commit cd5e0718bc8528db57bfe45de90f3810414fe5d3 Author: ModelHub XC Date: Tue Jul 7 18:42:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/VibeThinker-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a34718 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,77 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.BF16.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.F16.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.F32.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text + +VibeThinker-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..53368d8 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +license: mit +base_model: +- WeiboAI/VibeThinker-3B +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- math +- code +- reasoning +- gpqa +- instruction-following +- text-generation-inference +- llama-cpp +--- + +# **VibeThinker-3B-GGUF** + +> **[VibeThinker-3B](https://huggingface.co/WeiboAI/VibeThinker-3B)** is a 3-billion-parameter reasoning-focused language model developed by WeiboAI, built on top of Qwen2.5-Coder-3B and trained using the Spectrum-to-Signal Principle (SSP) post-training pipeline, which combines curriculum-based two-stage SFT, multi-domain reinforcement learning via MaxEnt-Guided Policy Optimization (MGPO), offline self-distillation, and instruct RL to systematically develop strong verifiable reasoning capabilities across mathematics, coding, and STEM tasks. Motivated by the Parametric Compression-Coverage Hypothesis — which posits that verifiable reasoning is a highly compressible, parameter-dense capability that compact models can carry near-frontier performance in — VibeThinker-3B achieves remarkable results for its size, scoring 76.4 on IMO-AnswerBench (improving to 80.6 with Claim-Level Reliability Assessment test-time scaling), competing with models like DeepSeek V3.2 (671B) and Kimi K2.5 (1T), while also achieving a 96.1% acceptance rate (123/128 submissions) on recent unseen LeetCode weekly and biweekly contests from April–May 2026, and reaching the performance range of top-tier frontier reasoning systems including Qwen3.6 Plus and Gemini 3 Pro on verifiable reasoning benchmarks. Inference is recommended via vLLM or SGLang with temperature 1.0, top_p 0.95, and supports up to 102K output tokens, making it best suited for competitive mathematics, coding contests, and STEM reasoning tasks where clear verification signals exist, while larger general-purpose models remain preferable for broad open-domain knowledge tasks. + +## Model Files + + File Name | Quant Type | File Size | File Link | + |-----------|------------|-----------|-----------| + | VibeThinker-3B.BF16.gguf | BF16 | 6.18 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.BF16.gguf) | + | VibeThinker-3B.F16.gguf | F16 | 6.18 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.F16.gguf) | + | VibeThinker-3B.F32.gguf | F32 | 12.3 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.F32.gguf) | + | VibeThinker-3B.Q2_K.gguf | Q2_K | 1.27 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q2_K.gguf) | + | VibeThinker-3B.Q3_K_L.gguf | Q3_K_L | 1.71 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q3_K_L.gguf) | + | VibeThinker-3B.Q3_K_M.gguf | Q3_K_M | 1.59 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q3_K_M.gguf) | + | VibeThinker-3B.Q3_K_S.gguf | Q3_K_S | 1.45 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q3_K_S.gguf) | + | VibeThinker-3B.Q4_0.gguf | Q4_0 | 1.82 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q4_0.gguf) | + | VibeThinker-3B.Q4_K_M.gguf | Q4_K_M | 1.93 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q4_K_M.gguf) | + | VibeThinker-3B.Q4_K_S.gguf | Q4_K_S | 1.83 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q4_K_S.gguf) | + | VibeThinker-3B.Q5_0.gguf | Q5_0 | 2.17 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q5_0.gguf) | + | VibeThinker-3B.Q5_K_M.gguf | Q5_K_M | 2.22 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q5_K_M.gguf) | + | VibeThinker-3B.Q5_K_S.gguf | Q5_K_S | 2.17 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q5_K_S.gguf) | + | VibeThinker-3B.Q6_K.gguf | Q6_K | 2.54 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q6_K.gguf) | + | VibeThinker-3B.Q8_0.gguf | Q8_0 | 3.29 GB | [Download](https://huggingface.co/prithivMLmods/VibeThinker-3B-GGUF/blob/main/VibeThinker-3B.Q8_0.gguf) | + +## llama.cpp + +LLM inference in C/C++ — https://github.com/ggml-org/llama.cpp \ No newline at end of file diff --git a/VibeThinker-3B.BF16.gguf b/VibeThinker-3B.BF16.gguf new file mode 100644 index 0000000..6583ab1 --- /dev/null +++ b/VibeThinker-3B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79805a9e6f748890d82f3865165a31b60584149785ac01d3ae84bffc840e829f +size 6178316992 diff --git a/VibeThinker-3B.F16.gguf b/VibeThinker-3B.F16.gguf new file mode 100644 index 0000000..6ecf2ca --- /dev/null +++ b/VibeThinker-3B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3f4915a20150686489b88757ab1f2186fbe6dedd012aba58aa8bce8eda2c95 +size 6178316992 diff --git a/VibeThinker-3B.F32.gguf b/VibeThinker-3B.F32.gguf new file mode 100644 index 0000000..318f3da --- /dev/null +++ b/VibeThinker-3B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc44afd2ff26937ae2e953691de648c2f6c3ceddc0b82939c3d5d3c2c4848f3 +size 12349711040 diff --git a/VibeThinker-3B.Q2_K.gguf b/VibeThinker-3B.Q2_K.gguf new file mode 100644 index 0000000..86e06b3 --- /dev/null +++ b/VibeThinker-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f70afd49998bc405ac20d0e922f24d79c6cb2db9df4bcdc978127e8697b33cb0 +size 1274755776 diff --git a/VibeThinker-3B.Q3_K_L.gguf b/VibeThinker-3B.Q3_K_L.gguf new file mode 100644 index 0000000..213ef20 --- /dev/null +++ b/VibeThinker-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1309251fb8d108d94d2aa992984a7b67f37cfc1a1ce4efb578842fdbb252e562 +size 1707391680 diff --git a/VibeThinker-3B.Q3_K_M.gguf b/VibeThinker-3B.Q3_K_M.gguf new file mode 100644 index 0000000..2fd2600 --- /dev/null +++ b/VibeThinker-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1897d2373d7b040a95d8dd068942e1ea9c27c012e63bb73de4a1658b4790dc50 +size 1590475456 diff --git a/VibeThinker-3B.Q3_K_S.gguf b/VibeThinker-3B.Q3_K_S.gguf new file mode 100644 index 0000000..e574457 --- /dev/null +++ b/VibeThinker-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd9738075d6fb586456560e3cd49d3a72633a8fc4e89fdb9cc14b0ba90723b9c +size 1454357184 diff --git a/VibeThinker-3B.Q4_0.gguf b/VibeThinker-3B.Q4_0.gguf new file mode 100644 index 0000000..8cffc86 --- /dev/null +++ b/VibeThinker-3B.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1da69e3540a89770216903ccd46ce90adf2bc37594f61e9e9c31fbd34f5e8fa +size 1822849728 diff --git a/VibeThinker-3B.Q4_K_M.gguf b/VibeThinker-3B.Q4_K_M.gguf new file mode 100644 index 0000000..75f1260 --- /dev/null +++ b/VibeThinker-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9782b918cc220fb81d59e21be3e45c3ae027e5d86fb56ce7c6d537a347c80d79 +size 1929902784 diff --git a/VibeThinker-3B.Q4_K_S.gguf b/VibeThinker-3B.Q4_K_S.gguf new file mode 100644 index 0000000..ee15604 --- /dev/null +++ b/VibeThinker-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcc81ef26ed8ec57e2fbd5053e98ab13dd050e0f7c5ecb630cc8a97f4bd0a444 +size 1834384064 diff --git a/VibeThinker-3B.Q5_0.gguf b/VibeThinker-3B.Q5_0.gguf new file mode 100644 index 0000000..a0c2e8c --- /dev/null +++ b/VibeThinker-3B.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1a91fec78fce193666e0a04c0dd2b4bf7af6383bc92a1602345a3aad7091f1 +size 2169666240 diff --git a/VibeThinker-3B.Q5_K_M.gguf b/VibeThinker-3B.Q5_K_M.gguf new file mode 100644 index 0000000..d532018 --- /dev/null +++ b/VibeThinker-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab12e99c894e26a1d780b578068ffa068fd78dc12d289462b60ef96f94ae4c3 +size 2224814784 diff --git a/VibeThinker-3B.Q5_K_S.gguf b/VibeThinker-3B.Q5_K_S.gguf new file mode 100644 index 0000000..e377837 --- /dev/null +++ b/VibeThinker-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3b26e96505618104c2c7da8b729395bda5ae441951673c5b96540265836d7f +size 2169666240 diff --git a/VibeThinker-3B.Q6_K.gguf b/VibeThinker-3B.Q6_K.gguf new file mode 100644 index 0000000..a435baf --- /dev/null +++ b/VibeThinker-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0895a93b7c81d67a9d3a3cff535fa0a03c6e114f6de2a864949559edc6957f80 +size 2538158784 diff --git a/VibeThinker-3B.Q8_0.gguf b/VibeThinker-3B.Q8_0.gguf new file mode 100644 index 0000000..3951771 --- /dev/null +++ b/VibeThinker-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e80bce863fedd7df3dfa05c2f6d052f3e9dface2139bd4b4239baedea64520e +size 3285476032 diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file