commit 762f7f49b9c4855891b28b4b1529b0c3487429b8 Author: ModelHub XC Date: Wed Jul 8 04:08:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Q2.5-Instruct-1M_Harmony-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c09f7c --- /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 +Q2.5-Instruct-1M_Harmony.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.f16.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Q2.5-Instruct-1M_Harmony.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Q2.5-Instruct-1M_Harmony.IQ4_XS.gguf b/Q2.5-Instruct-1M_Harmony.IQ4_XS.gguf new file mode 100644 index 0000000..b5f5cf2 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c0fa014c0cd0f43997b23f7d377e288c85121bab90bf71334d1b8d2ad0f175 +size 4250299328 diff --git a/Q2.5-Instruct-1M_Harmony.Q2_K.gguf b/Q2.5-Instruct-1M_Harmony.Q2_K.gguf new file mode 100644 index 0000000..bb2cf74 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:622c5e17b01d4b4a5c30fddc138c246dd8050e86f0ab99348a23b00e8272ec35 +size 3015941056 diff --git a/Q2.5-Instruct-1M_Harmony.Q3_K_L.gguf b/Q2.5-Instruct-1M_Harmony.Q3_K_L.gguf new file mode 100644 index 0000000..6db4669 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de56a3451d2492a645b51ca0024864bb652482c6f952682f35e18f5528f4de1b +size 4088460224 diff --git a/Q2.5-Instruct-1M_Harmony.Q3_K_M.gguf b/Q2.5-Instruct-1M_Harmony.Q3_K_M.gguf new file mode 100644 index 0000000..309d14c --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a447352f951b2534d7d29e05739f6a4aab41a242c2bec7f05a0dbf0a4952625 +size 3808392128 diff --git a/Q2.5-Instruct-1M_Harmony.Q3_K_S.gguf b/Q2.5-Instruct-1M_Harmony.Q3_K_S.gguf new file mode 100644 index 0000000..8720db8 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08225872f1c467d0beae6ea3d61e871297d4a80ef04e34e7ebd9b452858c4959 +size 3492369344 diff --git a/Q2.5-Instruct-1M_Harmony.Q4_K_M.gguf b/Q2.5-Instruct-1M_Harmony.Q4_K_M.gguf new file mode 100644 index 0000000..6740757 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcc818a13f66a1843f15bb2696edee07dc67b0d0e7215bd83e35b76e1795924b +size 4683074496 diff --git a/Q2.5-Instruct-1M_Harmony.Q4_K_S.gguf b/Q2.5-Instruct-1M_Harmony.Q4_K_S.gguf new file mode 100644 index 0000000..f573a92 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5819f4f5079829fb0d86cc7a1a668b5ec68bc634e515f421b102e67c6fedcf9 +size 4457769920 diff --git a/Q2.5-Instruct-1M_Harmony.Q5_K_M.gguf b/Q2.5-Instruct-1M_Harmony.Q5_K_M.gguf new file mode 100644 index 0000000..9c1b475 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13915501d27c6c297a5581c84645aa5b18a4a4411cd900bad908dff207301e7 +size 5444832192 diff --git a/Q2.5-Instruct-1M_Harmony.Q5_K_S.gguf b/Q2.5-Instruct-1M_Harmony.Q5_K_S.gguf new file mode 100644 index 0000000..a781552 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:382bf2ac1e156442150ee06cb4bf29c92288b99c91bb489b2357aec58e7e846b +size 5315177408 diff --git a/Q2.5-Instruct-1M_Harmony.Q6_K.gguf b/Q2.5-Instruct-1M_Harmony.Q6_K.gguf new file mode 100644 index 0000000..213f075 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af4688ed07e0f2cdd4d8727c5ab0117be6fad502b1bd6ef2afe6f59aa6b61cb +size 6254199744 diff --git a/Q2.5-Instruct-1M_Harmony.Q8_0.gguf b/Q2.5-Instruct-1M_Harmony.Q8_0.gguf new file mode 100644 index 0000000..a06b4ec --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:702a2fb9497b15be05aa0770426a2892241b7220a39ea98df9c9a2ab11b2d5c1 +size 8098526144 diff --git a/Q2.5-Instruct-1M_Harmony.f16.gguf b/Q2.5-Instruct-1M_Harmony.f16.gguf new file mode 100644 index 0000000..4c858e6 --- /dev/null +++ b/Q2.5-Instruct-1M_Harmony.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b4906287cea49fd7185883abe4dfa73eec28355e9eb752187f9411d25bcf47a +size 15237854144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..adf1099 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Triangle104/Q2.5-Instruct-1M_Harmony +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Triangle104/Q2.5-Instruct-1M_Harmony + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-i1-GGUF +## 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/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Q2.5-Instruct-1M_Harmony-GGUF/resolve/main/Q2.5-Instruct-1M_Harmony.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +