commit 249fa88eda180559be0124a4bf35b7346d4f6768 Author: ModelHub XC Date: Sat May 9 13:32:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepTheorem-qwen-3b-rl-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8778c38 --- /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 +DeepTheorem-qwen-3b-rl.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepTheorem-qwen-3b-rl.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepTheorem-qwen-3b-rl.IQ4_XS.gguf b/DeepTheorem-qwen-3b-rl.IQ4_XS.gguf new file mode 100644 index 0000000..f7b2409 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44f5e2c95f77bc11fe3137763a0b7e3cf8aaeb5944e825d66c232ea8875224a +size 1918490048 diff --git a/DeepTheorem-qwen-3b-rl.Q2_K.gguf b/DeepTheorem-qwen-3b-rl.Q2_K.gguf new file mode 100644 index 0000000..cd16f8d --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104046f436704dc79f09d83b4ad1839535820f0d560715cfabf99dfda3ca5ba1 +size 1376855488 diff --git a/DeepTheorem-qwen-3b-rl.Q3_K_L.gguf b/DeepTheorem-qwen-3b-rl.Q3_K_L.gguf new file mode 100644 index 0000000..505ae5e --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29c3eaf2a335936936896f2e52e2bd0bb15df4b74bc0b9d9178ee78a7ca3707 +size 1841094080 diff --git a/DeepTheorem-qwen-3b-rl.Q3_K_M.gguf b/DeepTheorem-qwen-3b-rl.Q3_K_M.gguf new file mode 100644 index 0000000..717616d --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418a04d9bc2628b359b0deca57cf7d62170066a61c7846644e2bcd9b2e55f1df +size 1724177856 diff --git a/DeepTheorem-qwen-3b-rl.Q3_K_S.gguf b/DeepTheorem-qwen-3b-rl.Q3_K_S.gguf new file mode 100644 index 0000000..69cb47f --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de3d68f1ae1c91bc415b04377c6fe6f942c727a05a2e4b66cc7926ef457e86b +size 1588059584 diff --git a/DeepTheorem-qwen-3b-rl.Q4_K_M.gguf b/DeepTheorem-qwen-3b-rl.Q4_K_M.gguf new file mode 100644 index 0000000..01fbf85 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23554aee3b439054b82221142e0d5bf42f5c361edd6adae43178b40100541690 +size 2104931776 diff --git a/DeepTheorem-qwen-3b-rl.Q4_K_S.gguf b/DeepTheorem-qwen-3b-rl.Q4_K_S.gguf new file mode 100644 index 0000000..37c911a --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dd055bad540a8891f06310bf934ed1cca59b8a45d98316f8841f32d51c5770e +size 2009413056 diff --git a/DeepTheorem-qwen-3b-rl.Q5_K_M.gguf b/DeepTheorem-qwen-3b-rl.Q5_K_M.gguf new file mode 100644 index 0000000..ea23696 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf24f0ed6d727d848d89483cba5f54880c65db87ca39b3ebd05f2290d09fc4a +size 2438739392 diff --git a/DeepTheorem-qwen-3b-rl.Q5_K_S.gguf b/DeepTheorem-qwen-3b-rl.Q5_K_S.gguf new file mode 100644 index 0000000..36be6b0 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55ee182e614cbb6582f1d36a3ebcdcfa8b6820f41b6966cb5df7a4fa92a7b63 +size 2383590848 diff --git a/DeepTheorem-qwen-3b-rl.Q6_K.gguf b/DeepTheorem-qwen-3b-rl.Q6_K.gguf new file mode 100644 index 0000000..c87b474 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0fca3dcca75671ffaa2667b236031da2665a03e21ef7a1568ab67f01e90082 +size 2793409984 diff --git a/DeepTheorem-qwen-3b-rl.Q8_0.gguf b/DeepTheorem-qwen-3b-rl.Q8_0.gguf new file mode 100644 index 0000000..c6c9697 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:158b98ad5d655f3dfbe7e88f8a91ab28383bbf6e700ac2a109e8d7c6e9953819 +size 3616087488 diff --git a/DeepTheorem-qwen-3b-rl.f16.gguf b/DeepTheorem-qwen-3b-rl.f16.gguf new file mode 100644 index 0000000..4ede970 --- /dev/null +++ b/DeepTheorem-qwen-3b-rl.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a82058fa82ab7f606cfe144eb4af69bc9cf710a32613f62bb4d77227326d715 +size 6800645568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..287da05 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Jiahao004/DeepTheorem-qwen-3b-rl +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Jiahao004/DeepTheorem-qwen-3b-rl + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-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/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepTheorem-qwen-3b-rl-GGUF/resolve/main/DeepTheorem-qwen-3b-rl.f16.gguf) | f16 | 6.9 | 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. + +