commit 186e4af17a5a4c5ad08db6ac0523720f33c564b7 Author: ModelHub XC Date: Sun Apr 19 17:25:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d8c7cfe --- /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 +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.f16.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.IQ4_XS.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.IQ4_XS.gguf new file mode 100644 index 0000000..ea0e707 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dec602522ba60976554f8dbfa791a76442ca7e08cc71bb240883306e01afddb +size 4593297216 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q2_K.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q2_K.gguf new file mode 100644 index 0000000..88b5685 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9230684afa44806d8f39bfb09125d78dca203e3ade879105ec898aba762a85f +size 3281733440 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_L.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_L.gguf new file mode 100644 index 0000000..f4c455a --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c4cc92524a852499f36828e519ac43d225786dad7bb23bd179511422cc7187 +size 4431394624 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_M.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_M.gguf new file mode 100644 index 0000000..6299903 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a55eecf4b728cd4df7d16c94418c4dd9cc7a48a6b7e906135cdc1adce9ea4c80 +size 4124161856 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_S.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_S.gguf new file mode 100644 index 0000000..6ceeac9 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f5022ab8be94ebc99c029aea10277c279e0cc7cb9a47f7f95afd0602cad2db +size 3769612096 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_M.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_M.gguf new file mode 100644 index 0000000..fd79126 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3837469f3de0679def9e484cef7abe0f696d9e0ebe56d82015c2a797ea538974 +size 5027784512 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_S.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_S.gguf new file mode 100644 index 0000000..dd84729 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460c9a34e29fb62bcb953db50eeb8e9d816d54bea89a99ee9f00135175efc665 +size 4802012992 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_M.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_M.gguf new file mode 100644 index 0000000..ee9a9af --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40180ff13262e024ca093000a58e112e192c617bfd8529fddd2f1235075d04d +size 5851113280 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_S.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_S.gguf new file mode 100644 index 0000000..0760c2f --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4f9454094a865e8f9261c9c745c701557923e12635f7fb57d86dcb9db4ff1e +size 5720762176 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q6_K.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q6_K.gguf new file mode 100644 index 0000000..d58cb6b --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36282496129d0f66df8a37a435160c6a111d6a20296f479a334450cd5216d00f +size 6725900096 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q8_0.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q8_0.gguf new file mode 100644 index 0000000..df22f4e --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64364e5b6e99d36472a07710e79ec15d63f4895f746ff961a1deb90478cfca81 +size 8709519168 diff --git a/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.f16.gguf b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.f16.gguf new file mode 100644 index 0000000..2c24eb3 --- /dev/null +++ b/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ea34c0a23771ca4cdd0ed6de29903f0ed9226c76f0a80192bedb7372ff0fcd +size 16388044608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9aa0011 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: yang31210999/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1 +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yang31210999/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-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/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1-GGUF/resolve/main/ICLR-1123_OC-H200-Qwen3-LoRE-Adapt-d1.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. + +