commit fa3324a2127b886d570e81a12099bcfb653ff419 Author: ModelHub XC Date: Wed Oct 14 06:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FlashResearch-4B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cd0a141 --- /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 +FlashResearch-4B-Thinking.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FlashResearch-4B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FlashResearch-4B-Thinking.IQ4_XS.gguf b/FlashResearch-4B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..484e2cb --- /dev/null +++ b/FlashResearch-4B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741f26ee01c2bb4e8679037739f2931c2046e0a29878ad51de4193c378fd50a9 +size 2286316448 diff --git a/FlashResearch-4B-Thinking.Q2_K.gguf b/FlashResearch-4B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..d054641 --- /dev/null +++ b/FlashResearch-4B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:019d87f9a03de83dbe775b3a99007fdffd437604194108923db5c66be6f9ad70 +size 1669499808 diff --git a/FlashResearch-4B-Thinking.Q3_K_L.gguf b/FlashResearch-4B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..b361c22 --- /dev/null +++ b/FlashResearch-4B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42dcde4d0b401d8d101f67af27a72ebdfdcb417d634fd768bccc081598034423 +size 2239785888 diff --git a/FlashResearch-4B-Thinking.Q3_K_M.gguf b/FlashResearch-4B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..69fd87f --- /dev/null +++ b/FlashResearch-4B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d952573eacdc4c8335281d3e4110d6e3be6eed06ae6e8c110234d78feaa8c94 +size 2075618208 diff --git a/FlashResearch-4B-Thinking.Q3_K_S.gguf b/FlashResearch-4B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..eae69fc --- /dev/null +++ b/FlashResearch-4B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a7682bd09da41bf1c663d1e74975e921e7f9e128efa82d9d6170197b0841f3 +size 1886997408 diff --git a/FlashResearch-4B-Thinking.Q4_K_M.gguf b/FlashResearch-4B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..d54634a --- /dev/null +++ b/FlashResearch-4B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96328abcb01dddd7a7988b78ce1a2d28a67e6b30c227cc9aea982bc0e074db30 +size 2497280928 diff --git a/FlashResearch-4B-Thinking.Q4_K_S.gguf b/FlashResearch-4B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..00d1446 --- /dev/null +++ b/FlashResearch-4B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2c449d764375ca12ec7b055ba0e744aee66886f9e14f68e84f0c07dcf9b4ce +size 2383309728 diff --git a/FlashResearch-4B-Thinking.Q5_K_M.gguf b/FlashResearch-4B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..e4fe1ac --- /dev/null +++ b/FlashResearch-4B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d88dd67b184e78d846ccf3923de5ca6efe744ee18c9e364eab7c41537bfc77c +size 2889513888 diff --git a/FlashResearch-4B-Thinking.Q5_K_S.gguf b/FlashResearch-4B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..9e1ce11 --- /dev/null +++ b/FlashResearch-4B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9baf5ef5ea5a4b24095bda3a01fa1b4fd0731ee68837bbc2acb53baa0757c19 +size 2823711648 diff --git a/FlashResearch-4B-Thinking.Q6_K.gguf b/FlashResearch-4B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..c27a10a --- /dev/null +++ b/FlashResearch-4B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f3252a28ee35f232917a0b90ff01696ccfc7cf9337cf31c60d8cd8eae5fb09 +size 3306261408 diff --git a/FlashResearch-4B-Thinking.Q8_0.gguf b/FlashResearch-4B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..db3e18d --- /dev/null +++ b/FlashResearch-4B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abda7da5e5eb41036fbb5491f548f246f545e4909755fe8550a24a6fe8b75d0e +size 4280405408 diff --git a/FlashResearch-4B-Thinking.f16.gguf b/FlashResearch-4B-Thinking.f16.gguf new file mode 100644 index 0000000..7f6e0d2 --- /dev/null +++ b/FlashResearch-4B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda8b10d87379a564ea4d91f32beb136c7e390eb10e22e53295521277871c41d +size 8051285408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4be90b1 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: flashresearch/FlashResearch-4B-Thinking +datasets: +- cheapresearch/CheapResearch-DS-33k +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/flashresearch/FlashResearch-4B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#FlashResearch-4B-Thinking-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/FlashResearch-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/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-4B-Thinking.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FlashResearch-4B-Thinking-GGUF/resolve/main/FlashResearch-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. + +