commit 849fde1f27ce2daa4446f33abfe50da98d2d47b9 Author: ModelHub XC Date: Fri Oct 9 02:51:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/social-llama-3-8b-instructions-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0822b0e --- /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-instructions.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +social-llama-3-8b-instructions.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..739a91c --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: AndersGiovanni/social-llama-3-8b-instructions +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/AndersGiovanni/social-llama-3-8b-instructions + + +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-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/social-llama-3-8b-instructions-GGUF/resolve/main/social-llama-3-8b-instructions.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/social-llama-3-8b-instructions.IQ4_XS.gguf b/social-llama-3-8b-instructions.IQ4_XS.gguf new file mode 100644 index 0000000..d4d9be2 --- /dev/null +++ b/social-llama-3-8b-instructions.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aafaf5c17746140b5dbb492c5e1b5c9ad1c29ee046cc2b088c5fb7c9f118b02e +size 4484363232 diff --git a/social-llama-3-8b-instructions.Q2_K.gguf b/social-llama-3-8b-instructions.Q2_K.gguf new file mode 100644 index 0000000..7fb3a75 --- /dev/null +++ b/social-llama-3-8b-instructions.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3fd84574dcae49fd3ffca65ce1520db33eb531d35b2d89fee7897e146822e8a +size 3179131872 diff --git a/social-llama-3-8b-instructions.Q3_K_L.gguf b/social-llama-3-8b-instructions.Q3_K_L.gguf new file mode 100644 index 0000000..b5eb099 --- /dev/null +++ b/social-llama-3-8b-instructions.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7481a456ee43548c44633399992e3395b5c6dce3fcbf3e25c075d97bd4c1b683 +size 4321956832 diff --git a/social-llama-3-8b-instructions.Q3_K_M.gguf b/social-llama-3-8b-instructions.Q3_K_M.gguf new file mode 100644 index 0000000..92fdbec --- /dev/null +++ b/social-llama-3-8b-instructions.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f500bd9202b763be8d7b61ac3d130616fa75649a2b6ec8eb208e30bb6e5d58b +size 4018918368 diff --git a/social-llama-3-8b-instructions.Q3_K_S.gguf b/social-llama-3-8b-instructions.Q3_K_S.gguf new file mode 100644 index 0000000..9378da5 --- /dev/null +++ b/social-llama-3-8b-instructions.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f1071fb4e744ff3d344e027bf45c1ee310b320fec9d8988f3849571be0b89b7 +size 3664499680 diff --git a/social-llama-3-8b-instructions.Q4_K_M.gguf b/social-llama-3-8b-instructions.Q4_K_M.gguf new file mode 100644 index 0000000..dfc34fb --- /dev/null +++ b/social-llama-3-8b-instructions.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba34203baad381c33619aa095a4fc1580e8d446934cc79f4bba48595634d9bff +size 4920734688 diff --git a/social-llama-3-8b-instructions.Q4_K_S.gguf b/social-llama-3-8b-instructions.Q4_K_S.gguf new file mode 100644 index 0000000..1ee7a76 --- /dev/null +++ b/social-llama-3-8b-instructions.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46e7bad05a970042f9a1c45bca9f9f3a9cd28fc7f727d39cfae4bc38e5f10cbe +size 4692669408 diff --git a/social-llama-3-8b-instructions.Q5_K_M.gguf b/social-llama-3-8b-instructions.Q5_K_M.gguf new file mode 100644 index 0000000..d2a9c85 --- /dev/null +++ b/social-llama-3-8b-instructions.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d79f5c9c1a3ad12dfd7849bfbf7b785ba8cb193a93ac16a66bb6332ec6b111 +size 5732987872 diff --git a/social-llama-3-8b-instructions.Q5_K_S.gguf b/social-llama-3-8b-instructions.Q5_K_S.gguf new file mode 100644 index 0000000..a636ed9 --- /dev/null +++ b/social-llama-3-8b-instructions.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ade208ead01e05a80db30a860cc1409595db1cdf755d4e61148c92ae3756569 +size 5599294432 diff --git a/social-llama-3-8b-instructions.Q6_K.gguf b/social-llama-3-8b-instructions.Q6_K.gguf new file mode 100644 index 0000000..4de3d72 --- /dev/null +++ b/social-llama-3-8b-instructions.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9df68ca2b64dd5526d1403872543259888c081abc0e6f4cf9a0d5a4b6b80754 +size 6596006880 diff --git a/social-llama-3-8b-instructions.Q8_0.gguf b/social-llama-3-8b-instructions.Q8_0.gguf new file mode 100644 index 0000000..a92ba28 --- /dev/null +++ b/social-llama-3-8b-instructions.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aaaa6454e82d03f2dddb7bdc61227155295534e7346240c3775f861c02a1162 +size 8540771296 diff --git a/social-llama-3-8b-instructions.f16.gguf b/social-llama-3-8b-instructions.f16.gguf new file mode 100644 index 0000000..f0c0eda --- /dev/null +++ b/social-llama-3-8b-instructions.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22393395a6387df7e13c9effc0726dcbcfc02f48e5d6b496d3dcfda695549249 +size 16068891616