commit 078c0fd6f79275777e44d36f20d45e4f8f54f87d Author: ModelHub XC Date: Wed Aug 5 09:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3.1-MFANN-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..30b8fe3 --- /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 +Llama3.1-MFANN-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3.1-MFANN-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3.1-MFANN-8b.IQ4_XS.gguf b/Llama3.1-MFANN-8b.IQ4_XS.gguf new file mode 100644 index 0000000..d2d7c0a --- /dev/null +++ b/Llama3.1-MFANN-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1ef438e2fb67ea1b2ebc06ced7f8cb9653ffb8b26be5784bba68b4ebbe8cbd3 +size 4484368448 diff --git a/Llama3.1-MFANN-8b.Q2_K.gguf b/Llama3.1-MFANN-8b.Q2_K.gguf new file mode 100644 index 0000000..fb0ef55 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:428a3097cf4005e8ca503567e8e4e2e0774c127aa836301d434d688ad20b834c +size 3179137088 diff --git a/Llama3.1-MFANN-8b.Q3_K_L.gguf b/Llama3.1-MFANN-8b.Q3_K_L.gguf new file mode 100644 index 0000000..19e7515 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5014560574e6aff2caa8e207b8ad087ebbc1ff3232097cd462b5a9a8e59462f3 +size 4321962048 diff --git a/Llama3.1-MFANN-8b.Q3_K_M.gguf b/Llama3.1-MFANN-8b.Q3_K_M.gguf new file mode 100644 index 0000000..6063b84 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74329db739b24b2b4ff8e064faf08130dcf89a835522ffaf49f483522d6eef19 +size 4018923584 diff --git a/Llama3.1-MFANN-8b.Q3_K_S.gguf b/Llama3.1-MFANN-8b.Q3_K_S.gguf new file mode 100644 index 0000000..4e144c5 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27643813c0ec9f250dd97ac2c0fc75bac22cfd74519982c1ec51ab6e216d58ee +size 3664504896 diff --git a/Llama3.1-MFANN-8b.Q4_K_M.gguf b/Llama3.1-MFANN-8b.Q4_K_M.gguf new file mode 100644 index 0000000..c3b436b --- /dev/null +++ b/Llama3.1-MFANN-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc16d72f087512bdf3d1762d4aab2d4e81e39237ef0a20a2e8544800197f8e95 +size 4920739904 diff --git a/Llama3.1-MFANN-8b.Q4_K_S.gguf b/Llama3.1-MFANN-8b.Q4_K_S.gguf new file mode 100644 index 0000000..ce0de7a --- /dev/null +++ b/Llama3.1-MFANN-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c676d7ba9be887b49d5b740f2d0506422eac521cb324a356910fa83692d84c66 +size 4692674624 diff --git a/Llama3.1-MFANN-8b.Q5_K_M.gguf b/Llama3.1-MFANN-8b.Q5_K_M.gguf new file mode 100644 index 0000000..a0b0af8 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6500bd19bccddcede00d437a34810f3d1af23a1cac41e74ad66440ff37929e60 +size 5732993088 diff --git a/Llama3.1-MFANN-8b.Q5_K_S.gguf b/Llama3.1-MFANN-8b.Q5_K_S.gguf new file mode 100644 index 0000000..aed8121 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0be193940d2c3901dedcf9e0778abac74018ff0a7318c1bfc2f96ae02d4d853 +size 5599299648 diff --git a/Llama3.1-MFANN-8b.Q6_K.gguf b/Llama3.1-MFANN-8b.Q6_K.gguf new file mode 100644 index 0000000..a2287e9 --- /dev/null +++ b/Llama3.1-MFANN-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c73e780debe5f08e3e26c36e6bf4e2d60b926421be04e7ecad501f5c98fde05 +size 6596012096 diff --git a/Llama3.1-MFANN-8b.Q8_0.gguf b/Llama3.1-MFANN-8b.Q8_0.gguf new file mode 100644 index 0000000..1300fec --- /dev/null +++ b/Llama3.1-MFANN-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bd24389f5187c60c03726ed7f924a7484730f8ed6b9a1446d4d6ccc6af0ea6 +size 8540776512 diff --git a/Llama3.1-MFANN-8b.f16.gguf b/Llama3.1-MFANN-8b.f16.gguf new file mode 100644 index 0000000..23baebe --- /dev/null +++ b/Llama3.1-MFANN-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519a1cfa5d0494fcf7e9662e522fb09564b9a6da304fc745cde9e22966705059 +size 16068896832 diff --git a/README.md b/README.md new file mode 100644 index 0000000..9d1bd1f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: netcat420/Llama3.1-MFANN-8b +datasets: +- netcat420/MFANN +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/netcat420/Llama3.1-MFANN-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3.1-MFANN-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-i1-GGUF +## 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/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3.1-MFANN-8b-GGUF/resolve/main/Llama3.1-MFANN-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. + +