commit 4bcfff7ce45db15da88cf35e1ac064ba474b9127 Author: ModelHub XC Date: Fri Jun 19 17:02:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..660f629 --- /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 +NAPS-llama-3.1-8b-instruct-v0.3.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NAPS-llama-3.1-8b-instruct-v0.3.2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.IQ4_XS.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.IQ4_XS.gguf new file mode 100644 index 0000000..1c98148 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc06fdced5714e5e8392e6c83570ef0260a99bfacf318e9a2bea9dd58ad1aa3 +size 4484367744 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q2_K.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q2_K.gguf new file mode 100644 index 0000000..ec57ea7 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:387c2934753fc75dc076b0c51f9fd38c0970737d1174c650773976e9f3adbfa1 +size 3179136384 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_L.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_L.gguf new file mode 100644 index 0000000..063988c --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b976176cf7147613896183155543c58f0c68cb8461476bb61f374f5a4a57ac06 +size 4321961344 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_M.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_M.gguf new file mode 100644 index 0000000..b9d4b8f --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd1ef61f52a6f314010cb45b3ef11239fde65c4d83d185676b27af21744da4d3 +size 4018922880 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_S.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_S.gguf new file mode 100644 index 0000000..836f17d --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bab53844f0ad7bd5eec87fe38e849ad64c9ff8a43a0d99c18a5cfe8b2c9103f4 +size 3664504192 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_M.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_M.gguf new file mode 100644 index 0000000..61c29c6 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93233d499935a9d0a3a54939227f9b1dfcd89f738f308fd47f1279fed2e8ed7 +size 4920739200 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_S.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_S.gguf new file mode 100644 index 0000000..0890716 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a55a9f465a3432ad834a34d97cda8f76ab7ff300d5cb4dd7f2983ea1fd52e6 +size 4692673920 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_M.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_M.gguf new file mode 100644 index 0000000..1e288c8 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a61a7cd2a94af4ec577e1a4ee33d3d8bba733baf53b8b7f31a6d23746d3504 +size 5732992384 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_S.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_S.gguf new file mode 100644 index 0000000..f4ea703 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a90848ad5e9657987a577daba5b160f0da9ea98bb58314c6d531fa6d12f82b +size 5599298944 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q6_K.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q6_K.gguf new file mode 100644 index 0000000..ff9474b --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b297d347419c2a115c3f48ea7d6a7f099d10b6f5679ed8e699bbd6a8eb62945 +size 6596011392 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.Q8_0.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q8_0.gguf new file mode 100644 index 0000000..2e96d47 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eceb2a39b92a3a3011ebda4868c752156d841cd5eb94bd60d20015ee5029c07f +size 8540775808 diff --git a/NAPS-llama-3.1-8b-instruct-v0.3.2.f16.gguf b/NAPS-llama-3.1-8b-instruct-v0.3.2.f16.gguf new file mode 100644 index 0000000..54c3488 --- /dev/null +++ b/NAPS-llama-3.1-8b-instruct-v0.3.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e515d40df7bdbe3e16f3975371687dc66877220f912526637f081f66673718 +size 16068896128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a7d3102 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: NAPS-ai/NAPS-llama-3.1-8b-instruct-v0.3.2 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/NAPS-ai/NAPS-llama-3.1-8b-instruct-v0.3.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-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/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NAPS-llama-3.1-8b-instruct-v0.3.2-GGUF/resolve/main/NAPS-llama-3.1-8b-instruct-v0.3.2.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. + +