commit 482f0e1ddcf27d2bb16ca56d859501ac385852aa Author: ModelHub XC Date: Wed Jun 17 22:31:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-tulu-2-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1dbc911 --- /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-3.1-tulu-2-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-tulu-2-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdb56f4 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: allenai/llama-3.1-tulu-2-8b +datasets: +- allenai/tulu-v2-sft-mixture +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/allenai/llama-3.1-tulu-2-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-tulu-2-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-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/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-tulu-2-8b-GGUF/resolve/main/llama-3.1-tulu-2-8b.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/llama-3.1-tulu-2-8b.IQ4_XS.gguf b/llama-3.1-tulu-2-8b.IQ4_XS.gguf new file mode 100644 index 0000000..1b7c057 --- /dev/null +++ b/llama-3.1-tulu-2-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53e9b8cc7116bf1ea47fbbe6ee0a58753a5ed339824209581fa50d09c380f677 +size 4484363936 diff --git a/llama-3.1-tulu-2-8b.Q2_K.gguf b/llama-3.1-tulu-2-8b.Q2_K.gguf new file mode 100644 index 0000000..f478b79 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b5985a622f1a7969cdf6ed6218b2e79b808a93b929b2732f3f121acc87d59c1 +size 3179132576 diff --git a/llama-3.1-tulu-2-8b.Q3_K_L.gguf b/llama-3.1-tulu-2-8b.Q3_K_L.gguf new file mode 100644 index 0000000..3c5aa4c --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b3c87d3142ed71c8b4567852724915696a9f9867885f7ab55112b5fe7ac6d4 +size 4321957536 diff --git a/llama-3.1-tulu-2-8b.Q3_K_M.gguf b/llama-3.1-tulu-2-8b.Q3_K_M.gguf new file mode 100644 index 0000000..ed21f85 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46551fac546d5b67091e7643abc0d914577cd0fa204f51637bc9891288dfe2e +size 4018919072 diff --git a/llama-3.1-tulu-2-8b.Q3_K_S.gguf b/llama-3.1-tulu-2-8b.Q3_K_S.gguf new file mode 100644 index 0000000..53d89e9 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f9204db82756b0d3533d4ad3e625d836678de7c87ddbc70a282e7562a35397e +size 3664500384 diff --git a/llama-3.1-tulu-2-8b.Q4_K_M.gguf b/llama-3.1-tulu-2-8b.Q4_K_M.gguf new file mode 100644 index 0000000..9b99594 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b712e1e893198e931a41d355d67f6ea536648a12608e15fc5c68a692eada954 +size 4920735392 diff --git a/llama-3.1-tulu-2-8b.Q4_K_S.gguf b/llama-3.1-tulu-2-8b.Q4_K_S.gguf new file mode 100644 index 0000000..5587da1 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea72422d1036ab050616140920a40ac534140d1e52b99941b60183996d9e7262 +size 4692670112 diff --git a/llama-3.1-tulu-2-8b.Q5_K_M.gguf b/llama-3.1-tulu-2-8b.Q5_K_M.gguf new file mode 100644 index 0000000..d604b04 --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3578298d8db258daace13f3d176ad3f0c5cf2e875cf673f31fa3f5942ff63218 +size 5732988576 diff --git a/llama-3.1-tulu-2-8b.Q5_K_S.gguf b/llama-3.1-tulu-2-8b.Q5_K_S.gguf new file mode 100644 index 0000000..eafb00d --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b61ddb8354fdc69cd3ad087f40d00ea23a633e556e6c70de86a479ec9aa4ed +size 5599295136 diff --git a/llama-3.1-tulu-2-8b.Q6_K.gguf b/llama-3.1-tulu-2-8b.Q6_K.gguf new file mode 100644 index 0000000..599c36b --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14cf0a682a690311b0cef37c302301d8a6e188a22393322120742055cbe187d +size 6596007584 diff --git a/llama-3.1-tulu-2-8b.Q8_0.gguf b/llama-3.1-tulu-2-8b.Q8_0.gguf new file mode 100644 index 0000000..2c58cef --- /dev/null +++ b/llama-3.1-tulu-2-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711a164ec3f6dcf5c085832a9efaaaf2a70d4ea805829532671d95f91da82adc +size 8540772000 diff --git a/llama-3.1-tulu-2-8b.f16.gguf b/llama-3.1-tulu-2-8b.f16.gguf new file mode 100644 index 0000000..893af84 --- /dev/null +++ b/llama-3.1-tulu-2-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b171fa30ecdcdb0c71da41c7d5e27fb836fd1befbc7af51bad867534ce1a58 +size 16068892320