commit d99f21cdaa84ee930928e7d712ddf77a7dd624fe Author: ModelHub XC Date: Wed Sep 16 10:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..41f9d58 --- /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 +THaLLE-0.2-ThaiLLM-8B-fa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +THaLLE-0.2-ThaiLLM-8B-fa.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..66e3809 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: KBTG-Labs/THaLLE-0.2-ThaiLLM-8B-fa +language: +- en +- th +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- finance +- mergekit +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/KBTG-Labs/THaLLE-0.2-ThaiLLM-8B-fa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#THaLLE-0.2-ThaiLLM-8B-fa-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-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/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/THaLLE-0.2-ThaiLLM-8B-fa-GGUF/resolve/main/THaLLE-0.2-ThaiLLM-8B-fa.f16.gguf) | f16 | 16.5 | 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/THaLLE-0.2-ThaiLLM-8B-fa.IQ4_XS.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.IQ4_XS.gguf new file mode 100644 index 0000000..2a2fa67 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9780fb63b4675da6929c426727ca9cae08307bcee0b48306146188c6e5a8e3ee +size 4591813248 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q2_K.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q2_K.gguf new file mode 100644 index 0000000..787f835 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21260df3fb504060ea6a7988dd11185a8593fb89baed061b6cc8c2a039f6f94 +size 3280471616 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_L.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_L.gguf new file mode 100644 index 0000000..828cc74 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa547befdef8bed7bcf98ae12fd44d66f84bf677d5266a9e8dce11954701e39c +size 4430021728 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_M.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_M.gguf new file mode 100644 index 0000000..df9457d --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:745d6e5f4d7381d235d98b414be6da401e106e91dfe48955d3bee7997a9a5448 +size 4122788960 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_S.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_S.gguf new file mode 100644 index 0000000..7ccc411 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bb4d857f7893a431b75c7a369b802bfdcb4397788dd03c4998e3e369b977fba +size 3768239200 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_M.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_M.gguf new file mode 100644 index 0000000..7168ad3 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:104bfd75fd5b97608b959f3b56554f73cf6a9215c32f8b6262254a7545a1cc36 +size 5026266368 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_S.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_S.gguf new file mode 100644 index 0000000..d21636f --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4418cd5af08e01b7fb1c9cfcc0d457757a9bc6a86a8f30605a97640fbb679c22 +size 4800494848 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_M.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_M.gguf new file mode 100644 index 0000000..ca6adc5 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b1a57bd67215062f385405bb616f7e237c80b3ffe69caaa2cf66d127a936dd1 +size 5849458432 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_S.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_S.gguf new file mode 100644 index 0000000..422b5d7 --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f60bceb3512b5e1998a3b4fe641a861185dd0d25a6eba324bba9b782cf4e87 +size 5719107328 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q6_K.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q6_K.gguf new file mode 100644 index 0000000..cb0ff6f --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02a54d00fbda20849019f59e5ca83f4bbae49067b5604209e141bc37bfef516b +size 6724100000 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.Q8_0.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.Q8_0.gguf new file mode 100644 index 0000000..1131dba --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef0895f69085b80f25ea96adb3be34fabaa4bc2a591a6ec40ed6994f09ce880 +size 8707189344 diff --git a/THaLLE-0.2-ThaiLLM-8B-fa.f16.gguf b/THaLLE-0.2-ThaiLLM-8B-fa.f16.gguf new file mode 100644 index 0000000..e87bc3d --- /dev/null +++ b/THaLLE-0.2-ThaiLLM-8B-fa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2646f548e362590262f68b38c42d465c50d2fd19b43f4afc118a7b3583ec40 +size 16383664224