commit b48181fa7c00ff482d5a7331cdeea3a7b8f6a2c5 Author: ModelHub XC Date: Thu Jun 18 10:09:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-typhoon2-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b93b18 --- /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 +llama3.1-typhoon2-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-typhoon2-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..000deb3 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: typhoon-ai/llama3.1-typhoon2-8b +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/typhoon-ai/llama3.1-typhoon2-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1-typhoon2-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-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/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-typhoon2-8b-GGUF/resolve/main/llama3.1-typhoon2-8b.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/llama3.1-typhoon2-8b.IQ4_XS.gguf b/llama3.1-typhoon2-8b.IQ4_XS.gguf new file mode 100644 index 0000000..0f9c312 --- /dev/null +++ b/llama3.1-typhoon2-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e858d356e36df5e61154ff7a7744d6a31d95f815b29366d5a35b12772885d669 +size 4484367776 diff --git a/llama3.1-typhoon2-8b.Q2_K.gguf b/llama3.1-typhoon2-8b.Q2_K.gguf new file mode 100644 index 0000000..21348d3 --- /dev/null +++ b/llama3.1-typhoon2-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f897eb96b7f396b69b7fc3b006c484016b363000a500c28cc7c9b71db5d1dddd +size 3179136416 diff --git a/llama3.1-typhoon2-8b.Q3_K_L.gguf b/llama3.1-typhoon2-8b.Q3_K_L.gguf new file mode 100644 index 0000000..ea9111e --- /dev/null +++ b/llama3.1-typhoon2-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e37ed2e71bd95fb50b102cd366fe013c06dd687dcca6342d28e51981b7ea050 +size 4321961376 diff --git a/llama3.1-typhoon2-8b.Q3_K_M.gguf b/llama3.1-typhoon2-8b.Q3_K_M.gguf new file mode 100644 index 0000000..9098812 --- /dev/null +++ b/llama3.1-typhoon2-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19cd26602513bd7a5564c7946729726378fb9ffd4f9ccd6ef42d581b0ac9e789 +size 4018922912 diff --git a/llama3.1-typhoon2-8b.Q3_K_S.gguf b/llama3.1-typhoon2-8b.Q3_K_S.gguf new file mode 100644 index 0000000..f24104e --- /dev/null +++ b/llama3.1-typhoon2-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a532dcc94d0c29a2a4e2f3d826358d5a9dc33b19ca40fba4357aa0683fd285 +size 3664504224 diff --git a/llama3.1-typhoon2-8b.Q4_K_M.gguf b/llama3.1-typhoon2-8b.Q4_K_M.gguf new file mode 100644 index 0000000..01a3137 --- /dev/null +++ b/llama3.1-typhoon2-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2fc4280634f5faec2be1ad7fc4b5b7874c71d1df9fb460ef203a7c04316705 +size 4920739232 diff --git a/llama3.1-typhoon2-8b.Q4_K_S.gguf b/llama3.1-typhoon2-8b.Q4_K_S.gguf new file mode 100644 index 0000000..706e14f --- /dev/null +++ b/llama3.1-typhoon2-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97bd6c0042c5c61f3338818766d9679571fc4676e02d5709fd971cf750aa0e4 +size 4692673952 diff --git a/llama3.1-typhoon2-8b.Q5_K_M.gguf b/llama3.1-typhoon2-8b.Q5_K_M.gguf new file mode 100644 index 0000000..896223d --- /dev/null +++ b/llama3.1-typhoon2-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac37828971069c23d904e4fcb01442973651902eaadb13dc4698e50cd72e4b61 +size 5732992416 diff --git a/llama3.1-typhoon2-8b.Q5_K_S.gguf b/llama3.1-typhoon2-8b.Q5_K_S.gguf new file mode 100644 index 0000000..05ad644 --- /dev/null +++ b/llama3.1-typhoon2-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a3d1a9873e89e9c624d3bfba159e1ad10173b0b8c5d614a7b020058ddbf2ed +size 5599298976 diff --git a/llama3.1-typhoon2-8b.Q6_K.gguf b/llama3.1-typhoon2-8b.Q6_K.gguf new file mode 100644 index 0000000..6ec2daf --- /dev/null +++ b/llama3.1-typhoon2-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c519c4f73630cb7e3585fd4d4ec247ce9b23978b6e2f24f5b21d25a8031de5 +size 6596011424 diff --git a/llama3.1-typhoon2-8b.Q8_0.gguf b/llama3.1-typhoon2-8b.Q8_0.gguf new file mode 100644 index 0000000..da557d0 --- /dev/null +++ b/llama3.1-typhoon2-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a392be91835452b324413b09a7e9ab2ae44dfb06bcdd1232539e629d19ff070c +size 8540775840 diff --git a/llama3.1-typhoon2-8b.f16.gguf b/llama3.1-typhoon2-8b.f16.gguf new file mode 100644 index 0000000..a0980fd --- /dev/null +++ b/llama3.1-typhoon2-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366642492cecdd19976d00599a64dc1bc0753d13fbc53a560de626f79b6d432f +size 16068896160