commit 43aa701c3fb0b60debe7c424136aa271949d0f4a Author: ModelHub XC Date: Wed Sep 16 05:29:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/RAFT-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1e10168 --- /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 +RAFT-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RAFT-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/RAFT-1.5B.IQ4_XS.gguf b/RAFT-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..4147530 --- /dev/null +++ b/RAFT-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fcca8f72aaaa92d5dd680df6ccf16d40a9df1bfc9272504637312d80be0035 +size 1026163232 diff --git a/RAFT-1.5B.Q2_K.gguf b/RAFT-1.5B.Q2_K.gguf new file mode 100644 index 0000000..8d9eb14 --- /dev/null +++ b/RAFT-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22031d44518113cac2a42021b2dcebcef51528a1f182fa8b62f4b5e1b5bcd1e4 +size 752881184 diff --git a/RAFT-1.5B.Q3_K_L.gguf b/RAFT-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..e1252c3 --- /dev/null +++ b/RAFT-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a15e9593265fe55250131fa14f891c1ee5d3fadf97a204f5c30709f00653c7 +size 980441120 diff --git a/RAFT-1.5B.Q3_K_M.gguf b/RAFT-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..c319dfd --- /dev/null +++ b/RAFT-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1554d3ba17c949cbc1d0cf03b178aa8ba85f88240d278609e1d33d57b99a3679 +size 924456992 diff --git a/RAFT-1.5B.Q3_K_S.gguf b/RAFT-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..33c1e13 --- /dev/null +++ b/RAFT-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2530774128fe8d0131b12c58c25f44710de79495601be4d3ddd14912e22b9b44 +size 861222944 diff --git a/RAFT-1.5B.Q4_K_M.gguf b/RAFT-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..56c200c --- /dev/null +++ b/RAFT-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:997a1503a445b2a4c8be6bf0190bd879c5fa1359f22f1c18f2eab8525f161b05 +size 1117321760 diff --git a/RAFT-1.5B.Q4_K_S.gguf b/RAFT-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..98dcfec --- /dev/null +++ b/RAFT-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aadcb224295735dffee5e364c999bd3f61a04564c822ca4d0208af6e9f6d9e9 +size 1071585824 diff --git a/RAFT-1.5B.Q5_K_M.gguf b/RAFT-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..9464072 --- /dev/null +++ b/RAFT-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbe00967a112c95c570abfb917b26df9320f6e4b5392db298a9fae02e00e90d +size 1285495328 diff --git a/RAFT-1.5B.Q5_K_S.gguf b/RAFT-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..1fea010 --- /dev/null +++ b/RAFT-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93546821c49891b2acf2c13d674b1bdb860a08ae0d4c4c05cdd8de4cd48c2d7c +size 1259174432 diff --git a/RAFT-1.5B.Q6_K.gguf b/RAFT-1.5B.Q6_K.gguf new file mode 100644 index 0000000..168c80b --- /dev/null +++ b/RAFT-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c72379cbe062126ded4b5b26b405f250eb1f2791c70ccee2dc89973ec51d2837 +size 1464179744 diff --git a/RAFT-1.5B.Q8_0.gguf b/RAFT-1.5B.Q8_0.gguf new file mode 100644 index 0000000..2bc593d --- /dev/null +++ b/RAFT-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec97d944086a0b28eeed15ab0d5fabfec3d60dea5bcdb10f6a219a5470580e04 +size 1894533152 diff --git a/RAFT-1.5B.f16.gguf b/RAFT-1.5B.f16.gguf new file mode 100644 index 0000000..a7c4662 --- /dev/null +++ b/RAFT-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a690f7db696b13e361c77dc459ed16258d0b99b09e21e12b5f155586b5f4c22c +size 3560417312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..050061f --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: INSAIT-Institute/RAFT-1.5B +datasets: +- INSAIT-Institute/Aletheia-Train +language: +- en +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code +- code-verification +- rlvr +- raft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/INSAIT-Institute/RAFT-1.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RAFT-1.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/RAFT-1.5B-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/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RAFT-1.5B-GGUF/resolve/main/RAFT-1.5B.f16.gguf) | f16 | 3.7 | 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. + +