf b/writer-8b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..37e87e0 --- /dev/null +++ b/writer-8b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2592f17e59e8379a93357c7a4f949ce82813eeddd78338a7557f751ab49be4b3 +size 3274912736 diff --git a/writer-8b.i1-IQ4_XS.gguf b/writer-8b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..efc6a72 --- /dev/null +++ b/writer-8b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4046316a78539e16fd4a6bff6e62c026f3e92a433d6937328424dce6e27311c7 +size 4447663072 diff --git a/writer-8b.i1-Q2_K.gguf b/writer-8b.i1-Q2_K.gguf new file mode 100644 index 0000000..d3b2ada --- /dev/null +++ b/writer-8b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c63183acaea5cd756f3bd6ab13ad3ccacd97a07b18882234439cef50dd0105 +size 3179131872 diff --git a/writer-8b.i1-Q3_K_L.gguf b/writer-8b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..64bf866 --- /dev/null +++ b/writer-8b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a16eacc8f99ad29633f6ee3ebb076873c4cb3fcdbb0d3536b3c51760152b5562 +size 4321956832 diff --git a/writer-8b.i1-Q3_K_M.gguf b/writer-8b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..cfcbca5 --- /dev/null +++ b/writer-8b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92206870214c431bba82a9587393999de28860efd3d5c22a42929c658bdd40ce +size 4018918368 diff --git a/writer-8b.i1-Q3_K_S.gguf b/writer-8b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..12f1ce2 --- /dev/null +++ b/writer-8b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80cff5d2619a2d93d951dce2c7568f69e83caa51038761a5415ec3858fdd4e6c +size 3664499680 diff --git a/writer-8b.i1-Q4_0.gguf b/writer-8b.i1-Q4_0.gguf new file mode 100644 index 0000000..01125c9 --- /dev/null +++ b/writer-8b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296fb52160a4089d5c02063aefe64ebe8979442f308b50a439a01ee68791790c +size 4675892192 diff --git a/writer-8b.i1-Q4_K_M.gguf b/writer-8b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..532f378 --- /dev/null +++ b/writer-8b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e27d17c6d4488457d973de2f5743da669a7f317b98a6757e6dedbe87ab791a +size 4920734688 diff --git a/writer-8b.i1-Q4_K_S.gguf b/writer-8b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..def162a --- /dev/null +++ b/writer-8b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7048a21ef47db5ef5ef1d36a9182e314b46398d021d2c57f16e27a89b437c5 +size 4692669408 diff --git a/writer-8b.i1-Q5_K_M.gguf b/writer-8b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6d92cf4 --- /dev/null +++ b/writer-8b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:995d36a8c9b6fb00663bdabed09832e36ea5bfcd44a9637dfb22e22331f59897 +size 5732987872 diff --git a/writer-8b.i1-Q5_K_S.gguf b/writer-8b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..df85509 --- /dev/null +++ b/writer-8b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a50d2aa82dd4cf48ffcfe9d459b3348ca4d589ad1bd89fc29e66d084bcb57b +size 5599294432 diff --git a/writer-8b.i1-Q6_K.gguf b/writer-8b.i1-Q6_K.gguf new file mode 100644 index 0000000..3aa15dd --- /dev/null +++ b/writer-8b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c7f78bbbdfe8e0963c87e411c9a3f637f0001817c3a05517afc3b450bbe6ad1 +size 6596006880