commit af03083d71b513a3b981492299eb6975f0f49e09 Author: ModelHub XC Date: Sun May 24 19:06:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/R-PRM-7B-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b91e63f --- /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 +R-PRM-7B-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +R-PRM-7B-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/R-PRM-7B-DPO.IQ4_XS.gguf b/R-PRM-7B-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..963b390 --- /dev/null +++ b/R-PRM-7B-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ee276a4449de75908b5bc43bdbbe8831c00349871658d9f775e63c28f4107f +size 4250298912 diff --git a/R-PRM-7B-DPO.Q2_K.gguf b/R-PRM-7B-DPO.Q2_K.gguf new file mode 100644 index 0000000..3e68f55 --- /dev/null +++ b/R-PRM-7B-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86438ce5a831df481118c0767c5231788bc0244ec80afdb55d31ce55cfadd260 +size 3015940640 diff --git a/R-PRM-7B-DPO.Q3_K_L.gguf b/R-PRM-7B-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..b1cf092 --- /dev/null +++ b/R-PRM-7B-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caec9d7243db398a2fdf688e6607b3142658083dfa2df045dc2ba9c055751caa +size 4088459808 diff --git a/R-PRM-7B-DPO.Q3_K_M.gguf b/R-PRM-7B-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..1518bee --- /dev/null +++ b/R-PRM-7B-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8b422cdc05bdf626d12f93ef9433c7912683deec4c438862ae71c0de2b7fac +size 3808391712 diff --git a/R-PRM-7B-DPO.Q3_K_S.gguf b/R-PRM-7B-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..db81b15 --- /dev/null +++ b/R-PRM-7B-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286f5edd5dedb13cc564de0b629ab43bb8cbe7ea475a7af76de2ba26e55edcfc +size 3492368928 diff --git a/R-PRM-7B-DPO.Q4_K_M.gguf b/R-PRM-7B-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..8edc604 --- /dev/null +++ b/R-PRM-7B-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44a2bc4ee4e83a4156d0bbf1f74289923549ec162aa5ce250433e2cb3ffd3abb +size 4683074080 diff --git a/R-PRM-7B-DPO.Q4_K_S.gguf b/R-PRM-7B-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..cdd90a0 --- /dev/null +++ b/R-PRM-7B-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f27d23dfa1f24aaf51623b03c11129457568d74edc2d1ef89c27d0b7ec3c3ba2 +size 4457769504 diff --git a/R-PRM-7B-DPO.Q5_K_M.gguf b/R-PRM-7B-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..0298c97 --- /dev/null +++ b/R-PRM-7B-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0a7424587445c5cbd60f3b4232cba5915db0232f567964be3f24fb4a2ba4f2c +size 5444831776 diff --git a/R-PRM-7B-DPO.Q5_K_S.gguf b/R-PRM-7B-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..bfe46d3 --- /dev/null +++ b/R-PRM-7B-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43984dc74270e8346e95283c0ed4bfe69485f6e1f80cbf00c2b9b6a77382b763 +size 5315176992 diff --git a/R-PRM-7B-DPO.Q6_K.gguf b/R-PRM-7B-DPO.Q6_K.gguf new file mode 100644 index 0000000..3e61bbe --- /dev/null +++ b/R-PRM-7B-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e807f46863612035c22b4b36e96c21542d4e39f8dd3929a605b24adc2ea3ca3 +size 6254199328 diff --git a/R-PRM-7B-DPO.Q8_0.gguf b/R-PRM-7B-DPO.Q8_0.gguf new file mode 100644 index 0000000..934090f --- /dev/null +++ b/R-PRM-7B-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:725936c491c8e576dc0403a2ee86060078bb155949f7f2bbf8855838dc9902af +size 8098525728 diff --git a/R-PRM-7B-DPO.f16.gguf b/R-PRM-7B-DPO.f16.gguf new file mode 100644 index 0000000..2cba97b --- /dev/null +++ b/R-PRM-7B-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e21043004d4d2c709f733a23fd75631da0c99de90dba8200cd3855be5ab81d +size 15237853728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..18e22f7 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: kevinpro/R-PRM-7B-DPO +language: zh +library_name: transformers +license: apache-2.0 +model_name: R-PRM-7B-DPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reinforcement-learning +- reward-model +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/kevinpro/R-PRM-7B-DPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#R-PRM-7B-DPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/R-PRM-7B-DPO-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/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/R-PRM-7B-DPO-GGUF/resolve/main/R-PRM-7B-DPO.f16.gguf) | f16 | 15.3 | 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. + +