commit c75c955a38cfd6a9ddc67fa5d888b39b3b923f43 Author: ModelHub XC Date: Tue Apr 21 20:33:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/FMT-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..69200f7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +FMT-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +FMT-v2.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/FMT-v2.IQ4_XS.gguf b/FMT-v2.IQ4_XS.gguf new file mode 100644 index 0000000..1c62abc --- /dev/null +++ b/FMT-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdca3dfc644f1fcd47ca69ac3debc9fecabac703a18291a0da6b03ac0a09e3e0 +size 3944401440 diff --git a/FMT-v2.Q2_K.gguf b/FMT-v2.Q2_K.gguf new file mode 100644 index 0000000..57aa85b --- /dev/null +++ b/FMT-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6faf2b5bba115230250da21ad84097a1cbde0907939932e3373690a1d5b01c7c +size 2719253408 diff --git a/FMT-v2.Q3_K_L.gguf b/FMT-v2.Q3_K_L.gguf new file mode 100644 index 0000000..dd4a591 --- /dev/null +++ b/FMT-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef36c4e607eafdc60e36aa5f51a67b64b818dabaefe96c676227bc5668fe1c37 +size 3822036704 diff --git a/FMT-v2.Q3_K_M.gguf b/FMT-v2.Q3_K_M.gguf new file mode 100644 index 0000000..ba6d855 --- /dev/null +++ b/FMT-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b297b52e47b584d51f4aa615c5c51689bae6de030c6ca7d3466d6480ab23be +size 3518998240 diff --git a/FMT-v2.Q3_K_S.gguf b/FMT-v2.Q3_K_S.gguf new file mode 100644 index 0000000..de1d9c1 --- /dev/null +++ b/FMT-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f02c1a3899dda2f4d772c3a06f01eb7deac78ae0617e019b4f0cd1b72fce5b +size 3164579552 diff --git a/FMT-v2.Q4_0_4_4.gguf b/FMT-v2.Q4_0_4_4.gguf new file mode 100644 index 0000000..0e62afa --- /dev/null +++ b/FMT-v2.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39f21fb2606d423d3b8b0945a8d3c5607e6ebd7049ee21bfc70dd8ec7b47000e +size 4108929824 diff --git a/FMT-v2.Q4_K_M.gguf b/FMT-v2.Q4_K_M.gguf new file mode 100644 index 0000000..113b50c --- /dev/null +++ b/FMT-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8e39150e77397250aadfb6ec73398b4be0fa4fa6b5656b48c1ce28b2e6734a +size 4368452384 diff --git a/FMT-v2.Q4_K_S.gguf b/FMT-v2.Q4_K_S.gguf new file mode 100644 index 0000000..c63a822 --- /dev/null +++ b/FMT-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4586220d7c5a43a3c645a1bd017d614a260f991cfd71b49a082e49054fd75b7f +size 4140387104 diff --git a/FMT-v2.Q5_K_M.gguf b/FMT-v2.Q5_K_M.gguf new file mode 100644 index 0000000..e09fa9d --- /dev/null +++ b/FMT-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41dd4bc05c35db5b7d9eb57622522ae61614f661a0539f88aea203312802226e +size 5131423520 diff --git a/FMT-v2.Q5_K_S.gguf b/FMT-v2.Q5_K_S.gguf new file mode 100644 index 0000000..ef2a116 --- /dev/null +++ b/FMT-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a5306393e10f68d4fe3a039237c12c4db3fbcf56d860b9bdc878d6217ccfa9 +size 4997730080 diff --git a/FMT-v2.Q6_K.gguf b/FMT-v2.Q6_K.gguf new file mode 100644 index 0000000..216c0a5 --- /dev/null +++ b/FMT-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c901ffd59a099358ecec58565789aa9956f9d4709fd7b3ba1b1e6a74bd465880 +size 5942080352 diff --git a/FMT-v2.Q8_0.gguf b/FMT-v2.Q8_0.gguf new file mode 100644 index 0000000..0b414cf --- /dev/null +++ b/FMT-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf28bdd857fe77f133e6455c0f000c2b8ea400ca9a47f32a8757f8bafa0e72ed +size 7695876832 diff --git a/FMT-v2.f16.gguf b/FMT-v2.f16.gguf new file mode 100644 index 0000000..c87d037 --- /dev/null +++ b/FMT-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5cd59b5201dd64008cf2ed35aee0a3b6f7943b6a1bd1af816b97dd7c9773030 +size 14484766432 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3c411de --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Virt-io/FMT-v2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- FuseAI/FuseChat-7B-VaRM +- occiglot/occiglot-7b-eu5-instruct +- INSAIT-Institute/BgGPT-7B-Instruct-v0.2 +--- +## About + + + + + + +static quants of https://huggingface.co/Virt-io/FMT-v2 + + +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/FMT-v2-GGUF/resolve/main/FMT-v2.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/FMT-v2-GGUF/resolve/main/FMT-v2.f16.gguf) | f16 | 14.6 | 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. + +