commit 9b795013c566963daf4a43e17097acd2ed75b4f1 Author: ModelHub XC Date: Tue Jun 16 09:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/License-Llama3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..24c35a1 --- /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 +License-Llama3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +License-Llama3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/License-Llama3-8B.IQ4_XS.gguf b/License-Llama3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..6ad58f5 --- /dev/null +++ b/License-Llama3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1b6e492823feb84df4d75c82a06ba7b364a90e0c060bd33505a23dda0625a4 +size 4484363424 diff --git a/License-Llama3-8B.Q2_K.gguf b/License-Llama3-8B.Q2_K.gguf new file mode 100644 index 0000000..7116f38 --- /dev/null +++ b/License-Llama3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3affa16d336608d18d4f73b2d5d88d0696497da0681db0fd6c9fa236cca8007b +size 3179132064 diff --git a/License-Llama3-8B.Q3_K_L.gguf b/License-Llama3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..03429ce --- /dev/null +++ b/License-Llama3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3466b46f98fa8d79e896139ba8c6c2313b4f968ca88a12e727d8495728c3219b +size 4321957024 diff --git a/License-Llama3-8B.Q3_K_M.gguf b/License-Llama3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..4e4696b --- /dev/null +++ b/License-Llama3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c54e0859af620993c90549764f4c49596ed0996ca190bb7ac509eb060b8364 +size 4018918560 diff --git a/License-Llama3-8B.Q3_K_S.gguf b/License-Llama3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..fba1f82 --- /dev/null +++ b/License-Llama3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7e87f623849438c4db086e4d859eef6edf6ec30287693a9e72abed1034595e +size 3664499872 diff --git a/License-Llama3-8B.Q4_K_M.gguf b/License-Llama3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..6de5fb0 --- /dev/null +++ b/License-Llama3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88caddbd766fea833ec1aa8efc35ae0a6a54bef2e7c1de49dca92b2adeb02f5 +size 4920734880 diff --git a/License-Llama3-8B.Q4_K_S.gguf b/License-Llama3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..018cce6 --- /dev/null +++ b/License-Llama3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c92581c0ee78f80caa3a0ddef025439b19e5e94a8937c4eb57e86b90d61879a +size 4692669600 diff --git a/License-Llama3-8B.Q5_K_M.gguf b/License-Llama3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a90f893 --- /dev/null +++ b/License-Llama3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76c6cec6b55c242ee23c803544ef6b33026967e390531f9cf5e66daf7488a7d +size 5732988064 diff --git a/License-Llama3-8B.Q5_K_S.gguf b/License-Llama3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..1b9c2e6 --- /dev/null +++ b/License-Llama3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84880f1c3bf566273f4e90d01261f22fbe256f869870d9cea7f653848da943b0 +size 5599294624 diff --git a/License-Llama3-8B.Q6_K.gguf b/License-Llama3-8B.Q6_K.gguf new file mode 100644 index 0000000..4b5dc8f --- /dev/null +++ b/License-Llama3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68536995717dda38bf518017955cb474254cd41a0b05da15dfd0e54c77ddb74 +size 6596007072 diff --git a/License-Llama3-8B.Q8_0.gguf b/License-Llama3-8B.Q8_0.gguf new file mode 100644 index 0000000..cc17844 --- /dev/null +++ b/License-Llama3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce94a386dbc0fed088fcdb5cc0bda9a06633ffbbf31f2c536dfe635a7bbf1fd5 +size 8540771488 diff --git a/License-Llama3-8B.f16.gguf b/License-Llama3-8B.f16.gguf new file mode 100644 index 0000000..1dbc74c --- /dev/null +++ b/License-Llama3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92fc3a6c257d0946824b743c2b12909c1fac90393b0c00f27b2f5031d89570ee +size 16068891808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..71ea875 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: AnonymousAuthors/License-Llama3-8B +datasets: +- AnonymousAuthors/OSS-License-Terms +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- pytorch +- llama +- llama-3 +--- +## About + + + + + + +static quants of https://huggingface.co/AnonymousAuthors/License-Llama3-8B + + +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/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/License-Llama3-8B-GGUF/resolve/main/License-Llama3-8B.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. + +