commit cfae851b137662d3cafc7ceed58f833700aa6ab7 Author: ModelHub XC Date: Sat Jun 13 14:58:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRM-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2cdc47 --- /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 +GRM-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRM-7b.IQ4_XS.gguf b/GRM-7b.IQ4_XS.gguf new file mode 100644 index 0000000..afc5022 --- /dev/null +++ b/GRM-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6098c6d5ce2c7e523ff51d32c65f0b24b8a3371e5c3074a936412be011ae7ad6 +size 4250300256 diff --git a/GRM-7b.Q2_K.gguf b/GRM-7b.Q2_K.gguf new file mode 100644 index 0000000..f9fbcf8 --- /dev/null +++ b/GRM-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530943eeb1e062aa0af3789da5b0e07ab2a7d2616ba070c5be1695e604273794 +size 3015941984 diff --git a/GRM-7b.Q3_K_L.gguf b/GRM-7b.Q3_K_L.gguf new file mode 100644 index 0000000..2f92dc3 --- /dev/null +++ b/GRM-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d556856db22939e61520a360b6de733b8be0fbe47f4215dce8259d81bdb08a +size 4088461152 diff --git a/GRM-7b.Q3_K_M.gguf b/GRM-7b.Q3_K_M.gguf new file mode 100644 index 0000000..bfa29aa --- /dev/null +++ b/GRM-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b07fb38718427897e39a14f5b4b919e9ffdffdb902ffb8d40c1da26b3544faa +size 3808393056 diff --git a/GRM-7b.Q3_K_S.gguf b/GRM-7b.Q3_K_S.gguf new file mode 100644 index 0000000..b15bd1c --- /dev/null +++ b/GRM-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9297593ded883c739abeb644000fa89a603dfb46de187b5903ba8722ae1a3469 +size 3492370272 diff --git a/GRM-7b.Q4_K_M.gguf b/GRM-7b.Q4_K_M.gguf new file mode 100644 index 0000000..fe65240 --- /dev/null +++ b/GRM-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e383e0c00d9a599922bf7281261c92fe4221d16716d493ae910f296a2ddaa2 +size 4683075424 diff --git a/GRM-7b.Q4_K_S.gguf b/GRM-7b.Q4_K_S.gguf new file mode 100644 index 0000000..09076b8 --- /dev/null +++ b/GRM-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4385c83707598bd4fbcc0d9349c7307b5be7d75246a31c123594fe1d5768da0 +size 4457770848 diff --git a/GRM-7b.Q5_K_M.gguf b/GRM-7b.Q5_K_M.gguf new file mode 100644 index 0000000..53f0c1e --- /dev/null +++ b/GRM-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d226058ab471697a272e68d7305472f03a022622e38566a04a015345fca2da +size 5444833120 diff --git a/GRM-7b.Q5_K_S.gguf b/GRM-7b.Q5_K_S.gguf new file mode 100644 index 0000000..18368df --- /dev/null +++ b/GRM-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb211a7df761452c037bb389ac1f6731e9b520ee7ece87f6e292e30438f2ca7d +size 5315178336 diff --git a/GRM-7b.Q6_K.gguf b/GRM-7b.Q6_K.gguf new file mode 100644 index 0000000..999fc72 --- /dev/null +++ b/GRM-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7af814b063146b01affee3f61535d3629d2276e8c185aaa7d35e83418e56fae +size 6254200672 diff --git a/GRM-7b.Q8_0.gguf b/GRM-7b.Q8_0.gguf new file mode 100644 index 0000000..d1dc54d --- /dev/null +++ b/GRM-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d881f7080b426742f9486e6377b68eface04ce6dc94d5c1506255fe20046c7 +size 8098527072 diff --git a/GRM-7b.f16.gguf b/GRM-7b.f16.gguf new file mode 100644 index 0000000..b7a22e0 --- /dev/null +++ b/GRM-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e57d76e27d810b298c7cb3ac75bb708a1b17ddde2166a262ac48fe2d00e7d7c +size 15237855072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0d000e --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: OrionLLM/GRM-7b +datasets: +- open-thoughts/OpenThoughts3-1.2M +- nvidia/OpenCodeReasoning-2 +- nvidia/OpenMathReasoning +- OpenMed/Medical-Reasoning-SFT-GPT-OSS-120B-V2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reasoning +- math +- code +- general +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OrionLLM/GRM-7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRM-7b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRM-7b-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/GRM-7b-GGUF/resolve/main/GRM-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-7b-GGUF/resolve/main/GRM-7b.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. + +