commit 342d737251532505b5200541caed4b12eadfae6b Author: ModelHub XC Date: Wed Jun 3 23:42:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HAD-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..672261a --- /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 +HAD-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HAD-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HAD-7B.IQ4_XS.gguf b/HAD-7B.IQ4_XS.gguf new file mode 100644 index 0000000..65440f1 --- /dev/null +++ b/HAD-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b77251a10bcee02d3a4bf93e16efa769026beb23531d47ed90e692ace8c8ce1 +size 4250298848 diff --git a/HAD-7B.Q2_K.gguf b/HAD-7B.Q2_K.gguf new file mode 100644 index 0000000..889b2ac --- /dev/null +++ b/HAD-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bfc1b29ac93c269f745473cc4903ea0d4b6541e49d847004dce04a6e8d4bbb7 +size 3015940576 diff --git a/HAD-7B.Q3_K_L.gguf b/HAD-7B.Q3_K_L.gguf new file mode 100644 index 0000000..6960367 --- /dev/null +++ b/HAD-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101d31f29c221a876fb72786ee931bcd1a6953904540ae0ffca3430c4fdb7e3a +size 4088459744 diff --git a/HAD-7B.Q3_K_M.gguf b/HAD-7B.Q3_K_M.gguf new file mode 100644 index 0000000..37a4c2c --- /dev/null +++ b/HAD-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4746bc25d637cd244e04c6ba00eb40f3bfcbb467342badc76e43f8cb6b9dbc68 +size 3808391648 diff --git a/HAD-7B.Q3_K_S.gguf b/HAD-7B.Q3_K_S.gguf new file mode 100644 index 0000000..6dbb703 --- /dev/null +++ b/HAD-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44087bd67baf460a8c28f9c4980df1f33503668e5e1c1a0e7f65ede7df0334ab +size 3492368864 diff --git a/HAD-7B.Q4_K_M.gguf b/HAD-7B.Q4_K_M.gguf new file mode 100644 index 0000000..5e54eb5 --- /dev/null +++ b/HAD-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d58d5b8267a15aee30e0bb63fae8baccb4e9dd59363ff7970097fe68a8a99d00 +size 4683074016 diff --git a/HAD-7B.Q4_K_S.gguf b/HAD-7B.Q4_K_S.gguf new file mode 100644 index 0000000..a50c79b --- /dev/null +++ b/HAD-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fc55025f565020951e3e7d67e4d0e5619a73e58097cbe3eb7c9609023700efe +size 4457769440 diff --git a/HAD-7B.Q5_K_M.gguf b/HAD-7B.Q5_K_M.gguf new file mode 100644 index 0000000..dbd29cf --- /dev/null +++ b/HAD-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0b1e2131af127843292a3038624ab7b6fcdbd1616a0d8080c46ca7c3d2dce99 +size 5444831712 diff --git a/HAD-7B.Q5_K_S.gguf b/HAD-7B.Q5_K_S.gguf new file mode 100644 index 0000000..2f2fa12 --- /dev/null +++ b/HAD-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094c0630c5a0113b26d0273f62de6aee494d9cdd52f283a1b86c420fda4ed82d +size 5315176928 diff --git a/HAD-7B.Q6_K.gguf b/HAD-7B.Q6_K.gguf new file mode 100644 index 0000000..f7f1c8a --- /dev/null +++ b/HAD-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5b10e61402b4a95a6788cd8b2299397b9599b9c9793bf53dcd9b0585ab185f +size 6254199264 diff --git a/HAD-7B.Q8_0.gguf b/HAD-7B.Q8_0.gguf new file mode 100644 index 0000000..14d54a8 --- /dev/null +++ b/HAD-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7fcd3dac08352e8810532964bc42001ffe9eca69220b865bb719a5f9c25233 +size 8098525664 diff --git a/HAD-7B.f16.gguf b/HAD-7B.f16.gguf new file mode 100644 index 0000000..5b0187c --- /dev/null +++ b/HAD-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ddc072db8c9d21bcf6c9a8f460710230ca48e745449cd9cef459f0982169c8 +size 15237853664 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc9d413 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: PKU-ONELab/HAD-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/PKU-ONELab/HAD-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HAD-7B-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/HAD-7B-GGUF/resolve/main/HAD-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HAD-7B-GGUF/resolve/main/HAD-7B.f16.gguf) | f16 | 15.3 | 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. + +