commit b4da135960b0e66feca2ba23b335b43144a32638 Author: ModelHub XC Date: Tue Jul 14 16:36:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SocialiteLlama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..78c99e6 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +SocialiteLlama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.f16.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SocialiteLlama.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7e8dcec --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: hlab/SocialiteLlama +datasets: +- hlab/SocialiteInstructions +language: +- en +library_name: transformers +license: llama2 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/hlab/SocialiteLlama + + +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/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SocialiteLlama-GGUF/resolve/main/SocialiteLlama.f16.gguf) | f16 | 13.6 | 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/SocialiteLlama.IQ4_XS.gguf b/SocialiteLlama.IQ4_XS.gguf new file mode 100644 index 0000000..754e7dc --- /dev/null +++ b/SocialiteLlama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b719db391fe33e6c748a39a090ae92466ff9b547e3d6da01c6260fc2162a7e0a +size 3647517152 diff --git a/SocialiteLlama.Q2_K.gguf b/SocialiteLlama.Q2_K.gguf new file mode 100644 index 0000000..bad95aa --- /dev/null +++ b/SocialiteLlama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd77ecf1c73c3f9ac4fa5671cd32ce4ea29df50810f469e40623eb3685af16a +size 2532864480 diff --git a/SocialiteLlama.Q3_K_L.gguf b/SocialiteLlama.Q3_K_L.gguf new file mode 100644 index 0000000..6e15a59 --- /dev/null +++ b/SocialiteLlama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84add1b8424b3d398c4547c2ad95fcd12ab5ee5bcaa7369328e876e57bb282a0 +size 3597111776 diff --git a/SocialiteLlama.Q3_K_M.gguf b/SocialiteLlama.Q3_K_M.gguf new file mode 100644 index 0000000..268b926 --- /dev/null +++ b/SocialiteLlama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae203e3b3fe92a24941d38f20184c04b435c8a52ad90ce1def260ff1f4ea114 +size 3298005472 diff --git a/SocialiteLlama.Q3_K_S.gguf b/SocialiteLlama.Q3_K_S.gguf new file mode 100644 index 0000000..2ed3ef6 --- /dev/null +++ b/SocialiteLlama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8887c27a119ec6a4f48552f24602557a54d007f496cd6d20f9534317e36e8765 +size 2948305376 diff --git a/SocialiteLlama.Q4_0_4_4.gguf b/SocialiteLlama.Q4_0_4_4.gguf new file mode 100644 index 0000000..86e9f7f --- /dev/null +++ b/SocialiteLlama.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a172f34e50c5084e29e26b97656ff33b336573b7a82b737e4b9837b617f4ad +size 3825807840 diff --git a/SocialiteLlama.Q4_K_M.gguf b/SocialiteLlama.Q4_K_M.gguf new file mode 100644 index 0000000..7c33fce --- /dev/null +++ b/SocialiteLlama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a52d94027849b2be4e6d8b3e338f8792a7cabf887b75d8d4b9c4f73cab0dae7 +size 4081005024 diff --git a/SocialiteLlama.Q4_K_S.gguf b/SocialiteLlama.Q4_K_S.gguf new file mode 100644 index 0000000..f317b61 --- /dev/null +++ b/SocialiteLlama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d19cb4a991aef527f4e84320e348364825245dc1e12580c0c68785e1abd1955 +size 3856740832 diff --git a/SocialiteLlama.Q5_K_M.gguf b/SocialiteLlama.Q5_K_M.gguf new file mode 100644 index 0000000..f09c51f --- /dev/null +++ b/SocialiteLlama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c787dbddcd99ffac19003855ae76c575abece5757cbe943f44573312632fa71 +size 4783157728 diff --git a/SocialiteLlama.Q5_K_S.gguf b/SocialiteLlama.Q5_K_S.gguf new file mode 100644 index 0000000..682dae9 --- /dev/null +++ b/SocialiteLlama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0d14a9f7c43e7f7af1d09a94b160f5506a1ff618a83ca0f2deb73f56b63911 +size 4651692512 diff --git a/SocialiteLlama.Q6_K.gguf b/SocialiteLlama.Q6_K.gguf new file mode 100644 index 0000000..74fe0ed --- /dev/null +++ b/SocialiteLlama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d6aa88aa49fc280caa3ffbe5161b8697b3a51909ddc927bf4d894a4585a0848 +size 5529194976 diff --git a/SocialiteLlama.Q8_0.gguf b/SocialiteLlama.Q8_0.gguf new file mode 100644 index 0000000..fd636c6 --- /dev/null +++ b/SocialiteLlama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acc7fc87077bb97ad11c497bfae6aa8831984a3a45e9b66b2e3f0705c4fd2f9a +size 7161090528 diff --git a/SocialiteLlama.f16.gguf b/SocialiteLlama.f16.gguf new file mode 100644 index 0000000..75934e7 --- /dev/null +++ b/SocialiteLlama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6b9fc1f506f34f490efcfc4e3651849e81d34e1f1d81f5d8b25a27ced1c0fc +size 13478105568