commit ddcd7f76f313d9d03299b8e78da2f9e499db7123 Author: ModelHub XC Date: Fri Sep 18 04:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75c24be --- /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 +OpenThaiGPT-100-instruct-finetuned.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenThaiGPT-100-instruct-finetuned.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenThaiGPT-100-instruct-finetuned.IQ4_XS.gguf b/OpenThaiGPT-100-instruct-finetuned.IQ4_XS.gguf new file mode 100644 index 0000000..7640c95 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00b20fa4a208779be65df19187c5788a47dba6f0dbd644e0da63b9e33232277 +size 3698110656 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q2_K.gguf b/OpenThaiGPT-100-instruct-finetuned.Q2_K.gguf new file mode 100644 index 0000000..da4a1f8 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8108c757d401107cf2bb6d0b8a311514431337bd33bfaa899860c17c1d90f486 +size 2575896768 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q3_K_L.gguf b/OpenThaiGPT-100-instruct-finetuned.Q3_K_L.gguf new file mode 100644 index 0000000..9e56595 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69c305e9c121fc7a94ae18d0e74b31070817941dd8fa380a2a70d76962ffa4cb +size 3643924672 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q3_K_M.gguf b/OpenThaiGPT-100-instruct-finetuned.Q3_K_M.gguf new file mode 100644 index 0000000..d077033 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a52fa6f55f76f609f796d69a3583fe37cb2676f3b73913580c5105d44b4910 +size 3344818368 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q3_K_S.gguf b/OpenThaiGPT-100-instruct-finetuned.Q3_K_S.gguf new file mode 100644 index 0000000..478548a --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b422be337481ada6a00ddb660c17280e38ee6b588604e6ccdc5b705ba89fe837 +size 2995118272 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q4_K_M.gguf b/OpenThaiGPT-100-instruct-finetuned.Q4_K_M.gguf new file mode 100644 index 0000000..1ec06b1 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2298d4963178c58ffb02cd40068549a1532a88dcda88f76d8846214a7e01f02 +size 4132761792 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q4_K_S.gguf b/OpenThaiGPT-100-instruct-finetuned.Q4_K_S.gguf new file mode 100644 index 0000000..e156ecd --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:339574cbf24a68779acf2492a77ab57d0609c302b3f0613730e81a7817cf8c75 +size 3908497600 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q5_K_M.gguf b/OpenThaiGPT-100-instruct-finetuned.Q5_K_M.gguf new file mode 100644 index 0000000..133378e --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bbc0229d03869f28821a82bd26e94c113750faf1cf5f0899acec0beafce8e6 +size 4839567552 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q5_K_S.gguf b/OpenThaiGPT-100-instruct-finetuned.Q5_K_S.gguf new file mode 100644 index 0000000..8f69248 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e615ba87e041609c04b3bbb4413b26c09bdded1a99fc40aa534f547dadd4dd +size 4708102336 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q6_K.gguf b/OpenThaiGPT-100-instruct-finetuned.Q6_K.gguf new file mode 100644 index 0000000..0e7150f --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9b5262f4ccbb1c5cecfd38d451c2f87a79a367e515048c89f702ed17e3dcf8 +size 5590548672 diff --git a/OpenThaiGPT-100-instruct-finetuned.Q8_0.gguf b/OpenThaiGPT-100-instruct-finetuned.Q8_0.gguf new file mode 100644 index 0000000..a2782e6 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5282fcc003e172ccb97e4754ddabed3ad739d194896434605abc87c2f12cf21 +size 7240474816 diff --git a/OpenThaiGPT-100-instruct-finetuned.f16.gguf b/OpenThaiGPT-100-instruct-finetuned.f16.gguf new file mode 100644 index 0000000..4608111 --- /dev/null +++ b/OpenThaiGPT-100-instruct-finetuned.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5476d53b1035919e086574d96fe15df3f176a0cf5e80c3caae69d34a2cd610b6 +size 13627285696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e422c86 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: saksornr/OpenThaiGPT-100-instruct-finetuned +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/saksornr/OpenThaiGPT-100-instruct-finetuned + + +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/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenThaiGPT-100-instruct-finetuned-GGUF/resolve/main/OpenThaiGPT-100-instruct-finetuned.f16.gguf) | f16 | 13.7 | 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. + +