commit 6e7c18f59f11b90476ad11c0df650f85bd486ff8 Author: ModelHub XC Date: Thu Jun 18 06:17:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e5e6d1b --- /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 +llama-3.2-typhoon-t1-3b-research-preview.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-typhoon-t1-3b-research-preview.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0eea7d3 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: typhoon-ai/llama3.2-typhoon2-t1-3b-research-preview +datasets: +- scb10x/typhoon-t1-3b-research-preview-data +language: +- en +- th +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/typhoon-ai/llama3.2-typhoon2-t1-3b-research-preview + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.2-typhoon-t1-3b-research-preview-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-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/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.2-typhoon-t1-3b-research-preview-GGUF/resolve/main/llama-3.2-typhoon-t1-3b-research-preview.f16.gguf) | f16 | 6.5 | 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/llama-3.2-typhoon-t1-3b-research-preview.IQ4_XS.gguf b/llama-3.2-typhoon-t1-3b-research-preview.IQ4_XS.gguf new file mode 100644 index 0000000..9ffe980 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04542ec18ba82e72b2195725b3bef7ded76a3d34961e947bb739bd51eb2dfae5 +size 1840906080 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q2_K.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q2_K.gguf new file mode 100644 index 0000000..c922cdd --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99b98290ecc4f99b129dd73c3939fee2271fbe9271ed1f0d981c1094a9788642 +size 1363935072 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_L.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_L.gguf new file mode 100644 index 0000000..19684e4 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44449d3b992ac8783a801c15e594eb79de19bf09efa97469866111aac7dfebec +size 1815347040 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_M.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_M.gguf new file mode 100644 index 0000000..3aa9852 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf9b8fe37744f29de06f9a64c940c51e4e8d1b6df015acfec221e81126d39eb +size 1687158624 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_S.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_S.gguf new file mode 100644 index 0000000..a5e0d83 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81f09b1335b9b0664d8d09d48b124d06630589fedb4e03ae0b0e5e7aef2c25bb +size 1542848352 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_M.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_M.gguf new file mode 100644 index 0000000..5aa7a16 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02442aace7f554b44090b87af826aa2c76308b14ab0dec6bec4cb5ab8416cbb1 +size 2019376992 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_S.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_S.gguf new file mode 100644 index 0000000..e9b996d --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0d9771fc39caa875ab7153db241aa30e73dc7ad6c9bb09b9c843b3334d3b5b8 +size 1928200032 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_M.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_M.gguf new file mode 100644 index 0000000..73bb161 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b08767f9f04cb46204d9d3f6accc651ba96f5094d8d70ca3fe0b7ee8973550a0 +size 2322153312 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_S.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_S.gguf new file mode 100644 index 0000000..38c7c39 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fd62c50ac09ba22c6cbd2826c146356085c7ea6143f6baa10c2e6d2cf5db1a +size 2269511520 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q6_K.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q6_K.gguf new file mode 100644 index 0000000..2b46f40 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab08e705645df852926c0955e35ff2dd73e55336befde6f2271c203994cbba22 +size 2643853152 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.Q8_0.gguf b/llama-3.2-typhoon-t1-3b-research-preview.Q8_0.gguf new file mode 100644 index 0000000..b2704f2 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21767c136a4c03964256f6524014f2e099da8562a2f61fb2947babf01e3374ac +size 3421898592 diff --git a/llama-3.2-typhoon-t1-3b-research-preview.f16.gguf b/llama-3.2-typhoon-t1-3b-research-preview.f16.gguf new file mode 100644 index 0000000..1ea8497 --- /dev/null +++ b/llama-3.2-typhoon-t1-3b-research-preview.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56c472138656f71a73d16b6242b8661d9e8a533c74aab8b466b2e5d6feb26ac +size 6433687392