commit d64d316d5759852a4319e02f0cb39fe76576fbaa Author: ModelHub XC Date: Sat Jun 27 01:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0fdcf50 --- /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 +Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B_Suzume_Task_Arithmetic.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.IQ4_XS.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.IQ4_XS.gguf new file mode 100644 index 0000000..a24c219 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b292bc8cc2e0af36245e3b078ec804e8d96d8c0e985905443792e921c669db03 +size 4484363904 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q2_K.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q2_K.gguf new file mode 100644 index 0000000..0d52d92 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:887df5493cb6f5df0492162b8a01a89eb97d05eaba9fd2654ae18dea9a778cd3 +size 3179132544 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_L.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_L.gguf new file mode 100644 index 0000000..dd93cb1 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8d13744dbd6609fae3d8cdad67406d2816f9e9de929246f1ec5efb08b78c4c +size 4321957504 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_M.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_M.gguf new file mode 100644 index 0000000..96b3ed9 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:662ba97e7e3e10e55d1b2f30a5194366f6e0953e183696d444882c4c59d613aa +size 4018919040 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_S.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_S.gguf new file mode 100644 index 0000000..34bb32e --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64b54caf1772f1ce2c04153e5087fb07274aa29432bd4af488c82ff7903faf0 +size 3664500352 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_M.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_M.gguf new file mode 100644 index 0000000..42f2107 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3934d1abb576add62816909d1d0740ec1be116a644cfd79578e081995ccf1ccc +size 4920735360 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_S.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_S.gguf new file mode 100644 index 0000000..7078dda --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05f2630d83e3e1b963a0be81a99fcc7d2435b0454542395f1503f1f4bd605af6 +size 4692670080 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_M.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_M.gguf new file mode 100644 index 0000000..2cb0b00 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5a5b5b2fc3ed1294ca80635a25b1e9aa6625172ec8f5c3081f316e3541752ab +size 5732988544 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_S.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_S.gguf new file mode 100644 index 0000000..24ee731 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee27184b6bc4c68249b9d9b305bb8d3e2351a37bed45cd7f89634027e536801 +size 5599295104 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q6_K.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q6_K.gguf new file mode 100644 index 0000000..218b560 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0752926d79b0395de4edbb0eb394ab9adc4cc2f5bcf4d356e91860e95e366b99 +size 6596007552 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.Q8_0.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.Q8_0.gguf new file mode 100644 index 0000000..e7b922b --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:660715023be6e61fd4fb9dfde85913529d35d0529944e15b2dc9b22c1d20b0fa +size 8540771968 diff --git a/Llama-3-8B_Suzume_Task_Arithmetic.f16.gguf b/Llama-3-8B_Suzume_Task_Arithmetic.f16.gguf new file mode 100644 index 0000000..4b83088 --- /dev/null +++ b/Llama-3-8B_Suzume_Task_Arithmetic.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b21838f47e624a106a5d33972540aa049e9263585d6b856fed208c889661149 +size 16068892288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bb7bb76 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: noirchan/Llama-3-8B_Suzume_Task_Arithmetic +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/noirchan/Llama-3-8B_Suzume_Task_Arithmetic + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B_Suzume_Task_Arithmetic-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B_Suzume_Task_Arithmetic-GGUF/resolve/main/Llama-3-8B_Suzume_Task_Arithmetic.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. + +