commit c2521137e3c7e82027a6b73377808066f3dbfb8b Author: ModelHub XC Date: Sat Jun 13 19:10:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4c6e16 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.f16.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b9a9c0c --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/dreamgen-preview/opus-v1.2-llama-3-8b-base-run3.4-epoch2 + + +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/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/opus-v1.2-llama-3-8b-base-run3.4-epoch2-GGUF/resolve/main/opus-v1.2-llama-3-8b-base-run3.4-epoch2.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/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_M.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_M.gguf new file mode 100644 index 0000000..c121f48 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb32b80e9aeac41b5175af6bf21834a43d5b2b09087f6ae5ee4234ccbf905cc +size 3785335744 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_S.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_S.gguf new file mode 100644 index 0000000..86d1ae5 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a2ce6eaef9cb99699c5880037bda859d2b500a32d9e87f73f68ce8110642ce +size 3682837440 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_XS.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_XS.gguf new file mode 100644 index 0000000..6bbe235 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0640d8567d877091af97c94c600e2cc4189c28df45fae2f432aa88a8183a5863 +size 3519259584 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ4_XS.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ4_XS.gguf new file mode 100644 index 0000000..785189d --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d33019eb66542ff7906f9e7a50fd43e70801ac6b77ec8c780bdc7eaa61c25053 +size 4484875200 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q2_K.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q2_K.gguf new file mode 100644 index 0000000..b2a5e22 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9a808bac14b8d447fb9decfdfffc2da9f606014ade67f6870099c236a74916 +size 3179643840 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_L.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_L.gguf new file mode 100644 index 0000000..12dcaed --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aada2b8f69d20c3f5cf5d8aec195fe47dff8ad5dc448415a3971f461073070f +size 4322468800 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_M.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_M.gguf new file mode 100644 index 0000000..1709db1 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffffb741a637066c45e1e63474fb285c04278d8eaf05a2f1dcdab4741dc46cf +size 4019430336 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_S.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_S.gguf new file mode 100644 index 0000000..febb6a4 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf81adb7b9707336cdddb9039f342aa7693582bc09eca4b53a58d7b1b559f886 +size 3665011648 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_M.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_M.gguf new file mode 100644 index 0000000..cb7a545 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3553b1d95db8b73f5c008a9dcc43ac8a607ffc40e113b07c470d14df8591b185 +size 4921246656 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_S.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_S.gguf new file mode 100644 index 0000000..87f3205 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e659b4f4ab43606bf6ae5c4fb5b37bd60067ce6ef5f5099a86b83eca9421630f +size 4693181376 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_M.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_M.gguf new file mode 100644 index 0000000..eb2ae8d --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ea5426450a1e8da8c181d1f7263748d1cc0a44a5d1bfb46010cb1d92fa6bd9 +size 5733499840 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_S.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_S.gguf new file mode 100644 index 0000000..ba64f7c --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a32c8f6f7eb9aa95d22cfcf2381b2c6d443962aad24b9314af6f5e24f6a500 +size 5599806400 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q6_K.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q6_K.gguf new file mode 100644 index 0000000..356f637 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74893b4c22dc2bc3eae9dbd2aabf1bf3443edb60a7ce8e4353bd6ed3572a219 +size 6596518848 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q8_0.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q8_0.gguf new file mode 100644 index 0000000..398c547 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa3787d0145becc4f17094e7cde658b045c45f5758b562a2f975cb5693d179b +size 8541283264 diff --git a/opus-v1.2-llama-3-8b-base-run3.4-epoch2.f16.gguf b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.f16.gguf new file mode 100644 index 0000000..bdf15b9 --- /dev/null +++ b/opus-v1.2-llama-3-8b-base-run3.4-epoch2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f9b2019484851c26e61bc94c59947f36114732ab81c2c6375d73545e75585f +size 16069403584