commit 4e0e3fd1936c91884917c32eb2f748b5a19f267d Author: ModelHub XC Date: Sat Jul 18 16:35:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/dragon-qwen-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eb9f52f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +dragon-qwen-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +dragon-qwen-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5cf5780 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: llmware/dragon-qwen-7b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/llmware/dragon-qwen-7b + + +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/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.IQ3_XS.gguf) | IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.IQ3_S.gguf) | IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.IQ3_M.gguf) | IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/dragon-qwen-7b-GGUF/resolve/main/dragon-qwen-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. + + diff --git a/dragon-qwen-7b.IQ3_M.gguf b/dragon-qwen-7b.IQ3_M.gguf new file mode 100644 index 0000000..067ef6e --- /dev/null +++ b/dragon-qwen-7b.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfa9ec2f938af0469e5318088a8dcc30831abde19de17270645953e0ac35f4b5 +size 3574009984 diff --git a/dragon-qwen-7b.IQ3_S.gguf b/dragon-qwen-7b.IQ3_S.gguf new file mode 100644 index 0000000..db1739c --- /dev/null +++ b/dragon-qwen-7b.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125bf77fa71ca68fa3f5cdd1594290c71eb6eaad2946032752eabe19a07c1f24 +size 3499190400 diff --git a/dragon-qwen-7b.IQ3_XS.gguf b/dragon-qwen-7b.IQ3_XS.gguf new file mode 100644 index 0000000..fa47673 --- /dev/null +++ b/dragon-qwen-7b.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b25971194ad681166343fa7c76ef1b612e5565b47ff5db5f10eca67c93416e2 +size 3346253952 diff --git a/dragon-qwen-7b.IQ4_XS.gguf b/dragon-qwen-7b.IQ4_XS.gguf new file mode 100644 index 0000000..8bdcfe7 --- /dev/null +++ b/dragon-qwen-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:566718e1188c9e71eef5fdd02641b3ba7b8f22e2346d1c7a8143597ce5b43bf0 +size 4250296448 diff --git a/dragon-qwen-7b.Q2_K.gguf b/dragon-qwen-7b.Q2_K.gguf new file mode 100644 index 0000000..122cbd3 --- /dev/null +++ b/dragon-qwen-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd92c32e8648b9d577db572fba403f89b92119aa21243ed458ac6d3e64099f6 +size 3015938176 diff --git a/dragon-qwen-7b.Q3_K_L.gguf b/dragon-qwen-7b.Q3_K_L.gguf new file mode 100644 index 0000000..3467402 --- /dev/null +++ b/dragon-qwen-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f6722cd619f9e2c234b7b63a522c6bdbd111d4fcbbba7f56f030e18c0df6f3 +size 4088457344 diff --git a/dragon-qwen-7b.Q3_K_M.gguf b/dragon-qwen-7b.Q3_K_M.gguf new file mode 100644 index 0000000..c8d3755 --- /dev/null +++ b/dragon-qwen-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88312481b18bfafa25f255ef091fca1759cc223ad3b238c2faeea8b57666b5e5 +size 3808389248 diff --git a/dragon-qwen-7b.Q3_K_S.gguf b/dragon-qwen-7b.Q3_K_S.gguf new file mode 100644 index 0000000..d4f4aac --- /dev/null +++ b/dragon-qwen-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0009cb3db14c6827e4a26c84295d5f6879545d6da225e8193a3f404522d7da38 +size 3492366464 diff --git a/dragon-qwen-7b.Q4_K_M.gguf b/dragon-qwen-7b.Q4_K_M.gguf new file mode 100644 index 0000000..4510e08 --- /dev/null +++ b/dragon-qwen-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9cae55be9f3fd2e34d007bbb07b67fec9972638a265eea3bdfc3e1b762e81b0 +size 4683071616 diff --git a/dragon-qwen-7b.Q4_K_S.gguf b/dragon-qwen-7b.Q4_K_S.gguf new file mode 100644 index 0000000..636986a --- /dev/null +++ b/dragon-qwen-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:145d9bc451d4292bf122a7657875439d5a5c3b972ccc5185b3a81d94376e29be +size 4457767040 diff --git a/dragon-qwen-7b.Q5_K_M.gguf b/dragon-qwen-7b.Q5_K_M.gguf new file mode 100644 index 0000000..79dda83 --- /dev/null +++ b/dragon-qwen-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d19657e939e3c393184f929724337a54691410f68866eee4d9f4aab77ced2e1 +size 5444829312 diff --git a/dragon-qwen-7b.Q5_K_S.gguf b/dragon-qwen-7b.Q5_K_S.gguf new file mode 100644 index 0000000..890f080 --- /dev/null +++ b/dragon-qwen-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2e5aebf0849bca6ed3b2f04473cf1c2b1fc634a5611a5c975575d16a7890cc8 +size 5315174528 diff --git a/dragon-qwen-7b.Q6_K.gguf b/dragon-qwen-7b.Q6_K.gguf new file mode 100644 index 0000000..8908a57 --- /dev/null +++ b/dragon-qwen-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d032a1f531647ec4360165236a63d581dd35ecec9c8a039fdcd5d134800f666 +size 6254196864 diff --git a/dragon-qwen-7b.Q8_0.gguf b/dragon-qwen-7b.Q8_0.gguf new file mode 100644 index 0000000..925fed3 --- /dev/null +++ b/dragon-qwen-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f20d14beab0525aca0a46c0c9a958ced7b322eae28496d6bee668eaf9abd787 +size 8098523264 diff --git a/dragon-qwen-7b.f16.gguf b/dragon-qwen-7b.f16.gguf new file mode 100644 index 0000000..8150c3e --- /dev/null +++ b/dragon-qwen-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2892b533b43670be608a1ecc7be3d80c84826925e1a770c6b20932482887e384 +size 15237851264