commit 044bd0a508373b7e91be2ded4cae547176778fcd Author: ModelHub XC Date: Tue Aug 4 18:01:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e96d03 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.IQ4_XS.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.IQ4_XS.gguf new file mode 100644 index 0000000..1b02638 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b72ddd75751b361a000ca83d4fb0a5d8aece6b53a8fdea97fb6ea8a50848bd4 +size 3373775072 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q2_K.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q2_K.gguf new file mode 100644 index 0000000..279ec71 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74c904ff65373b30923fa80e3f226bbc4976e61225e5a6db699b89f715c7c2e +size 2508507360 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_L.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_L.gguf new file mode 100644 index 0000000..12636f2 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea507d0190fe1b0f03c87f7f19c2576b36273c5bfaebad46cee6ec5b387a2907 +size 3280732384 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_M.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_M.gguf new file mode 100644 index 0000000..7dacf1a --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee597d8ea00911d67fbcf5f670034a06e580f394f1f5957db59b8ca72b0d38f1 +size 3140550880 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_S.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_S.gguf new file mode 100644 index 0000000..c750dcb --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4ed1950735d4be529b6a7e5dc9936019670ea8a77fad515fa32a0767488d3ed +size 2897936608 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_0_4_4.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_0_4_4.gguf new file mode 100644 index 0000000..e48d902 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2945f1a77ea683d786f1d3dd40799ac3dbaa178655d1d14e3755a0388dbb52f9 +size 3470694624 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_M.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_M.gguf new file mode 100644 index 0000000..4d03ce8 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6aee7704af34e46ea2056720d1bd9eb24e84b20ec4d17d08a3cb02e3a1373f +size 3951892704 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_S.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_S.gguf new file mode 100644 index 0000000..437a123 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:351e50b8014a99e36ce10feaea0349e9471c22b33779ae585f825eff6247c08e +size 3660945632 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_M.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_M.gguf new file mode 100644 index 0000000..2d94732 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1ee6c6895ad788c95de32860e7d69d42c3edf3343ad18fdeab8dd417ba4350 +size 4510619872 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_S.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_S.gguf new file mode 100644 index 0000000..cf7df6e --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a737ca9f47d90c71cfc054585b6ed760d92fb613c7aca516395cb8d6b5d056e +size 4269283552 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q6_K.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q6_K.gguf new file mode 100644 index 0000000..4c2c22a --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b984bb81864a70940218d04d8f29bbb5a80f94a0a7b86be3b2b0baae5a408e3f +size 5274579168 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q8_0.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q8_0.gguf new file mode 100644 index 0000000..2748894 --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24eecf3bc282e13ce16529a11abee84cde0acfc15dc10b4d9385908b47e59896 +size 6394380512 diff --git a/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.f16.gguf b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.f16.gguf new file mode 100644 index 0000000..d0c88bd --- /dev/null +++ b/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04121709d9d121e0577f8783d36cfcec9752ee9de105860bdcd1835abc38fe39 +size 12026708192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c203988 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Na0s/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained +datasets: +- Na0s/sft-ready-Text-Generation-Augmented-Data-Alpaca-Format +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Na0s/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained + + +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/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_M.gguf) | Q3_K_M | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q3_K_L.gguf) | Q3_K_L | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.IQ4_XS.gguf) | IQ4_XS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q4_K_M.gguf) | Q4_K_M | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_S.gguf) | Q5_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q6_K.gguf) | Q6_K | 5.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.Q8_0.gguf) | Q8_0 | 6.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained-GGUF/resolve/main/Qwen1.5-MoE-A2.7B-20-experts-SFT-trained.f16.gguf) | f16 | 12.1 | 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. + +