commit ecac3e79dbc037d717d0f8d2a8b0350889daf46d Author: ModelHub XC Date: Thu Oct 8 11:40:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/OpenRHO-2B-Thinker-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.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 +*.gguf* 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 \ No newline at end of file diff --git a/OpenRHO-2B-Thinker.BF16.gguf b/OpenRHO-2B-Thinker.BF16.gguf new file mode 100644 index 0000000..2b84647 --- /dev/null +++ b/OpenRHO-2B-Thinker.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276f4437cf673665fe7ee6f1208ae2e67ae2a87210423c4286c50052fedf7f03 +size 3560415968 diff --git a/OpenRHO-2B-Thinker.F16.gguf b/OpenRHO-2B-Thinker.F16.gguf new file mode 100644 index 0000000..b48e682 --- /dev/null +++ b/OpenRHO-2B-Thinker.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c3ad5800951bb25dab1b3230fee9777a5ab649edbb55a98b8bc69df14022bd +size 3560415968 diff --git a/OpenRHO-2B-Thinker.F32.gguf b/OpenRHO-2B-Thinker.F32.gguf new file mode 100644 index 0000000..187e580 --- /dev/null +++ b/OpenRHO-2B-Thinker.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7463806a0efaa916da5e18f477e77651b6e048b6fa9710a99456251f1676217e +size 7114302176 diff --git a/OpenRHO-2B-Thinker.Q2_K.gguf b/OpenRHO-2B-Thinker.Q2_K.gguf new file mode 100644 index 0000000..0067efe --- /dev/null +++ b/OpenRHO-2B-Thinker.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:954ef379d973a0f483e5240034f1da3dccbbb00fcb5e2450a13fbb5d6d1a6176 +size 752879840 diff --git a/OpenRHO-2B-Thinker.Q3_K_M.gguf b/OpenRHO-2B-Thinker.Q3_K_M.gguf new file mode 100644 index 0000000..530b3a5 --- /dev/null +++ b/OpenRHO-2B-Thinker.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1af8f9db0220e8bb0799625bace4532321024ed1655bfed09c04581e871a2a +size 924455648 diff --git a/OpenRHO-2B-Thinker.Q4_K_M.gguf b/OpenRHO-2B-Thinker.Q4_K_M.gguf new file mode 100644 index 0000000..68f023c --- /dev/null +++ b/OpenRHO-2B-Thinker.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a194b0766b95c70d4671cf490cd0b5d3e3054b3fad54e4ee66c5a8091db3f052 +size 1117320416 diff --git a/OpenRHO-2B-Thinker.Q4_K_S.gguf b/OpenRHO-2B-Thinker.Q4_K_S.gguf new file mode 100644 index 0000000..6c0f960 --- /dev/null +++ b/OpenRHO-2B-Thinker.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7037928d8599787d4d879d5af8cad4620afa00888dc1ced86a24bb4a428b7522 +size 1071584480 diff --git a/OpenRHO-2B-Thinker.Q5_K_M.gguf b/OpenRHO-2B-Thinker.Q5_K_M.gguf new file mode 100644 index 0000000..02ad564 --- /dev/null +++ b/OpenRHO-2B-Thinker.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b2d159ece1382c3851dc46fc82a755af251666a2d637a0c78469e433b30fefa +size 1285493984 diff --git a/OpenRHO-2B-Thinker.Q5_K_S.gguf b/OpenRHO-2B-Thinker.Q5_K_S.gguf new file mode 100644 index 0000000..775d8a9 --- /dev/null +++ b/OpenRHO-2B-Thinker.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cba0d1787ab901caf27382fd246002dff90531bc8cc1745ed5a33c3069f706e +size 1259173088 diff --git a/OpenRHO-2B-Thinker.Q6_K.gguf b/OpenRHO-2B-Thinker.Q6_K.gguf new file mode 100644 index 0000000..136033c --- /dev/null +++ b/OpenRHO-2B-Thinker.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e062d733eb8272cd5e195d9a3f3560ab3c7fe46c5103874e1b8eec6cf92dd7ac +size 1464178400 diff --git a/OpenRHO-2B-Thinker.Q8_0.gguf b/OpenRHO-2B-Thinker.Q8_0.gguf new file mode 100644 index 0000000..f2187ae --- /dev/null +++ b/OpenRHO-2B-Thinker.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68b6aee24a279b38430ca3d736fa404315af52a4e8ceeca4ff30682a45ac5fb9 +size 1894531808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec9b03d --- /dev/null +++ b/README.md @@ -0,0 +1,60 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- prithivMLmods/OpenRHO-2B-Thinker +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +--- + +# **OpenRHO-2B-Thinker-GGUF** + +> **OpenRHO-2B-Thinker** is a **general-purpose reasoning model** designed to enhance the cognitive abilities of **edge-deployed large language models (LLMs)** through **reinforcement learning (RL)**. Fine-tuned from **Qwen2-1.5B-Instruct** using the **QwQ distill dataset**, it delivers refined improvements in logical reasoning, structured problem-solving, and lightweight coding — making it highly efficient for **resource-constrained environments**. + +## Model Files + +| File Name | Size | Quantization | Format | Description | +| -------------------------------- | ------- | ------------ | ------ | ----------------------------- | +| `OpenRHO-2B-Thinker.BF16.gguf` | 3.56 GB | BF16 | GGUF | BFloat16 precision version | +| `OpenRHO-2B-Thinker.F16.gguf` | 3.56 GB | FP16 | GGUF | Float16 precision version | +| `OpenRHO-2B-Thinker.F32.gguf` | 7.11 GB | FP32 | GGUF | Float32 precision version | +| `OpenRHO-2B-Thinker.Q2_K.gguf` | 753 MB | Q2\_K | GGUF | 2-bit quantized (K variant) | +| `OpenRHO-2B-Thinker.Q3_K_M.gguf` | 924 MB | Q3\_K\_M | GGUF | 3-bit quantized (K M variant) | +| `OpenRHO-2B-Thinker.Q4_K_M.gguf` | 1.12 GB | Q4\_K\_M | GGUF | 4-bit quantized (K M variant) | +| `OpenRHO-2B-Thinker.Q4_K_S.gguf` | 1.07 GB | Q4\_K\_S | GGUF | 4-bit quantized (K S variant) | +| `OpenRHO-2B-Thinker.Q5_K_M.gguf` | 1.29 GB | Q5\_K\_M | GGUF | 5-bit quantized (K M variant) | +| `OpenRHO-2B-Thinker.Q5_K_S.gguf` | 1.26 GB | Q5\_K\_S | GGUF | 5-bit quantized (K S variant) | +| `OpenRHO-2B-Thinker.Q6_K.gguf` | 1.46 GB | Q6\_K | GGUF | 6-bit quantized (K variant) | +| `OpenRHO-2B-Thinker.Q8_0.gguf` | 1.89 GB | Q8\_0 | GGUF | 8-bit quantized | +| `.gitattributes` | 2.24 kB | — | — | Git LFS tracking file | +| `config.json` | 31 B | — | — | Configuration file | +| `README.md` | 670 B | — | — | Model documentation | + +--- + +## Quants Usage + +(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/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.Q8_0.gguf) | Q8_0 | 0.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B.f16.gguf) | f16 | 1.6 | 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) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..abb5987 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen2" +} \ No newline at end of file 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