commit 5e77401ff31a083042d09d27ab261250ac270cc8 Author: ModelHub XC Date: Fri Jul 17 17:49:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/Qwen2-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ab47b5b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.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 +Qwen2-7B-Instruct-f32.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct.imatrix filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-7B-Instruct-bf16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-7B-Instruct-IQ2_M.gguf b/Qwen2-7B-Instruct-IQ2_M.gguf new file mode 100644 index 0000000..51ca1e9 --- /dev/null +++ b/Qwen2-7B-Instruct-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b65122950bc41f4e4893b689fb0faff01b47a368157398c77b8697c07e55d6 +size 2780340000 diff --git a/Qwen2-7B-Instruct-IQ2_S.gguf b/Qwen2-7B-Instruct-IQ2_S.gguf new file mode 100644 index 0000000..42527a3 --- /dev/null +++ b/Qwen2-7B-Instruct-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a2177e22202f0cca7ef0e948ed68705c5ec94ef4743ed8db707b8056a086879 +size 2595634976 diff --git a/Qwen2-7B-Instruct-IQ2_XS.gguf b/Qwen2-7B-Instruct-IQ2_XS.gguf new file mode 100644 index 0000000..5648cba --- /dev/null +++ b/Qwen2-7B-Instruct-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:247883eca048b402e4829ae8d72359cb968581e71cbcefe49fb08b6d66673737 +size 2469019424 diff --git a/Qwen2-7B-Instruct-IQ3_M.gguf b/Qwen2-7B-Instruct-IQ3_M.gguf new file mode 100644 index 0000000..0c9eedc --- /dev/null +++ b/Qwen2-7B-Instruct-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc59415c3941cf07c2a3fe5e5581dc45c8951f82bab7f5614d0bba2e1a34a82 +size 3574009632 diff --git a/Qwen2-7B-Instruct-IQ3_XS.gguf b/Qwen2-7B-Instruct-IQ3_XS.gguf new file mode 100644 index 0000000..671e71d --- /dev/null +++ b/Qwen2-7B-Instruct-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd392f72431881477b20b772bcbc7b97c651ee8af6a8e95bbfa5a0c8d8dba39 +size 3346253600 diff --git a/Qwen2-7B-Instruct-IQ3_XXS.gguf b/Qwen2-7B-Instruct-IQ3_XXS.gguf new file mode 100644 index 0000000..61c137d --- /dev/null +++ b/Qwen2-7B-Instruct-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ab957f52e5dd77e991c02156f80c3f94e9f4ded2c93e38a8fb99e9407a3e6c +size 3114512160 diff --git a/Qwen2-7B-Instruct-IQ4_XS.gguf b/Qwen2-7B-Instruct-IQ4_XS.gguf new file mode 100644 index 0000000..44fd8a2 --- /dev/null +++ b/Qwen2-7B-Instruct-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d51e881f308be12283e63eefae625840e1d44af4a11ccbd80f8f177d5f7b01f2 +size 4218470176 diff --git a/Qwen2-7B-Instruct-Q2_K.gguf b/Qwen2-7B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..98623b1 --- /dev/null +++ b/Qwen2-7B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71d6be6a0faa192a938b1bd86bbc8d527d0f56b6672164180bf1a0464a80af0c +size 3015937824 diff --git a/Qwen2-7B-Instruct-Q3_K_L.gguf b/Qwen2-7B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..aea9709 --- /dev/null +++ b/Qwen2-7B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0577a71834e73ae59015880d34dcd5ef549176c50b02dcef3b0acdc975f7479a +size 4088456992 diff --git a/Qwen2-7B-Instruct-Q3_K_M.gguf b/Qwen2-7B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..5f75c11 --- /dev/null +++ b/Qwen2-7B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27f06e0b1910771eb7bf04fa4a88832d04c009d7b8506ffaa045b9a503b31d16 +size 3808388896 diff --git a/Qwen2-7B-Instruct-Q3_K_S.gguf b/Qwen2-7B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..517a5fa --- /dev/null +++ b/Qwen2-7B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34aa03f291b5d7b71c6d71062eeed1d2fa4d313b5048cebcb1923656d9806b8c +size 3492366112 diff --git a/Qwen2-7B-Instruct-Q4_K_M.gguf b/Qwen2-7B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..262892e --- /dev/null +++ b/Qwen2-7B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0d33f0d9110a04aad1711b1ca02dafc0fa658cd83028bdfa5eff89c294fe76 +size 4683071264 diff --git a/Qwen2-7B-Instruct-Q4_K_S.gguf b/Qwen2-7B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..cb376e8 --- /dev/null +++ b/Qwen2-7B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db87d60e881c760995cac29a8c0ed5d08c8b65cce8b052aaca9d2e3d6f833246 +size 4457766688 diff --git a/Qwen2-7B-Instruct-Q5_K_M.gguf b/Qwen2-7B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..32759e2 --- /dev/null +++ b/Qwen2-7B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f17976829b0e6d91852da2f3cd3f78d0f110778c858a29494a53d4acee8e69a +size 5444828960 diff --git a/Qwen2-7B-Instruct-Q5_K_S.gguf b/Qwen2-7B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..90a37fc --- /dev/null +++ b/Qwen2-7B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8696ac6e6c180f3f9528630b9b3cab0d779a4e4dfb12dc9f30c9030075708db4 +size 5315174176 diff --git a/Qwen2-7B-Instruct-Q6_K.gguf b/Qwen2-7B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..db69a37 --- /dev/null +++ b/Qwen2-7B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5c1a2f31ba0ddb10a40720a6c592a0f7898c7c7b1c752679b0d18bad6b12df +size 6254196512 diff --git a/Qwen2-7B-Instruct-Q8_0.gguf b/Qwen2-7B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..5d4f982 --- /dev/null +++ b/Qwen2-7B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3382bda013daf109f2d6fb7a990ca149fcaf4c221ec38597d0204c46d15d28 +size 8098522912 diff --git a/Qwen2-7B-Instruct-bf16.gguf b/Qwen2-7B-Instruct-bf16.gguf new file mode 100644 index 0000000..05d385d --- /dev/null +++ b/Qwen2-7B-Instruct-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcfd06d4f9911b033ef0574937de75878e4d7719bd89966203162a31b1a39f6f +size 15237850656 diff --git a/Qwen2-7B-Instruct-f32.gguf b/Qwen2-7B-Instruct-f32.gguf new file mode 100644 index 0000000..086af28 --- /dev/null +++ b/Qwen2-7B-Instruct-f32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a23f3f11e7143b81b45b0466c728e3b3d322a18bcdf6ebfbe1116182fc140a +size 30468417056 diff --git a/Qwen2-7B-Instruct.imatrix b/Qwen2-7B-Instruct.imatrix new file mode 100644 index 0000000..2820720 --- /dev/null +++ b/Qwen2-7B-Instruct.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23573f736284e14dd701cb2af68ca900ff640c6564ff0e7ce7e79d346db9dade +size 4536679 diff --git a/README.md b/README.md new file mode 100644 index 0000000..90c1a84 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +license: apache-2.0 +language: +- en +pipeline_tag: text-generation +tags: +- chat +quantized_by: bartowski +base_model: Qwen/Qwen2-7B-Instruct +--- + +# Heads up: currently CUDA offloading is broken unless you enable flash attention + +## Llamacpp imatrix Quantizations of Qwen2-7B-Instruct + +Using llama.cpp commit ee459f40f65810a810151b24eba5b8bd174ceffe for quantization. + +Original model: https://huggingface.co/Qwen/Qwen2-7B-Instruct + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant + +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Description | +| -------- | ---------- | --------- | ----------- | +| [Qwen2-7B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q8_0.gguf) | Q8_0 | 8.09GB | Extremely high quality, generally unneeded but max available quant. | +| [Qwen2-7B-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q6_K.gguf) | Q6_K | 6.25GB | Very high quality, near perfect, *recommended*. | +| [Qwen2-7B-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5.44GB | High quality, *recommended*. | +| [Qwen2-7B-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5.31GB | High quality, *recommended*. | +| [Qwen2-7B-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4.68GB | Good quality, uses about 4.83 bits per weight, *recommended*. | +| [Qwen2-7B-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4.45GB | Slightly lower quality with more space savings, *recommended*. | +| [Qwen2-7B-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ4_XS.gguf) | IQ4_XS | 4.21GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen2-7B-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 4.08GB | Lower quality but usable, good for low RAM availability. | +| [Qwen2-7B-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3.80GB | Even lower quality. | +| [Qwen2-7B-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ3_M.gguf) | IQ3_M | 3.57GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen2-7B-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3.49GB | Low quality, not recommended. | +| [Qwen2-7B-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ3_XS.gguf) | IQ3_XS | 3.34GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen2-7B-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 3.11GB | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen2-7B-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-Q2_K.gguf) | Q2_K | 3.01GB | Very low quality but surprisingly usable. | +| [Qwen2-7B-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ2_M.gguf) | IQ2_M | 2.78GB | Very low quality, uses SOTA techniques to also be surprisingly usable. | +| [Qwen2-7B-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ2_S.gguf) | IQ2_S | 2.59GB | Very low quality, uses SOTA techniques to be usable. | +| [Qwen2-7B-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/Qwen2-7B-Instruct-GGUF/blob/main/Qwen2-7B-Instruct-IQ2_XS.gguf) | IQ2_XS | 2.46GB | Very low quality, uses SOTA techniques to be usable. | + +## Downloading using huggingface-cli + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/Qwen2-7B-Instruct-GGUF --include "Qwen2-7B-Instruct-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/Qwen2-7B-Instruct-GGUF --include "Qwen2-7B-Instruct-Q8_0.gguf/*" --local-dir Qwen2-7B-Instruct-Q8_0 +``` + +You can either specify a new local-dir (Qwen2-7B-Instruct-Q8_0) or download them all in place (./) + +## Which file should I choose? + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file