commit b7fd27b37a37db4577be61d4b6ed61b0e0769ee7 Author: ModelHub XC Date: Sat May 30 20:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5312f96 --- /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 +OpenAssisted-English-Meta_3_1_8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenAssisted-English-Meta_3_1_8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenAssisted-English-Meta_3_1_8B.IQ4_XS.gguf b/OpenAssisted-English-Meta_3_1_8B.IQ4_XS.gguf new file mode 100644 index 0000000..7c333ca --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1a65f49348b80f660c34e0b8669dcc1bd0515dab7f3befe0b8cc70d3363f900 +size 4484367744 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q2_K.gguf b/OpenAssisted-English-Meta_3_1_8B.Q2_K.gguf new file mode 100644 index 0000000..25ff882 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72b59faa9e8f8e80d8709ed0ca8702da542b59d48f2ab93d6e825714ea8dafb +size 3179136384 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q3_K_L.gguf b/OpenAssisted-English-Meta_3_1_8B.Q3_K_L.gguf new file mode 100644 index 0000000..bc232c5 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f346752659b8b64febb91f0050af6d3535f63390343c6a9c2787455362f883cc +size 4321961344 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q3_K_M.gguf b/OpenAssisted-English-Meta_3_1_8B.Q3_K_M.gguf new file mode 100644 index 0000000..3e57cbd --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9840dcdfe44eec4ddac617055f7e50c16d09a45e16356a0656e6e10245a0ee91 +size 4018922880 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q3_K_S.gguf b/OpenAssisted-English-Meta_3_1_8B.Q3_K_S.gguf new file mode 100644 index 0000000..df0e42b --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f6a8e0abeb8eee3b35a11cb94dd473550fc0b201c1c27a4ade64d65227f6cc5 +size 3664504192 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q4_K_M.gguf b/OpenAssisted-English-Meta_3_1_8B.Q4_K_M.gguf new file mode 100644 index 0000000..befa431 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9594693be730a7af92b65fbd66627c90af678c38bad07f65d6df1cd1452b7922 +size 4920739200 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q4_K_S.gguf b/OpenAssisted-English-Meta_3_1_8B.Q4_K_S.gguf new file mode 100644 index 0000000..5fe430c --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06c3e1f87d48ac2a50db594005d57569e1d68cc56a189c68ae7aab5aa029ca30 +size 4692673920 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q5_K_M.gguf b/OpenAssisted-English-Meta_3_1_8B.Q5_K_M.gguf new file mode 100644 index 0000000..44aec4c --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1352e8dc66c2f038a22c8e041f29168c3ebb5e62135eec5d30206963a6f7daa0 +size 5732992384 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q5_K_S.gguf b/OpenAssisted-English-Meta_3_1_8B.Q5_K_S.gguf new file mode 100644 index 0000000..af1a924 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ba26d1b613da88868f189a3030a196858e29024d7a87b9c8261646848d2e331 +size 5599298944 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q6_K.gguf b/OpenAssisted-English-Meta_3_1_8B.Q6_K.gguf new file mode 100644 index 0000000..d138a05 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf3c9b04f6e7a8e9053e8ee6dc86792019f3e57abf59f6486b67c32eeda3fff5 +size 6596011392 diff --git a/OpenAssisted-English-Meta_3_1_8B.Q8_0.gguf b/OpenAssisted-English-Meta_3_1_8B.Q8_0.gguf new file mode 100644 index 0000000..c82b6b6 --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:554d77081ad852af463fc7896c3eeb9933e801d064d7835e38e73942fbdccd5a +size 8540775808 diff --git a/OpenAssisted-English-Meta_3_1_8B.f16.gguf b/OpenAssisted-English-Meta_3_1_8B.f16.gguf new file mode 100644 index 0000000..2030edb --- /dev/null +++ b/OpenAssisted-English-Meta_3_1_8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbfd718045af42214d733b682b2c65bc80fddb473e5865417f71e2682ba85c43 +size 16068896128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cc9d8d8 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Akshaykumarbm/OpenAssisted-English-Meta_3_1_8B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Akshaykumarbm/OpenAssisted-English-Meta_3_1_8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenAssisted-English-Meta_3_1_8B-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/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenAssisted-English-Meta_3_1_8B-GGUF/resolve/main/OpenAssisted-English-Meta_3_1_8B.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. + +