commit 690e43d6004a464740eb01c38d11bd43bdca5f23 Author: ModelHub XC Date: Sat Apr 11 08:01:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/fq2.5-7b-it-normalize_false-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..45ee685 --- /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 +fq2.5-7b-it-normalize_false.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.f16.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +fq2.5-7b-it-normalize_false.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..798b69a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: ehristoforu/fq2.5-7b-it-normalize_false +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/ehristoforu/fq2.5-7b-it-normalize_false + + +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/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/fq2.5-7b-it-normalize_false-GGUF/resolve/main/fq2.5-7b-it-normalize_false.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/fq2.5-7b-it-normalize_false.IQ4_XS.gguf b/fq2.5-7b-it-normalize_false.IQ4_XS.gguf new file mode 100644 index 0000000..061b246 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c376ebe692ec118b0fe3a82187066c2233a727b8989b8b79c657ecaabd3c20e +size 4250301184 diff --git a/fq2.5-7b-it-normalize_false.Q2_K.gguf b/fq2.5-7b-it-normalize_false.Q2_K.gguf new file mode 100644 index 0000000..7a4e903 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f52eea0343730c5ff461efd450b1353443f342a0640ebab75ea854b97334af2 +size 3015942912 diff --git a/fq2.5-7b-it-normalize_false.Q3_K_L.gguf b/fq2.5-7b-it-normalize_false.Q3_K_L.gguf new file mode 100644 index 0000000..0b15cc9 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a626fd18add4b24efc7e2452027ccd45d0792cab945074903f58dcbfe6a134b8 +size 4088462080 diff --git a/fq2.5-7b-it-normalize_false.Q3_K_M.gguf b/fq2.5-7b-it-normalize_false.Q3_K_M.gguf new file mode 100644 index 0000000..5e601b6 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf7621a96b7c739084cc1b8334a42f33d159a7a5440c6063eb03232a5a9bbfe0 +size 3808393984 diff --git a/fq2.5-7b-it-normalize_false.Q3_K_S.gguf b/fq2.5-7b-it-normalize_false.Q3_K_S.gguf new file mode 100644 index 0000000..0e73d5e --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8428c744176466f7b691e70e6457b1d30195c6bda756d254a6272d6ab51179d1 +size 3492371200 diff --git a/fq2.5-7b-it-normalize_false.Q4_K_M.gguf b/fq2.5-7b-it-normalize_false.Q4_K_M.gguf new file mode 100644 index 0000000..bb40f8a --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f9b7537c3e049e0553b01ce1d2d5f2e5f40e83b3567f0225787ffa62a11fbd8 +size 4683076352 diff --git a/fq2.5-7b-it-normalize_false.Q4_K_S.gguf b/fq2.5-7b-it-normalize_false.Q4_K_S.gguf new file mode 100644 index 0000000..6dc0abf --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05016888268b4a5dd6903378793bd62132a92ff40c5dc126bc5d6b6248ac3a1d +size 4457771776 diff --git a/fq2.5-7b-it-normalize_false.Q5_K_M.gguf b/fq2.5-7b-it-normalize_false.Q5_K_M.gguf new file mode 100644 index 0000000..a905ea1 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d03fdb8b2df0ed6aa8c679baca967c0ffc761ef1c37bd6fa53b3672ff5845b4 +size 5444834048 diff --git a/fq2.5-7b-it-normalize_false.Q5_K_S.gguf b/fq2.5-7b-it-normalize_false.Q5_K_S.gguf new file mode 100644 index 0000000..0ead70e --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0b4d1c6baf3534fd0f8a916f05d1f8281f1c8f7f937b9563e7292d177de332f +size 5315179264 diff --git a/fq2.5-7b-it-normalize_false.Q6_K.gguf b/fq2.5-7b-it-normalize_false.Q6_K.gguf new file mode 100644 index 0000000..3bfdabc --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66fd153b0deac2ec9db32638e8865dbe7e22bd63e7229f32f7804e4de4c964c +size 6254201600 diff --git a/fq2.5-7b-it-normalize_false.Q8_0.gguf b/fq2.5-7b-it-normalize_false.Q8_0.gguf new file mode 100644 index 0000000..8ad5642 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c433ecf6e992fb1ccc640fd82a448a0b6e938260129e04a83dd7ac8a020dc15d +size 8098528000 diff --git a/fq2.5-7b-it-normalize_false.f16.gguf b/fq2.5-7b-it-normalize_false.f16.gguf new file mode 100644 index 0000000..fd62877 --- /dev/null +++ b/fq2.5-7b-it-normalize_false.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9841a6ea0f0201dafef77cb4dbb43811f2b9065e098fba44ed394941a2eb4d5 +size 15237856000