commit b96ebe3fc99aef225ceea4911af8898d0d877e40 Author: ModelHub XC Date: Fri Jul 17 17:15:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/L3.1-8b-RP-Ink-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5af3002 --- /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 +L3.1-8b-RP-Ink.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.f16.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +L3.1-8b-RP-Ink.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/L3.1-8b-RP-Ink.IQ4_XS.gguf b/L3.1-8b-RP-Ink.IQ4_XS.gguf new file mode 100644 index 0000000..1722300 --- /dev/null +++ b/L3.1-8b-RP-Ink.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af5dc4c7886166984e56d8f52c1278a056ffa44461280c9615ec8cc1e21e674a +size 4484368128 diff --git a/L3.1-8b-RP-Ink.Q2_K.gguf b/L3.1-8b-RP-Ink.Q2_K.gguf new file mode 100644 index 0000000..4492343 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a19ebfc116af7e34f8590d87a3fbed853088c5ca53a08ad54b70398043506a5 +size 3179136768 diff --git a/L3.1-8b-RP-Ink.Q3_K_L.gguf b/L3.1-8b-RP-Ink.Q3_K_L.gguf new file mode 100644 index 0000000..08167a8 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1fd9c436a790c6412d7e7ee5b11018d0c0979fd87da1fffb2f346459ba307c4 +size 4321961728 diff --git a/L3.1-8b-RP-Ink.Q3_K_M.gguf b/L3.1-8b-RP-Ink.Q3_K_M.gguf new file mode 100644 index 0000000..b6e87ac --- /dev/null +++ b/L3.1-8b-RP-Ink.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb0323863be74a145659c8af268170f0df95d6d0b57df314e6a33d99a13b134 +size 4018923264 diff --git a/L3.1-8b-RP-Ink.Q3_K_S.gguf b/L3.1-8b-RP-Ink.Q3_K_S.gguf new file mode 100644 index 0000000..3b93ea0 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b9d4763305fa5b08c12048ebe426b2831de25bd729c8cf3a978cabf8a01c867 +size 3664504576 diff --git a/L3.1-8b-RP-Ink.Q4_K_M.gguf b/L3.1-8b-RP-Ink.Q4_K_M.gguf new file mode 100644 index 0000000..2d18ccf --- /dev/null +++ b/L3.1-8b-RP-Ink.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32d98639043d657f4b86e7d3436b170dd3cf7e8a3d23abcf590abb49ef1b6315 +size 4920739584 diff --git a/L3.1-8b-RP-Ink.Q4_K_S.gguf b/L3.1-8b-RP-Ink.Q4_K_S.gguf new file mode 100644 index 0000000..51cf065 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdfb54c478f6604ab0c29ca293fa64e5349cb530bda1eee21ee71b83112b24e0 +size 4692674304 diff --git a/L3.1-8b-RP-Ink.Q5_K_M.gguf b/L3.1-8b-RP-Ink.Q5_K_M.gguf new file mode 100644 index 0000000..c801b79 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4593d4b66552763ea84b9be2318bffeafd73dbdaec8db1b4d2c9fee9437022d0 +size 5732992768 diff --git a/L3.1-8b-RP-Ink.Q5_K_S.gguf b/L3.1-8b-RP-Ink.Q5_K_S.gguf new file mode 100644 index 0000000..3b0fe03 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdef93904701dc99ca3392dae143644c85b6f2378db1e3122d62c1afc4972fab +size 5599299328 diff --git a/L3.1-8b-RP-Ink.Q6_K.gguf b/L3.1-8b-RP-Ink.Q6_K.gguf new file mode 100644 index 0000000..e481513 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3c004183e5653785257bb8e07dc4499ed2893661c6afd1bf480ee090bc05124 +size 6596011776 diff --git a/L3.1-8b-RP-Ink.Q8_0.gguf b/L3.1-8b-RP-Ink.Q8_0.gguf new file mode 100644 index 0000000..37ac530 --- /dev/null +++ b/L3.1-8b-RP-Ink.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd863689e27c2c242c05831e0e3c887429550c1c3e63c5f077ab91e29750078e +size 8540776192 diff --git a/L3.1-8b-RP-Ink.f16.gguf b/L3.1-8b-RP-Ink.f16.gguf new file mode 100644 index 0000000..2a1f043 --- /dev/null +++ b/L3.1-8b-RP-Ink.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3791c3ffa916dc10cdb85325cc1eafd3fc0b6df6d6ee4bc06f2cf2b54dc641ca +size 16068896512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb4b0b6 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: allura-org/L3.1-8b-RP-Ink +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- conversational +- roleplay +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/allura-org/L3.1-8b-RP-Ink + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-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/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/L3.1-8b-RP-Ink-GGUF/resolve/main/L3.1-8b-RP-Ink.f16.gguf) | f16 | 16.2 | 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. + +