commit 193ceb474f7a1fdfbbc0cdbf57283b830099d8d0 Author: ModelHub XC Date: Sun Sep 20 21:00:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ed79058 --- /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-3.1-8B-Ins-RF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMA-3.1-8B-Ins-RF.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMA-3.1-8B-Ins-RF.IQ4_XS.gguf b/LLaMA-3.1-8B-Ins-RF.IQ4_XS.gguf new file mode 100644 index 0000000..5403d54 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ecaec0d64757d1986337ce0e4824ee8f69397627b63a87d14e1f42e6ef3f6d +size 4484367840 diff --git a/LLaMA-3.1-8B-Ins-RF.Q2_K.gguf b/LLaMA-3.1-8B-Ins-RF.Q2_K.gguf new file mode 100644 index 0000000..7ee5911 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2793cb85aa485cf55c215d6cde9aed3340643dc78b542f6f9e8598a28754a124 +size 3179136480 diff --git a/LLaMA-3.1-8B-Ins-RF.Q3_K_L.gguf b/LLaMA-3.1-8B-Ins-RF.Q3_K_L.gguf new file mode 100644 index 0000000..a59b817 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9642b5f1ba55ae62d80971f3a3b7644bae1042b1d1aa29984d63ed6219e16d5 +size 4321961440 diff --git a/LLaMA-3.1-8B-Ins-RF.Q3_K_M.gguf b/LLaMA-3.1-8B-Ins-RF.Q3_K_M.gguf new file mode 100644 index 0000000..6644f39 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e993e3a84bd3a3c6ae396ec9655e222b2c3eb5f42a7cc839e0bf27a7e7a5fe +size 4018922976 diff --git a/LLaMA-3.1-8B-Ins-RF.Q3_K_S.gguf b/LLaMA-3.1-8B-Ins-RF.Q3_K_S.gguf new file mode 100644 index 0000000..3c24294 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7646a608282553c5dff7161a582b235eb67532a2256eacc28f6917d633437c5 +size 3664504288 diff --git a/LLaMA-3.1-8B-Ins-RF.Q4_K_M.gguf b/LLaMA-3.1-8B-Ins-RF.Q4_K_M.gguf new file mode 100644 index 0000000..beb8cb2 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c3363b3f57af3c88f6ac9034bdddbeeb83b3ce81e84cf21232c5b1cebe37f1 +size 4920739296 diff --git a/LLaMA-3.1-8B-Ins-RF.Q4_K_S.gguf b/LLaMA-3.1-8B-Ins-RF.Q4_K_S.gguf new file mode 100644 index 0000000..b7fa068 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d910bd818c40953b7f5a1b02f074942352da957fd8406c84d32d3e212e6f3a9 +size 4692674016 diff --git a/LLaMA-3.1-8B-Ins-RF.Q5_K_M.gguf b/LLaMA-3.1-8B-Ins-RF.Q5_K_M.gguf new file mode 100644 index 0000000..7b7d200 --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41de34ae0d973804b1c9528acb268dc61ffbaeaf98ecd6e494234f2b505a4b1a +size 5732992480 diff --git a/LLaMA-3.1-8B-Ins-RF.Q5_K_S.gguf b/LLaMA-3.1-8B-Ins-RF.Q5_K_S.gguf new file mode 100644 index 0000000..e58d93f --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793af1f13ef087fa13be4f993630afd1d86099d48ea06d930fce29041dba789e +size 5599299040 diff --git a/LLaMA-3.1-8B-Ins-RF.Q6_K.gguf b/LLaMA-3.1-8B-Ins-RF.Q6_K.gguf new file mode 100644 index 0000000..959473c --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6127dac0172a8aa8ae77a0e7f2d28866eeadb33c3291720e3361324cc1a7cf3 +size 6596011488 diff --git a/LLaMA-3.1-8B-Ins-RF.Q8_0.gguf b/LLaMA-3.1-8B-Ins-RF.Q8_0.gguf new file mode 100644 index 0000000..ae9ea8e --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:025a5ea2df3037ad0f9b0216bd3747d77372bb1c27cbe5127d8d01af3ea0c79d +size 8540775904 diff --git a/LLaMA-3.1-8B-Ins-RF.f16.gguf b/LLaMA-3.1-8B-Ins-RF.f16.gguf new file mode 100644 index 0000000..f7d32ce --- /dev/null +++ b/LLaMA-3.1-8B-Ins-RF.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f80cdb09823d91a45a5dacd987e59bc744e6001e94de3c3e9228d9c8e1454621 +size 16068896224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d849f34 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Anonymous-EmpathyAI/LLaMA-3.1-8B-Ins-RF +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Anonymous-EmpathyAI/LLaMA-3.1-8B-Ins-RF + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLaMA-3.1-8B-Ins-RF-GGUF).*** + +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/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMA-3.1-8B-Ins-RF-GGUF/resolve/main/LLaMA-3.1-8B-Ins-RF.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. + +