commit 5504d0bb6106687f75c31bd4c82e60462cf2e329 Author: ModelHub XC Date: Fri Apr 24 19:58:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/UnifiedReward-qwen-3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1048ffd --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +UnifiedReward-qwen-3b.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +UnifiedReward-qwen-3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cac7af5 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: CodeGoat24/UnifiedReward-qwen-3b +datasets: +- CodeGoat24/HPD +- CodeGoat24/LiFT-HRA +- CodeGoat24/OIP +- CodeGoat24/EvalMuse +- CodeGoat24/ShareGPTVideo-DPO +- CodeGoat24/VideoFeedback +- CodeGoat24/LLaVA-Critic-113k +- CodeGoat24/VideoDPO +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/CodeGoat24/UnifiedReward-qwen-3b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#UnifiedReward-qwen-3b-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/UnifiedReward-qwen-3b-GGUF/resolve/main/UnifiedReward-qwen-3b.f16.gguf) | f16 | 6.3 | 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/UnifiedReward-qwen-3b.IQ4_XS.gguf b/UnifiedReward-qwen-3b.IQ4_XS.gguf new file mode 100644 index 0000000..65d38ea --- /dev/null +++ b/UnifiedReward-qwen-3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9b12ce6ecef703a3850c09f537e97fbe6bd3e19ad69901156e0848e0197d84d +size 1753185600 diff --git a/UnifiedReward-qwen-3b.Q2_K.gguf b/UnifiedReward-qwen-3b.Q2_K.gguf new file mode 100644 index 0000000..98d0bcd --- /dev/null +++ b/UnifiedReward-qwen-3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880a057c05e50daa7e89b0ae7b102e50ad90d97e8d4f2de6024881b6898e688b +size 1274756416 diff --git a/UnifiedReward-qwen-3b.Q3_K_L.gguf b/UnifiedReward-qwen-3b.Q3_K_L.gguf new file mode 100644 index 0000000..d519bc5 --- /dev/null +++ b/UnifiedReward-qwen-3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7ad6e6be403c03fbfb5304330f077425c28d464fcb0c5c2a8d623d35c962b7 +size 1707392320 diff --git a/UnifiedReward-qwen-3b.Q3_K_M.gguf b/UnifiedReward-qwen-3b.Q3_K_M.gguf new file mode 100644 index 0000000..8955df4 --- /dev/null +++ b/UnifiedReward-qwen-3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:957b5c052015e01a73f02013ae71085f5a001e19a9e2e829e369fd37c35d0e5c +size 1590476096 diff --git a/UnifiedReward-qwen-3b.Q3_K_S.gguf b/UnifiedReward-qwen-3b.Q3_K_S.gguf new file mode 100644 index 0000000..db3347c --- /dev/null +++ b/UnifiedReward-qwen-3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:712d5687db0e6e4f252f9fd9e77262245571994d2e826fd4ce2c210249c24195 +size 1454357824 diff --git a/UnifiedReward-qwen-3b.Q4_K_M.gguf b/UnifiedReward-qwen-3b.Q4_K_M.gguf new file mode 100644 index 0000000..81601f2 --- /dev/null +++ b/UnifiedReward-qwen-3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:965b061fc6092c3dcee39d68cfcb6d1e1af3c7f163b4e9f1b7f706150586ebcf +size 1929903424 diff --git a/UnifiedReward-qwen-3b.Q4_K_S.gguf b/UnifiedReward-qwen-3b.Q4_K_S.gguf new file mode 100644 index 0000000..15bad4b --- /dev/null +++ b/UnifiedReward-qwen-3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d832e08c1ce20e9cafbbfa94b626c309379dfbe4ad3d80b3b7d6e46438269b5f +size 1834384704 diff --git a/UnifiedReward-qwen-3b.Q5_K_M.gguf b/UnifiedReward-qwen-3b.Q5_K_M.gguf new file mode 100644 index 0000000..7dccc7d --- /dev/null +++ b/UnifiedReward-qwen-3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0439978939b99e142b8862612988e519a5b745a451fae01d477fcf443192a660 +size 2224815424 diff --git a/UnifiedReward-qwen-3b.Q5_K_S.gguf b/UnifiedReward-qwen-3b.Q5_K_S.gguf new file mode 100644 index 0000000..1d8da50 --- /dev/null +++ b/UnifiedReward-qwen-3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9370a1d568bfb024eca2849e0bffe026c13d421edb244de5e14e70e663148394 +size 2169666880 diff --git a/UnifiedReward-qwen-3b.Q6_K.gguf b/UnifiedReward-qwen-3b.Q6_K.gguf new file mode 100644 index 0000000..ac1aa2f --- /dev/null +++ b/UnifiedReward-qwen-3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f7e18abf0ff0232a59150af4104ed00478dee3408b3f0f5aae8965bcbf79dd +size 2538159424 diff --git a/UnifiedReward-qwen-3b.Q8_0.gguf b/UnifiedReward-qwen-3b.Q8_0.gguf new file mode 100644 index 0000000..277a117 --- /dev/null +++ b/UnifiedReward-qwen-3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b79fc951690668f9d138c933720aa6320173b809a07012c6bd468c5a9a09b97 +size 3285476672 diff --git a/UnifiedReward-qwen-3b.f16.gguf b/UnifiedReward-qwen-3b.f16.gguf new file mode 100644 index 0000000..515b898 --- /dev/null +++ b/UnifiedReward-qwen-3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715e78c2b267550eae4e4527d81088f48ac7fe7c5fd11d0825eaa9730230c3ea +size 6178317632 diff --git a/UnifiedReward-qwen-3b.mmproj-Q8_0.gguf b/UnifiedReward-qwen-3b.mmproj-Q8_0.gguf new file mode 100644 index 0000000..973f16d --- /dev/null +++ b/UnifiedReward-qwen-3b.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a7df38f6f84c54aa5277c816dd29d8c4fef92e96c2aa5d618e8ca33c5a40e3 +size 844759680 diff --git a/UnifiedReward-qwen-3b.mmproj-f16.gguf b/UnifiedReward-qwen-3b.mmproj-f16.gguf new file mode 100644 index 0000000..0425624 --- /dev/null +++ b/UnifiedReward-qwen-3b.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7310c213c7d805acfb84037dd5e9abd9f6eebda49dcf81630e2ea9a867588c +size 1338430080