commit 283560980e288c62cd975b1aefec0d1a2ea990c8 Author: ModelHub XC Date: Thu Apr 30 08:31:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Octantis-QwenR1-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a8a9da8 --- /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 +Octantis-QwenR1-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Octantis-QwenR1-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Octantis-QwenR1-1.5B.IQ4_XS.gguf b/Octantis-QwenR1-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..b9a6e5b --- /dev/null +++ b/Octantis-QwenR1-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86946957dd4ed33bc980336994e5e14b64bcebd0564b2a9bb4742b69afd64173 +size 1026162944 diff --git a/Octantis-QwenR1-1.5B.Q2_K.gguf b/Octantis-QwenR1-1.5B.Q2_K.gguf new file mode 100644 index 0000000..efc309a --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5558bc19d0a5bd6c95e58f9c4782864fd087de290ca826fabf1c67f037881e3 +size 752880896 diff --git a/Octantis-QwenR1-1.5B.Q3_K_L.gguf b/Octantis-QwenR1-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..6ce40ba --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a4779dd183d538e665ac80fafce80bf7c5ba6141abf9841412fefe5100580e7 +size 980440832 diff --git a/Octantis-QwenR1-1.5B.Q3_K_M.gguf b/Octantis-QwenR1-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..dcf60f0 --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:030e7e54e8633aa3f103d90659c1d2c6650c47858a2e45bb13e451f8ed43df0b +size 924456704 diff --git a/Octantis-QwenR1-1.5B.Q3_K_S.gguf b/Octantis-QwenR1-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..e691666 --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb5a17fd3da91e1544d890dd0bd1cebb32cd09c24db1c203cfb8dd3a74a071b9 +size 861222656 diff --git a/Octantis-QwenR1-1.5B.Q4_K_M.gguf b/Octantis-QwenR1-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..cfd277f --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3184ecbb677c4184b97d33879856a51e061a730efa024e736e45ddb175b27f +size 1117321472 diff --git a/Octantis-QwenR1-1.5B.Q4_K_S.gguf b/Octantis-QwenR1-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..13b756d --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc68386b569b433d20b07eceb17945bc6a6e5df063f055529cb830e8aca52e22 +size 1071585536 diff --git a/Octantis-QwenR1-1.5B.Q5_K_M.gguf b/Octantis-QwenR1-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..2bbdf72 --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c2d5c497cb13bc1b06dcfc601165c12c29455f938200bbbf0bde4c0da76751 +size 1285495040 diff --git a/Octantis-QwenR1-1.5B.Q5_K_S.gguf b/Octantis-QwenR1-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..03f423f --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c653f27c837169b6b4399f21471aca0626e2cca973911b5c9a82cac4e6ddba53 +size 1259174144 diff --git a/Octantis-QwenR1-1.5B.Q6_K.gguf b/Octantis-QwenR1-1.5B.Q6_K.gguf new file mode 100644 index 0000000..9b7a9d8 --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0aba35e6640abe236efa7baf22992a4244f0834a6d1615d649cfaac568411e8e +size 1464179456 diff --git a/Octantis-QwenR1-1.5B.Q8_0.gguf b/Octantis-QwenR1-1.5B.Q8_0.gguf new file mode 100644 index 0000000..1aad885 --- /dev/null +++ b/Octantis-QwenR1-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22ebd98a299ffc861878b702c55fb6db6c51a1e35269bf2fc8384cf202752961 +size 1894532864 diff --git a/Octantis-QwenR1-1.5B.f16.gguf b/Octantis-QwenR1-1.5B.f16.gguf new file mode 100644 index 0000000..a015ba6 --- /dev/null +++ b/Octantis-QwenR1-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d227472679035272cfd787ea844f1e553ada18987584bebe8fab12cd0e5907 +size 3560417024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ed0cada --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: prithivMLmods/Octantis-QwenR1-1.5B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- Math +- Code +- RL +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Octantis-QwenR1-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Octantis-QwenR1-1.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-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/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Octantis-QwenR1-1.5B-GGUF/resolve/main/Octantis-QwenR1-1.5B.f16.gguf) | f16 | 3.7 | 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. + +