commit a51bfaa046d3a5724f6cb05122c12d22c02c93dc Author: ModelHub XC Date: Wed Jul 22 10:29:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QWEN-Instruct-7B-Token-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bfcffb9 --- /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 +QWEN-Instruct-7B-Token.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.f16.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QWEN-Instruct-7B-Token.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QWEN-Instruct-7B-Token.IQ4_XS.gguf b/QWEN-Instruct-7B-Token.IQ4_XS.gguf new file mode 100644 index 0000000..73aab69 --- /dev/null +++ b/QWEN-Instruct-7B-Token.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a69e8ea19558b91f12a762f65ca645b757417293a0f3740b950516619a0e7d57 +size 4248405344 diff --git a/QWEN-Instruct-7B-Token.Q2_K.gguf b/QWEN-Instruct-7B-Token.Q2_K.gguf new file mode 100644 index 0000000..dfea8a0 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:702b8436a1ec555186044b4118704405e0d5603291c0725262a860d53545ed74 +size 3014330272 diff --git a/QWEN-Instruct-7B-Token.Q3_K_L.gguf b/QWEN-Instruct-7B-Token.Q3_K_L.gguf new file mode 100644 index 0000000..e3a9717 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ce588e7577ff89d3038ff6a8128ffb35dad4981c588ffe7e933c9052c34fc4 +size 4086707840 diff --git a/QWEN-Instruct-7B-Token.Q3_K_M.gguf b/QWEN-Instruct-7B-Token.Q3_K_M.gguf new file mode 100644 index 0000000..7d61652 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543d030421a978b9b4cfb1b98888494ac78fbc473ae34ff0653e4688dac5bcde +size 3806639744 diff --git a/QWEN-Instruct-7B-Token.Q3_K_S.gguf b/QWEN-Instruct-7B-Token.Q3_K_S.gguf new file mode 100644 index 0000000..8ee18ed --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12dc7e30b06c49d8ea1745bb9e18f1b9a767e61c470df8d737a62c6f8b091261 +size 3490616960 diff --git a/QWEN-Instruct-7B-Token.Q4_K_M.gguf b/QWEN-Instruct-7B-Token.Q4_K_M.gguf new file mode 100644 index 0000000..f748941 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b7e669ba0b783a4d1738776d3be985a7d25777df95a4d3f2d385faedd99a179 +size 4681136928 diff --git a/QWEN-Instruct-7B-Token.Q4_K_S.gguf b/QWEN-Instruct-7B-Token.Q4_K_S.gguf new file mode 100644 index 0000000..13b6ae9 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fad8a29584ba7843696c80400f9d572c938dcabd4c162e83a1014138a6a1f00 +size 4455832352 diff --git a/QWEN-Instruct-7B-Token.Q5_K_M.gguf b/QWEN-Instruct-7B-Token.Q5_K_M.gguf new file mode 100644 index 0000000..9a3bb94 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eaca6f80d8b9b15c789c6642d5c7e826730f223e5f17e60b3c82a6fbb590b10 +size 5442720352 diff --git a/QWEN-Instruct-7B-Token.Q5_K_S.gguf b/QWEN-Instruct-7B-Token.Q5_K_S.gguf new file mode 100644 index 0000000..2685b31 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823848cbc87eecd95182d90f6f0f7e3d2cedc44e1eed183ceffd5db013becdc6 +size 5313065568 diff --git a/QWEN-Instruct-7B-Token.Q6_K.gguf b/QWEN-Instruct-7B-Token.Q6_K.gguf new file mode 100644 index 0000000..9dcfb93 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c9f67e32faf144c9fb7152f0d653432efa641b9ffb2d4b37afeac827983371 +size 6251902752 diff --git a/QWEN-Instruct-7B-Token.Q8_0.gguf b/QWEN-Instruct-7B-Token.Q8_0.gguf new file mode 100644 index 0000000..28a6390 --- /dev/null +++ b/QWEN-Instruct-7B-Token.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce870c2a96812461c4eb86e42006e65f8596382ae043f7d501d7ea6f82d2c4ca +size 8095553824 diff --git a/QWEN-Instruct-7B-Token.f16.gguf b/QWEN-Instruct-7B-Token.f16.gguf new file mode 100644 index 0000000..4f3b66c --- /dev/null +++ b/QWEN-Instruct-7B-Token.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bddeec4dff449159989b169f258c82bb7e0b80ff7b5bba9f0a232684a5442b8 +size 15232267744 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8929e01 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: Viol2000/QWEN-Instruct-7B-Token +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Viol2000/QWEN-Instruct-7B-Token + + +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/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.IQ4_XS.gguf) | IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QWEN-Instruct-7B-Token-GGUF/resolve/main/QWEN-Instruct-7B-Token.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. + +