commit 35e432d1464b80e55282f4499816ca745fd5d981 Author: ModelHub XC Date: Thu Jun 18 10:44:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama_3.1_8B_Thai_instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f499d6a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +llama_3.1_8B_Thai_instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama_3.1_8B_Thai_instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8a04933 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: Suraponn/llama_3.1_8B_Thai_instruct +datasets: +- Suraponn/thai_instruction_sft +language: +- th +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Suraponn/llama_3.1_8B_Thai_instruct + + +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/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama_3.1_8B_Thai_instruct-GGUF/resolve/main/llama_3.1_8B_Thai_instruct.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/llama_3.1_8B_Thai_instruct.IQ3_M.gguf b/llama_3.1_8B_Thai_instruct.IQ3_M.gguf new file mode 100644 index 0000000..49af896 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d408c0abd15a24c938ebc627afe5b648bb2917953db3f78b23765fd1f44950 +size 3784824384 diff --git a/llama_3.1_8B_Thai_instruct.IQ3_S.gguf b/llama_3.1_8B_Thai_instruct.IQ3_S.gguf new file mode 100644 index 0000000..1169a6b --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f061143c087625d6ebda016069b78d3629562e0302a7bc5277117d1e8797ae94 +size 3682326080 diff --git a/llama_3.1_8B_Thai_instruct.IQ3_XS.gguf b/llama_3.1_8B_Thai_instruct.IQ3_XS.gguf new file mode 100644 index 0000000..d1cb148 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc3eebe5325050dc18993d349de8363b9d65a22a073384df478154ca106dd0c +size 3518748224 diff --git a/llama_3.1_8B_Thai_instruct.IQ4_XS.gguf b/llama_3.1_8B_Thai_instruct.IQ4_XS.gguf new file mode 100644 index 0000000..cce9c03 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db620c9fdd7e9077399445e36f4b13f20ed4473e342026a388d265741d6c001 +size 4484363840 diff --git a/llama_3.1_8B_Thai_instruct.Q2_K.gguf b/llama_3.1_8B_Thai_instruct.Q2_K.gguf new file mode 100644 index 0000000..9cf36bf --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d26333e852c604bc4e14582c75b97cc679238f6088995a15bcc946bb8b0c139d +size 3179132480 diff --git a/llama_3.1_8B_Thai_instruct.Q3_K_L.gguf b/llama_3.1_8B_Thai_instruct.Q3_K_L.gguf new file mode 100644 index 0000000..1051935 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fb19198945bd185f2c08b5c267db5dacff9be460a4aaf65a1526b8ccdefcd57 +size 4321957440 diff --git a/llama_3.1_8B_Thai_instruct.Q3_K_M.gguf b/llama_3.1_8B_Thai_instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e711a59 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee297ac8b453997804f5afa5b50bcd80a93205da1a338dd4370b5c2336516648 +size 4018918976 diff --git a/llama_3.1_8B_Thai_instruct.Q3_K_S.gguf b/llama_3.1_8B_Thai_instruct.Q3_K_S.gguf new file mode 100644 index 0000000..b74c1f5 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca99c43199636d3a975d6f2a353f85a506d1fc727ff60f0f29bbedc1850dc1b7 +size 3664500288 diff --git a/llama_3.1_8B_Thai_instruct.Q4_K_M.gguf b/llama_3.1_8B_Thai_instruct.Q4_K_M.gguf new file mode 100644 index 0000000..d063de4 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae784f497c7ca3f09a195ab93ca56f621957abf8f29b6d1feb4155b58438f81d +size 4920735296 diff --git a/llama_3.1_8B_Thai_instruct.Q4_K_S.gguf b/llama_3.1_8B_Thai_instruct.Q4_K_S.gguf new file mode 100644 index 0000000..aa8b7f9 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b44b57ec290c22dbd14b26dd785d1c2ab6002719fc4891c571744c2d841ce51f +size 4692670016 diff --git a/llama_3.1_8B_Thai_instruct.Q5_K_M.gguf b/llama_3.1_8B_Thai_instruct.Q5_K_M.gguf new file mode 100644 index 0000000..f1e36c0 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3badea686a3b8a80a5f9af90e001b309e6d17bb4ba460333956d8d6616ac4a +size 5732988480 diff --git a/llama_3.1_8B_Thai_instruct.Q5_K_S.gguf b/llama_3.1_8B_Thai_instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f23b370 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19c38dd80e5ff315ae64c3798e32fca5d53705cd6e0f1cb00ddddbf29b3b6437 +size 5599295040 diff --git a/llama_3.1_8B_Thai_instruct.Q6_K.gguf b/llama_3.1_8B_Thai_instruct.Q6_K.gguf new file mode 100644 index 0000000..54ff236 --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e947719320dc76092e5cd827e187c921634d11d1e625dcf9b2a42044fa4b7385 +size 6596007488 diff --git a/llama_3.1_8B_Thai_instruct.Q8_0.gguf b/llama_3.1_8B_Thai_instruct.Q8_0.gguf new file mode 100644 index 0000000..5ec843c --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5e99f03f44dde4f4881cb8baab726e8b7c583a29a093f284e4eee98cdbe01b +size 8540771904 diff --git a/llama_3.1_8B_Thai_instruct.f16.gguf b/llama_3.1_8B_Thai_instruct.f16.gguf new file mode 100644 index 0000000..c50c0ed --- /dev/null +++ b/llama_3.1_8B_Thai_instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923d092ac06df104e4ba9b1d55629f69d6de47377d971f20076b685ea60ac2ff +size 16068892224