commit 73f8e01af9e39687dc5f8c31c7dccfc39cddd308 Author: ModelHub XC Date: Sun Apr 12 20:10:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HyperLLama3.1-8b-Nova-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0f79567 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +HyperLLama3.1-8b-Nova.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.f16.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HyperLLama3.1-8b-Nova.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HyperLLama3.1-8b-Nova.IQ3_M.gguf b/HyperLLama3.1-8b-Nova.IQ3_M.gguf new file mode 100644 index 0000000..83f4d2b --- /dev/null +++ b/HyperLLama3.1-8b-Nova.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbe0c4a71fa9e95c140bb768f0ec2e2c7135918bb3f1fc18e2bf1f630ede0bd +size 3784825056 diff --git a/HyperLLama3.1-8b-Nova.IQ3_S.gguf b/HyperLLama3.1-8b-Nova.IQ3_S.gguf new file mode 100644 index 0000000..dc59679 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:420f0e53a2b9ece6948a669396ad0518a46089834b55b7d7aa2a60f07d691425 +size 3682326752 diff --git a/HyperLLama3.1-8b-Nova.IQ3_XS.gguf b/HyperLLama3.1-8b-Nova.IQ3_XS.gguf new file mode 100644 index 0000000..6e3dbe7 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ce581286c3ee2c04b54f5c5f6dce3bbf1dfbb2fab9aecf15aab4c1e50193924 +size 3518748896 diff --git a/HyperLLama3.1-8b-Nova.IQ4_XS.gguf b/HyperLLama3.1-8b-Nova.IQ4_XS.gguf new file mode 100644 index 0000000..33a8fce --- /dev/null +++ b/HyperLLama3.1-8b-Nova.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fab8322cdda9907a4e9266008e2739e90018a0b25160048776bd3421f5f125e +size 4484364512 diff --git a/HyperLLama3.1-8b-Nova.Q2_K.gguf b/HyperLLama3.1-8b-Nova.Q2_K.gguf new file mode 100644 index 0000000..b66a6e2 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2af1fcfe451fc27382554423ba6f01bf0a6d29fbf9039d9c371ccc4778206433 +size 3179133152 diff --git a/HyperLLama3.1-8b-Nova.Q3_K_L.gguf b/HyperLLama3.1-8b-Nova.Q3_K_L.gguf new file mode 100644 index 0000000..45167f1 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9265328341721cfb1ea0477bfdcf067a0144c4adcff3bfe87d4d34c558f9ca6 +size 4321958112 diff --git a/HyperLLama3.1-8b-Nova.Q3_K_M.gguf b/HyperLLama3.1-8b-Nova.Q3_K_M.gguf new file mode 100644 index 0000000..47d26e9 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112ab0d6de3ccec9d950ec4f19bde99e2c919545a19b2fb0f6cabaf680c927c5 +size 4018919648 diff --git a/HyperLLama3.1-8b-Nova.Q3_K_S.gguf b/HyperLLama3.1-8b-Nova.Q3_K_S.gguf new file mode 100644 index 0000000..2ca7888 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:325c01700d4a734019f1859c567bfbe726bc90c383e53a08fbd75e504a1e80bb +size 3664500960 diff --git a/HyperLLama3.1-8b-Nova.Q4_K_M.gguf b/HyperLLama3.1-8b-Nova.Q4_K_M.gguf new file mode 100644 index 0000000..a48a0ff --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70da8b87f16713a76dbb621699ce09656ea3e0a05fc94a1e4fb1908b766318a4 +size 4920735968 diff --git a/HyperLLama3.1-8b-Nova.Q4_K_S.gguf b/HyperLLama3.1-8b-Nova.Q4_K_S.gguf new file mode 100644 index 0000000..e230629 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28a60a7fe451fda34afbbebe9c9b8083bf70773df2b85c2846bf303fec5a560a +size 4692670688 diff --git a/HyperLLama3.1-8b-Nova.Q5_K_M.gguf b/HyperLLama3.1-8b-Nova.Q5_K_M.gguf new file mode 100644 index 0000000..c295347 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c156b4815215bc287852f4054ab6693037977e84c3b09ac7dbd57a8e284c51 +size 5732989152 diff --git a/HyperLLama3.1-8b-Nova.Q5_K_S.gguf b/HyperLLama3.1-8b-Nova.Q5_K_S.gguf new file mode 100644 index 0000000..3ffdb1a --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a07a72db20cc8c217f3af9efea8809672eb896578e7759de3cb74f1589ac2e74 +size 5599295712 diff --git a/HyperLLama3.1-8b-Nova.Q6_K.gguf b/HyperLLama3.1-8b-Nova.Q6_K.gguf new file mode 100644 index 0000000..bf29722 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8140f8e7dfd86b57db9ea652f5289ec8ec4b3093af52d5b82287bc80d040d6a2 +size 6596008160 diff --git a/HyperLLama3.1-8b-Nova.Q8_0.gguf b/HyperLLama3.1-8b-Nova.Q8_0.gguf new file mode 100644 index 0000000..c92997a --- /dev/null +++ b/HyperLLama3.1-8b-Nova.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2371d6e2b3d0e3cfdd320a015c91799c0bf81859388cfb180d086e69b748f35 +size 8540772576 diff --git a/HyperLLama3.1-8b-Nova.f16.gguf b/HyperLLama3.1-8b-Nova.f16.gguf new file mode 100644 index 0000000..12f1328 --- /dev/null +++ b/HyperLLama3.1-8b-Nova.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77efcbc28195f6df58768c3299b5d8d2d238e100bd4f91a519eeb43126ef373 +size 16068892896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a054fd2 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: bunnycore/HyperLLama3.1-8b-Nova +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/bunnycore/HyperLLama3.1-8b-Nova + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-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/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HyperLLama3.1-8b-Nova-GGUF/resolve/main/HyperLLama3.1-8b-Nova.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. + +