commit e30c890ade83fcc4b26f9b4cdf982ddb7d1fd0ec Author: ModelHub XC Date: Thu Aug 20 08:37:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4263b84 --- /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-RR-LLaMA-3.1-8B-RewardModel.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAM-RR-LLaMA-3.1-8B-RewardModel.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.IQ4_XS.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.IQ4_XS.gguf new file mode 100644 index 0000000..0973867 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc630914e7b22a199e012ecf7de88ec8cb3f28c26971a695f75e43085cf1ccc +size 4484368416 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q2_K.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q2_K.gguf new file mode 100644 index 0000000..c7994de --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84a0b43a54179a6106341f7dce131d92ba399cfed891bf5b07861745aec06cb +size 3179137056 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_L.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_L.gguf new file mode 100644 index 0000000..9a75bf9 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebb6cc2bb9fc8791fb76b3d10f7687a68710ea531e81b645707ad1c0e82bc30 +size 4321962016 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_M.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_M.gguf new file mode 100644 index 0000000..d68bb59 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2459f626f5a29981a1b7a352876761935f4dbe84196e63260a9e96518e2256e +size 4018923552 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_S.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_S.gguf new file mode 100644 index 0000000..83f3ae3 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e84875e357f62e9e0d150909e80bcfd6bc77f33f215593583c52bc927920a2ef +size 3664504864 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_M.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_M.gguf new file mode 100644 index 0000000..e1b5aaf --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ba4d00f45c399cc6d7f0faa7644e4cd0195caf35c44067274daf7c783d2715 +size 4920739872 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_S.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_S.gguf new file mode 100644 index 0000000..ab65139 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7997cc70884de0dc07da4f19da5158209cf7691b9d7d3235783f7c5c758d332f +size 4692674592 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_M.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_M.gguf new file mode 100644 index 0000000..5d11c15 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ea41270e531401c9f17e8f61362d26899576fc0e7d6c307fe4c89021ed222c +size 5732993056 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_S.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_S.gguf new file mode 100644 index 0000000..ffb8a42 --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de18bed36194d267da26ad3fd3549fa88bd37a308cbba88336e9b86a0f779d8 +size 5599299616 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q6_K.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q6_K.gguf new file mode 100644 index 0000000..60ce06a --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e571a92b7314f70ff66e6cab07c987e606c096840e9c65d0968eef567a31cd +size 6596012064 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q8_0.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q8_0.gguf new file mode 100644 index 0000000..a24a9cb --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1293f4fe37e2139f00d8b4039060dfec537302492769c3202ff32bab7b8f081c +size 8540776480 diff --git a/GRAM-RR-LLaMA-3.1-8B-RewardModel.f16.gguf b/GRAM-RR-LLaMA-3.1-8B-RewardModel.f16.gguf new file mode 100644 index 0000000..baffdef --- /dev/null +++ b/GRAM-RR-LLaMA-3.1-8B-RewardModel.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:763a0a7090ec56dd6cf1eb4ebdaa86b48ab64cadc9d4c8e1909ccf10af21e5d3 +size 16068896800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a2f690e --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: wangclnlp/GRAM-RR-LLaMA-3.1-8B-RewardModel +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- Reward +- RewardModel +- RewardReasoning +- Reasoning +- RLHF +- Best-of-N +--- +## About + + + + + + + + + +static quants of https://huggingface.co/wangclnlp/GRAM-RR-LLaMA-3.1-8B-RewardModel + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-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-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRAM-RR-LLaMA-3.1-8B-RewardModel-GGUF/resolve/main/GRAM-RR-LLaMA-3.1-8B-RewardModel.f16.gguf) | f16 | 16.2 | 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. + +