commit c7e45d0b7acef592018deb5ead9912b59c09e356 Author: ModelHub XC Date: Thu Jul 16 15:37:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c23f04 --- /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 +Qwen2.5-1.5B-Instruct-Thai-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.IQ4_XS.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..6b118cc --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:133aea533f9d04d7b7c2c2bc4e505f1f58a76e5b0a094732f504f856b532dc20 +size 902183232 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q2_K.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q2_K.gguf new file mode 100644 index 0000000..86d31ec --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f72d8c025eff59f90a3075878b36477877d5c0431a16748bcc3001660b64ffe5 +size 676305216 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_L.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..1f297ad --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d6544afbc07e4cebd627e1fb446681b1b242dbf9fa7a18b1b10b56a600dd8a +size 880163136 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_M.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..bcbf5da --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8989f6ed54e5939b558e994695a205ca599f13096b4346cf900286aa3e1a5202 +size 824179008 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_S.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..0b55dfd --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14448c8e9736c7a3092735c3059997f9d7905ece8793dd64789c01995b7413f3 +size 760944960 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_0_4_4.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_0_4_4.gguf new file mode 100644 index 0000000..102f74e --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273f1bac92a3e95ab5d8f7d05ab44298b27f99148a3ea133f7089858af33f2ad +size 934955328 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_M.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..d33bfb6 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2546662a4121f2e62c392e717d3bd939c59b2746a25834806da035f5bfcd1010 +size 986048832 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_S.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..5c99916 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60510b07a1859a763e469f88c3e99305688dc1200def808d484937e0b5836921 +size 940312896 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_M.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..0e293ef --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472192074e441d8c949ff50edf5970a8902ed4d36ceafc77fcb19a0fb596d0c0 +size 1125050688 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_S.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..29f6f9b --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b09ee4c7ae72311fe80d362205e72a2c3be0af32df07af1cbe0d44cfb50665ea +size 1098729792 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q6_K.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q6_K.gguf new file mode 100644 index 0000000..a381e15 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e16966e7f1db6d89d1510d4c9f110b367027f24cd4bfbf127a563938dd2e75ee +size 1272740160 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.Q8_0.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q8_0.gguf new file mode 100644 index 0000000..eaa067d --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba30c69cbe3039fea43e21a90ccc1ae869899339830acca2932991b681f76d0 +size 1646573376 diff --git a/Qwen2.5-1.5B-Instruct-Thai-SFT.f16.gguf b/Qwen2.5-1.5B-Instruct-Thai-SFT.f16.gguf new file mode 100644 index 0000000..25ef416 --- /dev/null +++ b/Qwen2.5-1.5B-Instruct-Thai-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6ae1e3a2b0d45803b166e5644731f1a7ff4d1a05fe42c1710d1cdbe9b3ff25 +size 3093669696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7449740 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: jaeyong2/Qwen2.5-1.5B-Instruct-Thai-SFT +language: +- th +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/jaeyong2/Qwen2.5-1.5B-Instruct-Thai-SFT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-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/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF/resolve/main/Qwen2.5-1.5B-Instruct-Thai-SFT.f16.gguf) | f16 | 3.2 | 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. + +