commit 6f6d76a1c25bd4ee5794771a9a4744032760ddfd Author: ModelHub XC Date: Thu Aug 27 06:07:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TurkLlama-Mix-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c1f49b --- /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 +TurkLlama-Mix.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.f16.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TurkLlama-Mix.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..37daf30 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: matrixportalx/TurkLlama-Mix +language: +- tr +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- meta-llama/Meta-Llama-3-8B +- ytu-ce-cosmos/Turkish-Llama-8b-Instruct-v0.1 +--- +## About + + + + + + +static quants of https://huggingface.co/matrixportalx/TurkLlama-Mix + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TurkLlama-Mix-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/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TurkLlama-Mix-GGUF/resolve/main/TurkLlama-Mix.f16.gguf) | f16 | 16.2 | 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/TurkLlama-Mix.IQ4_XS.gguf b/TurkLlama-Mix.IQ4_XS.gguf new file mode 100644 index 0000000..79ca907 --- /dev/null +++ b/TurkLlama-Mix.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e23d7123cfcab7e3714245cf15f1a25e8ff540244291a47461b9757634d7024 +size 4484363488 diff --git a/TurkLlama-Mix.Q2_K.gguf b/TurkLlama-Mix.Q2_K.gguf new file mode 100644 index 0000000..655187d --- /dev/null +++ b/TurkLlama-Mix.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1986ea7d4276ba70179b7e4d46066371b7007afb41747ddaa0195bbb9b96e69 +size 3179132128 diff --git a/TurkLlama-Mix.Q3_K_L.gguf b/TurkLlama-Mix.Q3_K_L.gguf new file mode 100644 index 0000000..54e1aee --- /dev/null +++ b/TurkLlama-Mix.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ff7e4ad5f8fd685793a38f01d032aa450f45a0f3267803796ba9b1dcfcfd62 +size 4321957088 diff --git a/TurkLlama-Mix.Q3_K_M.gguf b/TurkLlama-Mix.Q3_K_M.gguf new file mode 100644 index 0000000..493882e --- /dev/null +++ b/TurkLlama-Mix.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86ef5e9e0bf3469e3766b0c476ae283151d9cea4cbe16a8c5e75bfa54f4c95a0 +size 4018918624 diff --git a/TurkLlama-Mix.Q3_K_S.gguf b/TurkLlama-Mix.Q3_K_S.gguf new file mode 100644 index 0000000..82bc3d3 --- /dev/null +++ b/TurkLlama-Mix.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a209dea36c51fa3dada2f78c86ce956a5d5aa8e448cfd7abd6e746f4ff004fe2 +size 3664499936 diff --git a/TurkLlama-Mix.Q4_K_M.gguf b/TurkLlama-Mix.Q4_K_M.gguf new file mode 100644 index 0000000..87accb7 --- /dev/null +++ b/TurkLlama-Mix.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:998e4fc15894b93b730e41680d08ca5cb27c9a3d8e20cd4608148eaac97ff333 +size 4920734944 diff --git a/TurkLlama-Mix.Q4_K_S.gguf b/TurkLlama-Mix.Q4_K_S.gguf new file mode 100644 index 0000000..60734cf --- /dev/null +++ b/TurkLlama-Mix.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2054f309db34a747c2b82f96544e565f2e000abed11faaa2b3cad5ff7e15ba10 +size 4692669664 diff --git a/TurkLlama-Mix.Q5_K_M.gguf b/TurkLlama-Mix.Q5_K_M.gguf new file mode 100644 index 0000000..1ae2fba --- /dev/null +++ b/TurkLlama-Mix.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df82ba816aaf6b144cd61f6a17642559cf4e96c5404d2961947a396563a4c5e3 +size 5732988128 diff --git a/TurkLlama-Mix.Q5_K_S.gguf b/TurkLlama-Mix.Q5_K_S.gguf new file mode 100644 index 0000000..dc1f38e --- /dev/null +++ b/TurkLlama-Mix.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80211a5f21f97c0a1d28a52fc13e8a302ef7406c9ebed698ea8d751c589a8e1d +size 5599294688 diff --git a/TurkLlama-Mix.Q6_K.gguf b/TurkLlama-Mix.Q6_K.gguf new file mode 100644 index 0000000..ca035b5 --- /dev/null +++ b/TurkLlama-Mix.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d5822853b999dcc7066665c0dd0c12c0b9794a225cd24d2d14f21cb0446ce45 +size 6596007136 diff --git a/TurkLlama-Mix.Q8_0.gguf b/TurkLlama-Mix.Q8_0.gguf new file mode 100644 index 0000000..fd13ac3 --- /dev/null +++ b/TurkLlama-Mix.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2db236826fa2ab099cfcbbaa22c1ea3d52e00269813bf1c6ddbc1fe33abc317 +size 8540771552 diff --git a/TurkLlama-Mix.f16.gguf b/TurkLlama-Mix.f16.gguf new file mode 100644 index 0000000..49d9f0d --- /dev/null +++ b/TurkLlama-Mix.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f0027512a4ab3ade82bd997238be25b700700072c748e71ce2b896a7ebff248 +size 16068891872