commit 47a4aebcf836e1f32a3ba8dba61e00650b0b0d99 Author: ModelHub XC Date: Sat Aug 8 19:17:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d2aea0 --- /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 +intent-aware-lfqa-qwen3-8b-multiview.f16.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-qwen3-8b-multiview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd28789 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: allenai/intent-aware-lfqa-qwen3-8b-multiview +language: en +library_name: transformers +license: odc-by +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/allenai/intent-aware-lfqa-qwen3-8b-multiview + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#intent-aware-lfqa-qwen3-8b-multiview-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/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-qwen3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-qwen3-8b-multiview.f16.gguf) | f16 | 16.5 | 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/intent-aware-lfqa-qwen3-8b-multiview.IQ4_XS.gguf b/intent-aware-lfqa-qwen3-8b-multiview.IQ4_XS.gguf new file mode 100644 index 0000000..b56400e --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ab0d1aaf27f5bb216ac88ed7d250545ad5a35332124b2b1f09a96dcf82a8aa +size 4593293536 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q2_K.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q2_K.gguf new file mode 100644 index 0000000..c57c40f --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8092de62ad0b365789ee6f015c114a7229a6f79d67040a20d89c6d78cb4748ba +size 3281729760 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_L.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_L.gguf new file mode 100644 index 0000000..ed33373 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73bbce47e277d44205cb053327ab5c34d444acfc903583dd8c3d4c2ba2a4ad8 +size 4431390944 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_M.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_M.gguf new file mode 100644 index 0000000..53d8cef --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0507a67a54284e46e5bf936a105763127c2e14b34c8e6180bd57f3d31644133f +size 4124158176 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_S.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_S.gguf new file mode 100644 index 0000000..84de86f --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d284a27ba163ba692ea704691eb4e725b5abcf5b60dbbb8389697c9fe623ae55 +size 3769608416 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_M.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_M.gguf new file mode 100644 index 0000000..b923764 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01ef2c6ffcc84866b1377b60163655a309830fa58910a2b271de804a3c74389 +size 5027780832 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_S.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_S.gguf new file mode 100644 index 0000000..3ce1a61 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a05e6abfd024a47dfbbb92c037f89fb1b6778f5589fce3ac2a9179ea0a8c61 +size 4802009312 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_M.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_M.gguf new file mode 100644 index 0000000..a3765cc --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf616ecb1826b7e89237489acfd44ccc12a226c8a402a4eb20d59835e9f2a9b3 +size 5851109600 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_S.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_S.gguf new file mode 100644 index 0000000..3ee8575 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0dddbf0c74a985b87c0470142a94a72b844c625f09e5359804cd103ab379678 +size 5720758496 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q6_K.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q6_K.gguf new file mode 100644 index 0000000..71cb558 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63080c808a04573fecb2c2bb5c068b93775d331d965a1d03e8af0fce19678bed +size 6725896416 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.Q8_0.gguf b/intent-aware-lfqa-qwen3-8b-multiview.Q8_0.gguf new file mode 100644 index 0000000..2c35ebd --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:709ec458d9960c39a945148cf6d1cf1d048d40859aaa0d884750493a520336dc +size 8709515488 diff --git a/intent-aware-lfqa-qwen3-8b-multiview.f16.gguf b/intent-aware-lfqa-qwen3-8b-multiview.f16.gguf new file mode 100644 index 0000000..f482a02 --- /dev/null +++ b/intent-aware-lfqa-qwen3-8b-multiview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2b6b779040c8947495650a4362b1fdb15b8796e59256922303af416c34fcdfa +size 16388040928