commit 214eca65aa66df7e4b2c3ff20350276959719b9b Author: ModelHub XC Date: Mon Sep 14 20:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MKLLM-7B-Translate-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88e1925 --- /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 +MKLLM-7B-Translate.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MKLLM-7B-Translate.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MKLLM-7B-Translate.IQ4_XS.gguf b/MKLLM-7B-Translate.IQ4_XS.gguf new file mode 100644 index 0000000..41831f2 --- /dev/null +++ b/MKLLM-7B-Translate.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6dbf4b88cd49ddff54b94bb96b7f228d6fc6e85d8ac159d04f7dac78aaafbb1 +size 3944389248 diff --git a/MKLLM-7B-Translate.Q2_K.gguf b/MKLLM-7B-Translate.Q2_K.gguf new file mode 100644 index 0000000..fda46ea --- /dev/null +++ b/MKLLM-7B-Translate.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da2da53ba30db8260194ed815f201d0417d710a9f6639e22730239622f961346 +size 2719242880 diff --git a/MKLLM-7B-Translate.Q3_K_L.gguf b/MKLLM-7B-Translate.Q3_K_L.gguf new file mode 100644 index 0000000..cae2787 --- /dev/null +++ b/MKLLM-7B-Translate.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87c83b0892f3b2a1068a9f63187911d8ea80dd54bb17903a0659ffcd75443435 +size 3822025344 diff --git a/MKLLM-7B-Translate.Q3_K_M.gguf b/MKLLM-7B-Translate.Q3_K_M.gguf new file mode 100644 index 0000000..b9d49c5 --- /dev/null +++ b/MKLLM-7B-Translate.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb6ba70ffd396ab0d8e37c134b4eee47cfee16f5a27884c8af1166b44b2e0d05 +size 3518986880 diff --git a/MKLLM-7B-Translate.Q3_K_S.gguf b/MKLLM-7B-Translate.Q3_K_S.gguf new file mode 100644 index 0000000..2f104d8 --- /dev/null +++ b/MKLLM-7B-Translate.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c58f9eeec7499260ce775c2afeefe4ef19ea752e2d2ce9812f380009605405 +size 3164568192 diff --git a/MKLLM-7B-Translate.Q4_K_M.gguf b/MKLLM-7B-Translate.Q4_K_M.gguf new file mode 100644 index 0000000..2259824 --- /dev/null +++ b/MKLLM-7B-Translate.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:213b850dfe57a954e764335c8be737726394f5df85398b89320ed8bd1e6ffdbc +size 4368439936 diff --git a/MKLLM-7B-Translate.Q4_K_S.gguf b/MKLLM-7B-Translate.Q4_K_S.gguf new file mode 100644 index 0000000..d5be7a4 --- /dev/null +++ b/MKLLM-7B-Translate.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae7c8e5fd3395a3b7e53299ae5ae734133195da9876bbd0aa1dc4f8be2a2ecbb +size 4140374656 diff --git a/MKLLM-7B-Translate.Q5_K_M.gguf b/MKLLM-7B-Translate.Q5_K_M.gguf new file mode 100644 index 0000000..7464353 --- /dev/null +++ b/MKLLM-7B-Translate.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea9f54ce705689dce39c901db43480061fba828481cd3f751eef728db72f875 +size 5131410048 diff --git a/MKLLM-7B-Translate.Q5_K_S.gguf b/MKLLM-7B-Translate.Q5_K_S.gguf new file mode 100644 index 0000000..23cf377 --- /dev/null +++ b/MKLLM-7B-Translate.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17931e64ea87158e24ac2ec4454731b84459116120351d68071d323502d7c4a +size 4997716608 diff --git a/MKLLM-7B-Translate.Q6_K.gguf b/MKLLM-7B-Translate.Q6_K.gguf new file mode 100644 index 0000000..d4dd4de --- /dev/null +++ b/MKLLM-7B-Translate.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30334507a8a87494ee938339311a3ff6ea6f785b92845e820917cb04c245340d +size 5942065792 diff --git a/MKLLM-7B-Translate.Q8_0.gguf b/MKLLM-7B-Translate.Q8_0.gguf new file mode 100644 index 0000000..e6746eb --- /dev/null +++ b/MKLLM-7B-Translate.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99344e64e8df5d66003ea13d3969f40524540b33bf6c38b964b9bc9dd07998fc +size 7695858304 diff --git a/MKLLM-7B-Translate.f16.gguf b/MKLLM-7B-Translate.f16.gguf new file mode 100644 index 0000000..1adcf77 --- /dev/null +++ b/MKLLM-7B-Translate.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3a9e09ce44bffcbec8e0b4ea0d26abc7911975f83dbdaffc1039c0de2a26ab0 +size 14484732544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de829cd --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: trajkovnikola/MKLLM-7B-Translate +language: +- mk +- en +library_name: transformers +license: cc-by-nc-sa-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- axolotl +--- +## About + + + + + + +static quants of https://huggingface.co/trajkovnikola/MKLLM-7B-Translate + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MKLLM-7B-Translate-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MKLLM-7B-Translate-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/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MKLLM-7B-Translate-GGUF/resolve/main/MKLLM-7B-Translate.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. + +