commit 81e6cb1e25f7bb2c79ccb82654f7153c40441c81 Author: ModelHub XC Date: Sat Oct 17 13:44:23 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed8a4d9 --- /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 +SearchR1-ppo-llama3.1-8b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SearchR1-ppo-llama3.1-8b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b720e46 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: omron-sinicx/SearchR1-ppo-llama3.1-8b-instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/omron-sinicx/SearchR1-ppo-llama3.1-8b-instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SearchR1-ppo-llama3.1-8b-instruct-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/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SearchR1-ppo-llama3.1-8b-instruct-GGUF/resolve/main/SearchR1-ppo-llama3.1-8b-instruct.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. + + diff --git a/SearchR1-ppo-llama3.1-8b-instruct.IQ4_XS.gguf b/SearchR1-ppo-llama3.1-8b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..2071ead --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83519a328929c62f9f3bd9cd2f27ae2910fc1f8851540591f817a59e0ef68524 +size 4484367968 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q2_K.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q2_K.gguf new file mode 100644 index 0000000..f1b1a82 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c37a43bdee235f187463446a137594260cebea2bc3ded915e7fd8b70864f45 +size 3179136608 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_L.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..083194e --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7776e7ce6b4c345e72d51e75105d01fca82eb6e7786f37e459c6730e7b3f1786 +size 4321961568 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_M.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..4848dd0 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be1dcfe87bb03cfda8c1015146bb7534f954f6440128aef8c7efad12cf373b3 +size 4018923104 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_S.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8cd7406 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b1220f04295ab02c6a3bcaf59be62bcc63d1ae9c71e062930608c8462d08f6 +size 3664504416 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_M.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..c54c05d --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:055d1c2e1b28b22da7c2d6133140de9a6c2988a146d80c996a36977255b7d574 +size 4920739424 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_S.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..bf71561 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81e580b06fff04559aeb273c58271be417bf85fb34c5be9c78f8b31ffe1af490 +size 4692674144 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_M.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..b487e63 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab024f9a1ccaaa89fe6abd316f9188dad8fd673a080550610acfefb597b71ef3 +size 5732992608 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_S.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..e7ce21f --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e4288ff8322ef4632057ed0745be57ead1e633308a5146902a124ed9404800 +size 5599299168 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q6_K.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q6_K.gguf new file mode 100644 index 0000000..a2a0787 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4cf41a5d8e13368e6b12ad1fcdb629d1b9c9bb77fcc4fa896b0d357e138057 +size 6596011616 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.Q8_0.gguf b/SearchR1-ppo-llama3.1-8b-instruct.Q8_0.gguf new file mode 100644 index 0000000..ab56fe7 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5bf1bf33162cd72e89baec3cdb94d7f0efb6b3303acf43389418700cce0c71 +size 8540776032 diff --git a/SearchR1-ppo-llama3.1-8b-instruct.f16.gguf b/SearchR1-ppo-llama3.1-8b-instruct.f16.gguf new file mode 100644 index 0000000..f260e20 --- /dev/null +++ b/SearchR1-ppo-llama3.1-8b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06ccf6d27c51e1f220b0d3e54d5ee223040c03f7d26e41be054ee20f96aa243c +size 16068896352