commit a0eb01d0025d6453e8e008dc4a3837b0fdefc0ce Author: ModelHub XC Date: Sun Jun 14 01:04:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/taraV2-M16B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8936950 --- /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 +taraV2-M16B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +taraV2-M16B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b4ef830 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Gragroo/taraV2-M16B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/Gragroo/taraV2-M16B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#taraV2-M16B-GGUF).*** + +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/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/taraV2-M16B-GGUF/resolve/main/taraV2-M16B.f16.gguf) | f16 | 6.5 | 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/taraV2-M16B.IQ4_XS.gguf b/taraV2-M16B.IQ4_XS.gguf new file mode 100644 index 0000000..0341af4 --- /dev/null +++ b/taraV2-M16B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1043465edfbb6c9aa2a30c4a1d659265828ea97c2350cde01db3dc8568b8127f +size 1840907904 diff --git a/taraV2-M16B.Q2_K.gguf b/taraV2-M16B.Q2_K.gguf new file mode 100644 index 0000000..b1756e8 --- /dev/null +++ b/taraV2-M16B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73fda4db60419156b33c7dc0e1008ec16d0de15cc14d9643fd43c3859d688e6 +size 1363936896 diff --git a/taraV2-M16B.Q3_K_L.gguf b/taraV2-M16B.Q3_K_L.gguf new file mode 100644 index 0000000..8eedc45 --- /dev/null +++ b/taraV2-M16B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5112288dec1465f531bd397674fcbdd2940c303f93825285c397d0786f16345 +size 1815348864 diff --git a/taraV2-M16B.Q3_K_M.gguf b/taraV2-M16B.Q3_K_M.gguf new file mode 100644 index 0000000..af8528a --- /dev/null +++ b/taraV2-M16B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445c411ed8fd3e3364c73584baaaa668fc900e77fb1272e7f70ada7622260fed +size 1687160448 diff --git a/taraV2-M16B.Q3_K_S.gguf b/taraV2-M16B.Q3_K_S.gguf new file mode 100644 index 0000000..1239f35 --- /dev/null +++ b/taraV2-M16B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d1fdb0f0f5919c2f22628cd38db391ea74e79f574406da5b80a511df0827863 +size 1542850176 diff --git a/taraV2-M16B.Q4_K_M.gguf b/taraV2-M16B.Q4_K_M.gguf new file mode 100644 index 0000000..96e0375 --- /dev/null +++ b/taraV2-M16B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fddbd07e834aead7a44c95a01202608860d2da8e1e10783e635ee145a8f1946a +size 2019378816 diff --git a/taraV2-M16B.Q4_K_S.gguf b/taraV2-M16B.Q4_K_S.gguf new file mode 100644 index 0000000..330cf48 --- /dev/null +++ b/taraV2-M16B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd27063acba0306e569b828a2fc024cf083d4510cfa92ec3ec2328e3093ebb9e +size 1928201856 diff --git a/taraV2-M16B.Q5_K_M.gguf b/taraV2-M16B.Q5_K_M.gguf new file mode 100644 index 0000000..d228de6 --- /dev/null +++ b/taraV2-M16B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baa724607f4efdf11e3717b256996d8a201682b4dbc3f20eaa6235b9158eece1 +size 2322155136 diff --git a/taraV2-M16B.Q5_K_S.gguf b/taraV2-M16B.Q5_K_S.gguf new file mode 100644 index 0000000..fd6e51d --- /dev/null +++ b/taraV2-M16B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38fea48c6d04369850a79766ed1031d4e33aacdad4ddadae1b3dbd22181be875 +size 2269513344 diff --git a/taraV2-M16B.Q6_K.gguf b/taraV2-M16B.Q6_K.gguf new file mode 100644 index 0000000..c87b67c --- /dev/null +++ b/taraV2-M16B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77371905a5d9649fb375f1f921c59f20050916213786a1b7e8d79b8a9d726d60 +size 2643854976 diff --git a/taraV2-M16B.Q8_0.gguf b/taraV2-M16B.Q8_0.gguf new file mode 100644 index 0000000..32adcb5 --- /dev/null +++ b/taraV2-M16B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff4ceeec8ed0cd456e200dd4271037717def1c39d5d0ee8d0849e6baf669e0d +size 3421900416 diff --git a/taraV2-M16B.f16.gguf b/taraV2-M16B.f16.gguf new file mode 100644 index 0000000..5589397 --- /dev/null +++ b/taraV2-M16B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5b8e4b427a1e052b9ec9f40b2e60459814b82efcde865b52879eb2144bbb4f +size 6433689216