commit 6a25320fddc846027eea2b4092231704e743bdfb Author: ModelHub XC Date: Mon Sep 28 10:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Whale-4B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f512816 --- /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 +Whale-4B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Whale-4B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e95fd92 --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: roskosmos19/Orca-4B-Thinking +language: +- en +- de +- es +- fr +- zh +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Whale-AI/Whale-4B-Thinking/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- chain-of-thought +- deepseek-r1 +- thinking +- qwen3 +- whale +--- +## About + + + + + + + + + +static quants of https://huggingface.co/roskosmos19/Orca-4B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Whale-4B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Whale-4B-Thinking-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/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Whale-4B-Thinking-GGUF/resolve/main/Whale-4B-Thinking.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. + + diff --git a/Whale-4B-Thinking.IQ4_XS.gguf b/Whale-4B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..33c7a83 --- /dev/null +++ b/Whale-4B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5f2feb2fdf317eff8b56aee5226662dd93f007191f1c5cbf9567f857e02513 +size 2286316960 diff --git a/Whale-4B-Thinking.Q2_K.gguf b/Whale-4B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..e58919b --- /dev/null +++ b/Whale-4B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c027a10bea98751cae72d3b6c4520cc9feef53aa0194f9e5fcd0c8d1601e274 +size 1669500320 diff --git a/Whale-4B-Thinking.Q3_K_L.gguf b/Whale-4B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..bfd8a88 --- /dev/null +++ b/Whale-4B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04398f55c1ca4b0d78e2ee55f6250c50adb654d8fa8c64bd43422f104d36f85d +size 2239786400 diff --git a/Whale-4B-Thinking.Q3_K_M.gguf b/Whale-4B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..6f48072 --- /dev/null +++ b/Whale-4B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec004bb6c89b7e795e0c9ec7466c1198c27e857d6fa83454327e34400f9c6a2 +size 2075618720 diff --git a/Whale-4B-Thinking.Q3_K_S.gguf b/Whale-4B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..8aaa166 --- /dev/null +++ b/Whale-4B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4186acefb33a8fe5cc4b9a321629fbb0b09be677f38f44e555a097fb4a5691 +size 1886997920 diff --git a/Whale-4B-Thinking.Q4_K_M.gguf b/Whale-4B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..f73531a --- /dev/null +++ b/Whale-4B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19a8694c7654dd00a0a173b041b1bce17aa71c5e45bb6811468bc6f297d497c2 +size 2497281440 diff --git a/Whale-4B-Thinking.Q4_K_S.gguf b/Whale-4B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..8dd84c5 --- /dev/null +++ b/Whale-4B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74717d40d39116a877ef48837a04d89f9e1ab534642e9c0c22964ac0ba1c5898 +size 2383310240 diff --git a/Whale-4B-Thinking.Q5_K_M.gguf b/Whale-4B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..7c9e5bd --- /dev/null +++ b/Whale-4B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea0eca6ae7b326234ce634ada07781e05921d3c1f3e60c4b9af0e18a3628cba +size 2889514400 diff --git a/Whale-4B-Thinking.Q5_K_S.gguf b/Whale-4B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..1244109 --- /dev/null +++ b/Whale-4B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c549d07d7dfcbc89815f4cd7705687dd2987a08812b0ed852db417b4b894857 +size 2823712160 diff --git a/Whale-4B-Thinking.Q6_K.gguf b/Whale-4B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..55ce931 --- /dev/null +++ b/Whale-4B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1632941b201be9e495774c82487608c87e95620d2b3d4929592515c172abe7 +size 3306261920 diff --git a/Whale-4B-Thinking.Q8_0.gguf b/Whale-4B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..792ddf0 --- /dev/null +++ b/Whale-4B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1a67a956b847d9fbdf2d6d4a099f9aff59b54131274b97ff1af7829da71922 +size 4280405920 diff --git a/Whale-4B-Thinking.f16.gguf b/Whale-4B-Thinking.f16.gguf new file mode 100644 index 0000000..81938ad --- /dev/null +++ b/Whale-4B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e848611b30cc8ac50f96d52fa062e2949bed122d0adb75b127490f9735d5b3 +size 8051285920