commit 8d542a9d66fee1cd4927832372ed152d039a7446 Author: ModelHub XC Date: Mon Jul 13 00:49:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/openthaigpt-1.0.0-7b-chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b30990 --- /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-1.0.0-7b-chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.f16.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +openthaigpt-1.0.0-7b-chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9be58f0 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: openthaigpt/openthaigpt-1.0.0-7b-chat +language: +- th +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +tags: +- openthaigpt +- llama +--- +## About + + + + + + +static quants of https://huggingface.co/openthaigpt/openthaigpt-1.0.0-7b-chat + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-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/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.IQ4_XS.gguf) | IQ4_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q6_K.gguf) | Q6_K | 5.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/openthaigpt-1.0.0-7b-chat-GGUF/resolve/main/openthaigpt-1.0.0-7b-chat.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. + + diff --git a/openthaigpt-1.0.0-7b-chat.IQ4_XS.gguf b/openthaigpt-1.0.0-7b-chat.IQ4_XS.gguf new file mode 100644 index 0000000..20e038e --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1d29db9d8123fb7632667256275ac31ff94db462f9ee9e0038c88f05e854ac +size 3698110304 diff --git a/openthaigpt-1.0.0-7b-chat.Q2_K.gguf b/openthaigpt-1.0.0-7b-chat.Q2_K.gguf new file mode 100644 index 0000000..fce17e3 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef75a58b7e6750cd08999c34b6d3f77c408f18c41b6f3a9386e0ae984a856d4 +size 2575896416 diff --git a/openthaigpt-1.0.0-7b-chat.Q3_K_L.gguf b/openthaigpt-1.0.0-7b-chat.Q3_K_L.gguf new file mode 100644 index 0000000..dabf9d4 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963eb818687e8a76ece3b6064efd1c66e00d1f9bb51d3dad71b6f208aadeb9bc +size 3643924320 diff --git a/openthaigpt-1.0.0-7b-chat.Q3_K_M.gguf b/openthaigpt-1.0.0-7b-chat.Q3_K_M.gguf new file mode 100644 index 0000000..1ccc2ec --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996ec299d757dbdeb45e82114c716505463edd56433178c39ab328ad966d3159 +size 3344818016 diff --git a/openthaigpt-1.0.0-7b-chat.Q3_K_S.gguf b/openthaigpt-1.0.0-7b-chat.Q3_K_S.gguf new file mode 100644 index 0000000..4c7353e --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b81d3396d769ad7c48513d8dbdf08a020296d964fc33dd813af4203ec09ee3a +size 2995117920 diff --git a/openthaigpt-1.0.0-7b-chat.Q4_K_M.gguf b/openthaigpt-1.0.0-7b-chat.Q4_K_M.gguf new file mode 100644 index 0000000..c85e330 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b7c24b3e7c0f23d742cc7f114e6e6ed148d6437a8589d3c84734ed9f64bde8 +size 4132761440 diff --git a/openthaigpt-1.0.0-7b-chat.Q4_K_S.gguf b/openthaigpt-1.0.0-7b-chat.Q4_K_S.gguf new file mode 100644 index 0000000..f073476 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff9a8857cd6e1ae938256e196390ed64626bae192cd47e2f54d77a4775125c7 +size 3908497248 diff --git a/openthaigpt-1.0.0-7b-chat.Q5_K_M.gguf b/openthaigpt-1.0.0-7b-chat.Q5_K_M.gguf new file mode 100644 index 0000000..1b75f32 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:530ed36a43e665b6956468e2efe0affc759ebc1b65c97b6eed2ecb24667181f0 +size 4839567200 diff --git a/openthaigpt-1.0.0-7b-chat.Q5_K_S.gguf b/openthaigpt-1.0.0-7b-chat.Q5_K_S.gguf new file mode 100644 index 0000000..b9e83f5 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:184784cbc894a46fd6d584968ae515179122ea7f3995b654572518150b78d447 +size 4708101984 diff --git a/openthaigpt-1.0.0-7b-chat.Q6_K.gguf b/openthaigpt-1.0.0-7b-chat.Q6_K.gguf new file mode 100644 index 0000000..1943c59 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d0815547a92301226a61dd11d6624e2fcb79b1005808de0722d7fca1c8a9a8 +size 5590548320 diff --git a/openthaigpt-1.0.0-7b-chat.Q8_0.gguf b/openthaigpt-1.0.0-7b-chat.Q8_0.gguf new file mode 100644 index 0000000..1e26d4c --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4970e0498129c1582dd86e2ce0e7f89bdd3892b4e3938f9671947fc310c40e99 +size 7240474464 diff --git a/openthaigpt-1.0.0-7b-chat.f16.gguf b/openthaigpt-1.0.0-7b-chat.f16.gguf new file mode 100644 index 0000000..a161562 --- /dev/null +++ b/openthaigpt-1.0.0-7b-chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a747c07dc12fe2e5578b190c344d85bd7fe1765a08b018b97e57487f035e6b90 +size 13627285344