commit af94be4edfaa01821d87b399cc763d010c4e2f23 Author: ModelHub XC Date: Thu May 14 18:52:30 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c7ef62 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-ThaiInstruct.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ1_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ1_M.gguf new file mode 100644 index 0000000..e68354c --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:615baca35ad938cc0067dc55cff8283583aa40998e60efe5e9b19d639b106ada +size 2161977568 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ1_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ1_S.gguf new file mode 100644 index 0000000..bbaf60b --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1099cf9a0dd26ee17e69f2298a16b89d835578ea9afb7b0486bc38843bb32fc +size 2019633376 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ2_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_M.gguf new file mode 100644 index 0000000..600178d --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b94edbd483f8411d8bbf55b6c854f52c79b833d4ebd6789c9ff3be6e10bcb94 +size 2948286688 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ2_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_S.gguf new file mode 100644 index 0000000..99c88cd --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a53f879abc3185357eeffd596019a3f9ae92b26d9b224a8a2e47f5d8dbe0aa89 +size 2758494432 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XS.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4a8c137 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3f167a1b82b9d2e97dca839e29b0b9f7c2f8b4b945344e0c2b0b14656cf488 +size 2605787360 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XXS.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a976764 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7702b13e4b368901bd0c63ed1d7e096b8a5867fad4fd81aa43463921408770 +size 2399217888 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ3_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_M.gguf new file mode 100644 index 0000000..931c882 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c8d861fd6178bc87fdf530e9252b785d516973ecee1077e653e188f53582e3 +size 3784829152 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ3_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_S.gguf new file mode 100644 index 0000000..a5d6413 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d43f258d1aac38f2c12bbcadf86c03f50d7446d05f13e61e056380c76bcc3f +size 3682330848 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XS.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XS.gguf new file mode 100644 index 0000000..1ad1dad --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81f4557b47330d5f05384aca076ef859b66ca818eac6b905e150c18d86da051 +size 3518752992 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XXS.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..1fdd2b5 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40d50ed4178f2c8bc31ae4f337cd9462a1712172be26f5c5451bca9f7baaef34 +size 3274918112 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-IQ4_XS.gguf b/Llama-3.1-8B-ThaiInstruct.i1-IQ4_XS.gguf new file mode 100644 index 0000000..bceb98c --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:009910979a7583559ea6ae4eae2447e0b89041d491b2b103ccb4972839994401 +size 4447668448 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q2_K.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q2_K.gguf new file mode 100644 index 0000000..b320c48 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff53f0be8fb7b5820be25d2e661fe9cbd12d7e2aafad0f5c51db64958c259221 +size 3179137248 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_L.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7521d79 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9422d38cee622e3a68abd3d81d1f061b6f535293e708d9eb6204a5724bc607db +size 4321962208 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_M.gguf new file mode 100644 index 0000000..2efdea6 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a30b98ef58ee97cf7ad44e5bc1dd407d4562f84448262fa34cd19678c866ca +size 4018923744 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_S.gguf new file mode 100644 index 0000000..eb49aa0 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c365d325f1bb35341de12d979e9090e24e6e6f6c074e6e69a0fd79aa81011b5 +size 3664505056 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_0.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0.gguf new file mode 100644 index 0000000..a44e5de --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbfabb561a27be91269f75130837d1d6ed0cb083d0cb163058ac3749d54ce44 +size 4675897568 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_4.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..b8cf442 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c375f2aec0f31d5700b6e8aabdf8cc9cd1feea717a4840874c57bbf3b2b6aca +size 4661217504 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_8.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..018ef49 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01aced84aa9f02abd9262e8ff0e7a50ccad9e80736f38287f7db8d0d278e6387 +size 4661217504 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_8_8.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..1625a18 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8547bce587fc1d6a8b2cbcd60583da1f861b7741051db832cfbc00f88dd2ce73 +size 4661217504 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_M.gguf new file mode 100644 index 0000000..488f619 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0440f9d1c5e578ec42fff7060bdcade0a72c2e00a30159a766d4c6cedb0e6e4f +size 4920740064 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_S.gguf new file mode 100644 index 0000000..766f551 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e2f3e177a453dd298f0fc22aaeec5d0282f5aad7141dcb345fc06e9e64aae48 +size 4692674784 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_M.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_M.gguf new file mode 100644 index 0000000..24eb6b4 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d54155f86b294ca84120b32fd6dd43b12c5953702c4d58f42bea2cd8b60d7db +size 5732993248 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_S.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3304ca7 --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:740391bdc349c33730eca04264bab969daeba87f47f1e4c642be22d1b90318c7 +size 5599299808 diff --git a/Llama-3.1-8B-ThaiInstruct.i1-Q6_K.gguf b/Llama-3.1-8B-ThaiInstruct.i1-Q6_K.gguf new file mode 100644 index 0000000..a17466a --- /dev/null +++ b/Llama-3.1-8B-ThaiInstruct.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdc1e71e344c154e919515c44454eeb17343643f93c9e7f6c88332721b69d1bb +size 6596012256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f2348da --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: Konthee/Llama-3.1-8B-ThaiInstruct +datasets: +- airesearch/WangchanThaiInstruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Konthee/Llama-3.1-8B-ThaiInstruct + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-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/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-ThaiInstruct-i1-GGUF/resolve/main/Llama-3.1-8B-ThaiInstruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..6ae62fe --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27cd71fa4629f3d4e97888f5e954d81b803d42fdb97ae7684fc7b3333d58f9a5 +size 4988157