commit 3a5eeaee199853484a6f919e935becbd7492c99c Author: ModelHub XC Date: Fri Jul 3 06:04:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llamazing-3.1-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e8d1122 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +Llamazing-3.1-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llamazing-3.1-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llamazing-3.1-8B-Instruct.IQ4_XS.gguf b/Llamazing-3.1-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ed681a4 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e707709ddc8686d8352d2f62dbe5b47ff54c49759d4e5b6b9331ef97b31d57d4 +size 4484363648 diff --git a/Llamazing-3.1-8B-Instruct.Q2_K.gguf b/Llamazing-3.1-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..e075555 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b02786adf4edc7c4ca587194568527e656e34ab6d9fc42ed0588bccd91b84a +size 3179132288 diff --git a/Llamazing-3.1-8B-Instruct.Q3_K_L.gguf b/Llamazing-3.1-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..7409aee --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:107f82a55c8c6b1b31090fd89be404034fe214e9c7ec6d44634e86c81f0b9f10 +size 4321957248 diff --git a/Llamazing-3.1-8B-Instruct.Q3_K_M.gguf b/Llamazing-3.1-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..41b1e56 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d42ad085dbc8e03f6edb12e3590d1633651132833bb0c17686c963b1c2f56093 +size 4018918784 diff --git a/Llamazing-3.1-8B-Instruct.Q3_K_S.gguf b/Llamazing-3.1-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..adadddc --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a05a3bd2c8d8bc14fbfd1cfc99e700eef83b9f08b07b1725f9ac66a1ba346f +size 3664500096 diff --git a/Llamazing-3.1-8B-Instruct.Q4_K_M.gguf b/Llamazing-3.1-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..f796638 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11daac3b2f0976c451c885ce1ffd73ace37c5a7c7854623292de03cd537457f +size 4920735104 diff --git a/Llamazing-3.1-8B-Instruct.Q4_K_S.gguf b/Llamazing-3.1-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..c6c53da --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7499ef299a8416fe09161d7541ad5637d51081effe2938c844a83cb8b3a55c19 +size 4692669824 diff --git a/Llamazing-3.1-8B-Instruct.Q5_K_M.gguf b/Llamazing-3.1-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..476fda5 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a9218e1d076ddf776846c38869e01627b07551012e03e735c6c4eb78aa91fa7 +size 5732988288 diff --git a/Llamazing-3.1-8B-Instruct.Q5_K_S.gguf b/Llamazing-3.1-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..1725b57 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3e13d6a09bc890b2d7f5e3b871775de96cb2bcc7bef185d1b85199a1238d71 +size 5599294848 diff --git a/Llamazing-3.1-8B-Instruct.Q6_K.gguf b/Llamazing-3.1-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..149b8a9 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07ea4dad47648deda0b3998d54d340dee13131f3baf5e5c4f620a3428177be79 +size 6596007296 diff --git a/Llamazing-3.1-8B-Instruct.Q8_0.gguf b/Llamazing-3.1-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..a53f393 --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59e6d86a15ac02ccbf0c43ebf0c17f68da98994c8b0fb770507b27caba2defc +size 8540771712 diff --git a/Llamazing-3.1-8B-Instruct.f16.gguf b/Llamazing-3.1-8B-Instruct.f16.gguf new file mode 100644 index 0000000..770182f --- /dev/null +++ b/Llamazing-3.1-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e15b3d65ac42d66957b8db9fea5bdf37694f9f8304e25fd6a82f30d754052f +size 16068892032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4ab7f7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: sethuiyer/Llamazing-3.1-8B-Instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- narration +- Truthful +--- +## About + + + + + + +static quants of https://huggingface.co/sethuiyer/Llamazing-3.1-8B-Instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-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/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llamazing-3.1-8B-Instruct-GGUF/resolve/main/Llamazing-3.1-8B-Instruct.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. + +