commit dd2435dc86d327621ab8a0ae2f99c56fc6f0e843 Author: ModelHub XC Date: Tue Jun 23 23:48:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e6ae1ef --- /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-v02.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.f16.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +naps-llama-3_1-8b-instruct-v02.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..42723c0 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: NAPS-ai/naps-llama-3_1-8b-instruct-v02 +datasets: +- nayohan/math-gpt-4o-200k-ko +language: +- ko +- 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-v02 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-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-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/naps-llama-3_1-8b-instruct-v02-GGUF/resolve/main/naps-llama-3_1-8b-instruct-v02.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/naps-llama-3_1-8b-instruct-v02.IQ4_XS.gguf b/naps-llama-3_1-8b-instruct-v02.IQ4_XS.gguf new file mode 100644 index 0000000..e4563fd --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c24960c30824e8054e41b2be8803f6dd8cba05f803e8ac1ea2ab1228125dd54 +size 4484368352 diff --git a/naps-llama-3_1-8b-instruct-v02.Q2_K.gguf b/naps-llama-3_1-8b-instruct-v02.Q2_K.gguf new file mode 100644 index 0000000..25ea384 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2005441fa26d8cf6e2cc93ffacd2aad6793394763f515a897c4169a19860acd9 +size 3179136992 diff --git a/naps-llama-3_1-8b-instruct-v02.Q3_K_L.gguf b/naps-llama-3_1-8b-instruct-v02.Q3_K_L.gguf new file mode 100644 index 0000000..8d77345 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b96a21996910cd699b56b288362abb0f07e9c1a0926d6ba7c2fa6656c77746 +size 4321961952 diff --git a/naps-llama-3_1-8b-instruct-v02.Q3_K_M.gguf b/naps-llama-3_1-8b-instruct-v02.Q3_K_M.gguf new file mode 100644 index 0000000..04276f2 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567c9198749d8c92108f4160c43a321df191db2f497e295b0a66260ffc1be33d +size 4018923488 diff --git a/naps-llama-3_1-8b-instruct-v02.Q3_K_S.gguf b/naps-llama-3_1-8b-instruct-v02.Q3_K_S.gguf new file mode 100644 index 0000000..9af10dc --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade602951be61351b4a69b704741393aeabe1637add0a1ba7060805c72b04049 +size 3664504800 diff --git a/naps-llama-3_1-8b-instruct-v02.Q4_K_M.gguf b/naps-llama-3_1-8b-instruct-v02.Q4_K_M.gguf new file mode 100644 index 0000000..77dd305 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d842331444a52fd92010dd268da561684c53c02b1c38910bc05ecc6ca3a887f +size 4920739808 diff --git a/naps-llama-3_1-8b-instruct-v02.Q4_K_S.gguf b/naps-llama-3_1-8b-instruct-v02.Q4_K_S.gguf new file mode 100644 index 0000000..5fb0897 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e61200ff28bb30ecb87ae7e638991d14fa04e205077a69a6fd97ef80789fa24 +size 4692674528 diff --git a/naps-llama-3_1-8b-instruct-v02.Q5_K_M.gguf b/naps-llama-3_1-8b-instruct-v02.Q5_K_M.gguf new file mode 100644 index 0000000..ce20739 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d964d658cc88ff1e3df76305e762721d5e755111d5eea40282859275afbf2158 +size 5732992992 diff --git a/naps-llama-3_1-8b-instruct-v02.Q5_K_S.gguf b/naps-llama-3_1-8b-instruct-v02.Q5_K_S.gguf new file mode 100644 index 0000000..4f69936 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c3149c3fe8c48742638c2bb92fd5cac5ae86c487c67fa618de48c04e8a6ea3 +size 5599299552 diff --git a/naps-llama-3_1-8b-instruct-v02.Q6_K.gguf b/naps-llama-3_1-8b-instruct-v02.Q6_K.gguf new file mode 100644 index 0000000..efd53a5 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f08acb87db9b52a5ccee8c20d4b0bd037865727ed08a2409884045f0bd6c55 +size 6596012000 diff --git a/naps-llama-3_1-8b-instruct-v02.Q8_0.gguf b/naps-llama-3_1-8b-instruct-v02.Q8_0.gguf new file mode 100644 index 0000000..f51d312 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7196e9377dacd3fccba17e97f51a740ca077fe1940b4c52a6a0fccca4d5a35b0 +size 8540776416 diff --git a/naps-llama-3_1-8b-instruct-v02.f16.gguf b/naps-llama-3_1-8b-instruct-v02.f16.gguf new file mode 100644 index 0000000..338f233 --- /dev/null +++ b/naps-llama-3_1-8b-instruct-v02.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:926adf3ea0ad53a4f9b7b6cc9258b779273269bf666b58fed118d3ab30233fe0 +size 16068896736