commit 63d08bbeae51cfc47630fdd9874e72d82b09e282 Author: ModelHub XC Date: Mon Jul 13 00:46:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/social-llama-3-8b-beta-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..56d0f3e --- /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 +social-llama-3-8b-beta.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.f16.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-beta.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..3c46726 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: AndersGiovanni/social-llama-3-8b-beta +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/AndersGiovanni/social-llama-3-8b-beta + + +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/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-beta-GGUF/resolve/main/social-llama-3-8b-beta.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/social-llama-3-8b-beta.IQ4_XS.gguf b/social-llama-3-8b-beta.IQ4_XS.gguf new file mode 100644 index 0000000..fb8f2cc --- /dev/null +++ b/social-llama-3-8b-beta.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7069b4406d8efc63052271f99df0955932222d02c3bf06ea1b174b1dd11f50f +size 4484363200 diff --git a/social-llama-3-8b-beta.Q2_K.gguf b/social-llama-3-8b-beta.Q2_K.gguf new file mode 100644 index 0000000..58b1757 --- /dev/null +++ b/social-llama-3-8b-beta.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25057579eb82c18c6043fa2a8b0b100be64123b7caaee835f018ec6ac804bf5c +size 3179131840 diff --git a/social-llama-3-8b-beta.Q3_K_L.gguf b/social-llama-3-8b-beta.Q3_K_L.gguf new file mode 100644 index 0000000..49f2f49 --- /dev/null +++ b/social-llama-3-8b-beta.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6f4bc38fea54d1dcc05a4ed45e738197e13632171fdf0a6d29115c985697ffe +size 4321956800 diff --git a/social-llama-3-8b-beta.Q3_K_M.gguf b/social-llama-3-8b-beta.Q3_K_M.gguf new file mode 100644 index 0000000..9363c06 --- /dev/null +++ b/social-llama-3-8b-beta.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19655ac795722c4c3ecf67c083274f10df76673a4ce938319c563a2f81edc787 +size 4018918336 diff --git a/social-llama-3-8b-beta.Q3_K_S.gguf b/social-llama-3-8b-beta.Q3_K_S.gguf new file mode 100644 index 0000000..71a88da --- /dev/null +++ b/social-llama-3-8b-beta.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe4ac22e3eb9784a4d0ee76421c4fe96d5dfc9b949ae23806945c3309a37c39 +size 3664499648 diff --git a/social-llama-3-8b-beta.Q4_K_M.gguf b/social-llama-3-8b-beta.Q4_K_M.gguf new file mode 100644 index 0000000..f3482fa --- /dev/null +++ b/social-llama-3-8b-beta.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd872e35222e81891e1b131704e31b0fdd5273b96b2b9c501249b253a7463f7a +size 4920734656 diff --git a/social-llama-3-8b-beta.Q4_K_S.gguf b/social-llama-3-8b-beta.Q4_K_S.gguf new file mode 100644 index 0000000..74d078a --- /dev/null +++ b/social-llama-3-8b-beta.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625f970b16164f6f26ca9970834092e6d032906ad1deca7dc9ea1cfc6daec64e +size 4692669376 diff --git a/social-llama-3-8b-beta.Q5_K_M.gguf b/social-llama-3-8b-beta.Q5_K_M.gguf new file mode 100644 index 0000000..66392f7 --- /dev/null +++ b/social-llama-3-8b-beta.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2a3de71e5b0b04784ee338b3874380d557754a9f2972ad6266ae0aa84898f3 +size 5732987840 diff --git a/social-llama-3-8b-beta.Q5_K_S.gguf b/social-llama-3-8b-beta.Q5_K_S.gguf new file mode 100644 index 0000000..35e3c8f --- /dev/null +++ b/social-llama-3-8b-beta.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284ba452199e4271a96125c5d4f774d4b10e35e2971283d1944ba0f2725fa104 +size 5599294400 diff --git a/social-llama-3-8b-beta.Q6_K.gguf b/social-llama-3-8b-beta.Q6_K.gguf new file mode 100644 index 0000000..31c1817 --- /dev/null +++ b/social-llama-3-8b-beta.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:984af3c1eb02a7654c588acb1e56bbcf7024c7a2ac7dd1ef7defdb25cc246530 +size 6596006848 diff --git a/social-llama-3-8b-beta.Q8_0.gguf b/social-llama-3-8b-beta.Q8_0.gguf new file mode 100644 index 0000000..ae16c98 --- /dev/null +++ b/social-llama-3-8b-beta.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:625a89e153de284b546e4924f20bc0ef5a4b18e25ea773c6c43124f7b001ebc8 +size 8540771264 diff --git a/social-llama-3-8b-beta.f16.gguf b/social-llama-3-8b-beta.f16.gguf new file mode 100644 index 0000000..39960e4 --- /dev/null +++ b/social-llama-3-8b-beta.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39aa78b4cd44bb0d560762a4679ffd99a89605ba162ad282117116631f556322 +size 16068891584