commit e306c0c382649b70e2397fadad6c787d03b4d540 Author: ModelHub XC Date: Thu Jun 25 15:58:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a4985c --- /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-llama3-8b-multiview.f16.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-multiview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +intent-aware-lfqa-llama3-8b-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..847438b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: allenai/intent-aware-lfqa-llama3-8b-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-llama3-8b-multiview + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#intent-aware-lfqa-llama3-8b-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-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/intent-aware-lfqa-llama3-8b-multiview-GGUF/resolve/main/intent-aware-lfqa-llama3-8b-multiview.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/intent-aware-lfqa-llama3-8b-multiview.IQ4_XS.gguf b/intent-aware-lfqa-llama3-8b-multiview.IQ4_XS.gguf new file mode 100644 index 0000000..6ff9d66 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a510464f7332f0dea840ec10a05993d189e5e369f868310e612b6a669e6117cb +size 4484408704 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q2_K.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q2_K.gguf new file mode 100644 index 0000000..3a9fe7d --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89f379ce540ace114619f392f96d6d5eefd2b039732f04c46b3fe659e378a6ca +size 3179170688 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q3_K_L.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_L.gguf new file mode 100644 index 0000000..25defef --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f588c8290da7b0aabb9a531e70f58406d7f7e19f423c6ce4007c9fa031d0aed8 +size 4321998976 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q3_K_M.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_M.gguf new file mode 100644 index 0000000..9ebd56e --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66b2beeb69fa568c220ef9ccca2ac7b2d38f782f7cd87fca878cf9683d9ccedb +size 4018960512 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q3_K_S.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_S.gguf new file mode 100644 index 0000000..8fc613e --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:958696cdb6a7be30f08daf105a18cce67384aece6d4dd39810b63e8ded63a0c0 +size 3664541824 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q4_K_M.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q4_K_M.gguf new file mode 100644 index 0000000..8fc03b4 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ff2b8ce8333ab94def21d118aa3fde3ac0621e0c348fd11723a9d25ac65f1a +size 4920781184 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q4_K_S.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q4_K_S.gguf new file mode 100644 index 0000000..4ce6fd3 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ecf9e16b322ced354f62454cf0d86d5a1150cb3fc339e0f1a5443d0a3fc8e7f +size 4692715904 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q5_K_M.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q5_K_M.gguf new file mode 100644 index 0000000..f108b2c --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2fdeae3b402d2f73ba34e72b72f19d22bf1f1ba2a9f382628a18ce12f3220b8 +size 5733038464 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q5_K_S.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q5_K_S.gguf new file mode 100644 index 0000000..0008321 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4925c8d99f983c0a2adb3291c308b3933afd7345a9583d3218376da54877f3d +size 5599345024 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q6_K.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q6_K.gguf new file mode 100644 index 0000000..b96da16 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19ff1bd7c16cc3123eb6b9605588b64c573d8c0bbeb77de568e7c308b9ff1bfa +size 6596061824 diff --git a/intent-aware-lfqa-llama3-8b-multiview.Q8_0.gguf b/intent-aware-lfqa-llama3-8b-multiview.Q8_0.gguf new file mode 100644 index 0000000..cf68d81 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dffb49a3b611449bf0b3f90717b5017e2747a78db83287382ac0691006bb94a1 +size 8540842112 diff --git a/intent-aware-lfqa-llama3-8b-multiview.f16.gguf b/intent-aware-lfqa-llama3-8b-multiview.f16.gguf new file mode 100644 index 0000000..e29f8a0 --- /dev/null +++ b/intent-aware-lfqa-llama3-8b-multiview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5971ad57a41ce68290d68af925b130d1b873da6eadd2a31253331d3b1dfc54d1 +size 16069023872