commit 074ddfeb1eb568e633420ec6825d0bd8cb105e51 Author: ModelHub XC Date: Fri May 8 13:44:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qibil-4B-v0.1-RP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..612dc27 --- /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 +Qibil-4B-v0.1-RP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qibil-4B-v0.1-RP.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qibil-4B-v0.1-RP.IQ4_XS.gguf b/Qibil-4B-v0.1-RP.IQ4_XS.gguf new file mode 100644 index 0000000..a5514f3 --- /dev/null +++ b/Qibil-4B-v0.1-RP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6976dff8309ffb8474f628dee40c88a6c0ea6cc1bd7c55fcdc7ccce29738e0f4 +size 2286312448 diff --git a/Qibil-4B-v0.1-RP.Q2_K.gguf b/Qibil-4B-v0.1-RP.Q2_K.gguf new file mode 100644 index 0000000..a3ba1f7 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9874b34f2e6fc072a8f327d5953a41de9c34910d344175821e08171659ec1658 +size 1669495808 diff --git a/Qibil-4B-v0.1-RP.Q3_K_L.gguf b/Qibil-4B-v0.1-RP.Q3_K_L.gguf new file mode 100644 index 0000000..4155483 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1351deac46325ed62dfba6b8bf4ce0c4b4fbe577e8e02c1d7f8a74cdfd9b137e +size 2239781888 diff --git a/Qibil-4B-v0.1-RP.Q3_K_M.gguf b/Qibil-4B-v0.1-RP.Q3_K_M.gguf new file mode 100644 index 0000000..decafd4 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5c54251e5fca52c5bfa83639cbfe2f9939861c350abe49ea3b43b63404a39b0 +size 2075614208 diff --git a/Qibil-4B-v0.1-RP.Q3_K_S.gguf b/Qibil-4B-v0.1-RP.Q3_K_S.gguf new file mode 100644 index 0000000..cae37e4 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06ca35193d018c6f7571313a478f30d650bd311a5ea86f0b9aebf6972f0b9c6 +size 1886993408 diff --git a/Qibil-4B-v0.1-RP.Q4_K_M.gguf b/Qibil-4B-v0.1-RP.Q4_K_M.gguf new file mode 100644 index 0000000..ecfb2d2 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dff7153e52f0e224f82fa7d34c7d61faffbb965c79242e4231d2d5680f310aa +size 2497276928 diff --git a/Qibil-4B-v0.1-RP.Q4_K_S.gguf b/Qibil-4B-v0.1-RP.Q4_K_S.gguf new file mode 100644 index 0000000..2bbf6e2 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3a28c568dee03c7fe093b79942cbdceb2377b773e77b353d42bfeb1c7d3d4c +size 2383305728 diff --git a/Qibil-4B-v0.1-RP.Q5_K_M.gguf b/Qibil-4B-v0.1-RP.Q5_K_M.gguf new file mode 100644 index 0000000..14c5516 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f63995321fcdcb9dc22a605487b0e8a3b0dbe4db9fa9a3dad36fadb247fb6e +size 2889509888 diff --git a/Qibil-4B-v0.1-RP.Q5_K_S.gguf b/Qibil-4B-v0.1-RP.Q5_K_S.gguf new file mode 100644 index 0000000..ea9bd83 --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8260346fe1dd286ba1df594a8286d1770f64a749e61b9a03ba031a611d7687 +size 2823707648 diff --git a/Qibil-4B-v0.1-RP.Q6_K.gguf b/Qibil-4B-v0.1-RP.Q6_K.gguf new file mode 100644 index 0000000..a2ac05e --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65bc696ec8b71052dc67cfab46695c289a72fb526960952eb4d1f56417ea7ea +size 3306257408 diff --git a/Qibil-4B-v0.1-RP.Q8_0.gguf b/Qibil-4B-v0.1-RP.Q8_0.gguf new file mode 100644 index 0000000..f63be7b --- /dev/null +++ b/Qibil-4B-v0.1-RP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c373bac23f334dbca5f5c8f367b5ddff7cd7a423602f09407698808916b18f37 +size 4280401408 diff --git a/Qibil-4B-v0.1-RP.f16.gguf b/Qibil-4B-v0.1-RP.f16.gguf new file mode 100644 index 0000000..c7c333e --- /dev/null +++ b/Qibil-4B-v0.1-RP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e146c9aafb9864f7ffdf73ee36c75845265a0fd4ed99e9115c8049542a09bcb7 +size 8051281408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1a2669e --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Hastagaras/Qibil-4B-v0.1-RP +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Hastagaras/Qibil-4B-v0.1-RP + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-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/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qibil-4B-v0.1-RP-GGUF/resolve/main/Qibil-4B-v0.1-RP.f16.gguf) | f16 | 8.2 | 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. + +