commit fad9f7982716f738da9b7c0b288486653ee771cc Author: ModelHub XC Date: Tue May 26 05:46:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a853706 --- /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 +GRAM-LLaMA3.2-3B-RewardModel.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-LLaMA3.2-3B-RewardModel.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRAM-LLaMA3.2-3B-RewardModel.IQ4_XS.gguf b/GRAM-LLaMA3.2-3B-RewardModel.IQ4_XS.gguf new file mode 100644 index 0000000..8fb688a --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3d1fdf69a5910fca796b3c4f97f2b770ea5d239789627cd8173a30a9d1e3f44 +size 1840907296 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf new file mode 100644 index 0000000..8f08078 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7e5c1a8b8f90cfc93582415d221d84b30f9333ffe13208d66acac41d0e70c5 +size 1363936288 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf new file mode 100644 index 0000000..1c41323 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c847e52adbe3e8a88e7dd57ac87a723b99b67b33e7bd326f160edc8b1eccc38e +size 1815348256 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf new file mode 100644 index 0000000..e260523 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:883fc34645164d12ef1fa7562dfa09a44ce306e9eef11a91858b1598f3f01fe5 +size 1687159840 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf new file mode 100644 index 0000000..706225b --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4478564d5827a6b054e4af3f81d018a1453f0be80e440378939485bd097f1026 +size 1542849568 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf new file mode 100644 index 0000000..fcdd5e8 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a768edc5cf15facf25df5055be5bf18c61230a933841884aa2b173cba14ebc88 +size 2019378208 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf new file mode 100644 index 0000000..90905c1 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6146d46946542d003d3440c03e2b3030bf6d886ea4ba2a24cc6cf67fbe842531 +size 1928201248 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf new file mode 100644 index 0000000..5fc6382 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:878b58ff70ad3a58126722a40a46395aab8ca37fd712c3f624063a662cd5350a +size 2322154528 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf new file mode 100644 index 0000000..81f3267 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38327c39386c9cdc92eb284eca7b116b565f613cff5555a4a8fd5336cf6c0481 +size 2269512736 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf new file mode 100644 index 0000000..80e8613 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7285f41b0edf19693802f7e5aeb308dad03515bc11a85e791cbf36b8c8fef2ee +size 2643854368 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf b/GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf new file mode 100644 index 0000000..cd9c71c --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e759bd1eb15887c43b00ffa4e6892951a0e1c2da3920629b15ad4b8404eb5c2c +size 3421899808 diff --git a/GRAM-LLaMA3.2-3B-RewardModel.f16.gguf b/GRAM-LLaMA3.2-3B-RewardModel.f16.gguf new file mode 100644 index 0000000..d858a06 --- /dev/null +++ b/GRAM-LLaMA3.2-3B-RewardModel.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36002856b7f0b260f69aac6bfc590139b25c51bca37be81eb293b330afa3eaf5 +size 6433688608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c96d154 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: NiuTrans/GRAM-LLaMA3.2-3B-RewardModel +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- rewardmodel +- GRAM +- RLHF +- reward +--- +## About + + + + + + + + + +static quants of https://huggingface.co/NiuTrans/GRAM-LLaMA3.2-3B-RewardModel + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRAM-LLaMA3.2-3B-RewardModel-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-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/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-LLaMA3.2-3B-RewardModel-GGUF/resolve/main/GRAM-LLaMA3.2-3B-RewardModel.f16.gguf) | f16 | 6.5 | 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. + +