commit f19bd1ad828924107c47bb0c5c5c7dedae526f0f Author: ModelHub XC Date: Sat May 9 05:42:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c11b38f --- /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-wangchanX-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-wangchanX-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..f6bcfb4 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: monshinawatra/llama-3.1-8b-wangchanX-instruct +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/monshinawatra/llama-3.1-8b-wangchanX-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-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-wangchanX-instruct-GGUF/resolve/main/llama-3.1-8b-wangchanX-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-wangchanX-instruct.IQ3_M.gguf b/llama-3.1-8b-wangchanX-instruct.IQ3_M.gguf new file mode 100644 index 0000000..0692b55 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:050cbafef044fb1647074484f2eb8ce34193481508749c26087fbb336bd0fec4 +size 3784824128 diff --git a/llama-3.1-8b-wangchanX-instruct.IQ3_S.gguf b/llama-3.1-8b-wangchanX-instruct.IQ3_S.gguf new file mode 100644 index 0000000..e75418b --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11fe939d1b1dc7cb84e152a4b9ddf073a88e936b634753b520e93e15af800bc8 +size 3682325824 diff --git a/llama-3.1-8b-wangchanX-instruct.IQ3_XS.gguf b/llama-3.1-8b-wangchanX-instruct.IQ3_XS.gguf new file mode 100644 index 0000000..7cd2a11 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bbb6530ae65c5d7a7116dc5a4d0d5f552e1038fc28aef6eff34595481456810 +size 3518747968 diff --git a/llama-3.1-8b-wangchanX-instruct.IQ4_XS.gguf b/llama-3.1-8b-wangchanX-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..600cc28 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09cd490889417f0430e4f185005040320441649eba53191aa4974111e64fb03b +size 4484363584 diff --git a/llama-3.1-8b-wangchanX-instruct.Q2_K.gguf b/llama-3.1-8b-wangchanX-instruct.Q2_K.gguf new file mode 100644 index 0000000..ca7abfe --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:940c3eab2daf9e3f0df1ffc6f7954c9eee43a712109d93ed147f49cf64759831 +size 3179132224 diff --git a/llama-3.1-8b-wangchanX-instruct.Q3_K_L.gguf b/llama-3.1-8b-wangchanX-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c0b26b6 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a4c8a5a44282831c41eb58337cfd094797f7f183b58ae1fee043145579cd84e +size 4321957184 diff --git a/llama-3.1-8b-wangchanX-instruct.Q3_K_M.gguf b/llama-3.1-8b-wangchanX-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..e6ddb93 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ec05988a024e6d1a878c0e7fa0a2b47ab1673f79641b34c0582249559b889ea +size 4018918720 diff --git a/llama-3.1-8b-wangchanX-instruct.Q3_K_S.gguf b/llama-3.1-8b-wangchanX-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..4fd9eb6 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6288b29cba98ddc18df22511bfbe3b5834c4c014af606de6435111f5f06344e +size 3664500032 diff --git a/llama-3.1-8b-wangchanX-instruct.Q4_K_M.gguf b/llama-3.1-8b-wangchanX-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..b00cbac --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1428f5e31589a5394b7d04f6be1914e1efc8d0de7146c6c061263b555249e20f +size 4920735040 diff --git a/llama-3.1-8b-wangchanX-instruct.Q4_K_S.gguf b/llama-3.1-8b-wangchanX-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..5bc21b7 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cd97061f36f38581a4ca62807a94972cf6be82e6e30f2c1fbb7e2c7eaa60c5b +size 4692669760 diff --git a/llama-3.1-8b-wangchanX-instruct.Q5_K_M.gguf b/llama-3.1-8b-wangchanX-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..9aaadc4 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf80ad1475c8a605804ad6211739d3a4216652555d5c10da76f927c219e8ddd0 +size 5732988224 diff --git a/llama-3.1-8b-wangchanX-instruct.Q5_K_S.gguf b/llama-3.1-8b-wangchanX-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..14857b3 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e8c4c7118ca5731aec2c1b200cfd587ed9c69abf68c42205ea45987ea63e1d +size 5599294784 diff --git a/llama-3.1-8b-wangchanX-instruct.Q6_K.gguf b/llama-3.1-8b-wangchanX-instruct.Q6_K.gguf new file mode 100644 index 0000000..baad6ca --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6238a737fa8702c9065d142ee65c81d895abe9e93c87eac7a06536e6b635a1 +size 6596007232 diff --git a/llama-3.1-8b-wangchanX-instruct.Q8_0.gguf b/llama-3.1-8b-wangchanX-instruct.Q8_0.gguf new file mode 100644 index 0000000..eabb204 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1013819f6ddcf66cd229a8f8608ae0164367b32a896a5cfecff31699ce36097 +size 8540771648 diff --git a/llama-3.1-8b-wangchanX-instruct.f16.gguf b/llama-3.1-8b-wangchanX-instruct.f16.gguf new file mode 100644 index 0000000..50a69b9 --- /dev/null +++ b/llama-3.1-8b-wangchanX-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa34a9746502e2a56f1acf79b6ce0b71d42cf0524f53fef4394cc20d1cb4b2ec +size 16068891968