commit 61bfeabea4fa4e0e3619edd93d61061b3fe52f88 Author: ModelHub XC Date: Tue Sep 29 01:58:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-6B-Granite-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1d7822c --- /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 +Llama-3-6B-Granite-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-6B-Granite-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-6B-Granite-v0.1.IQ3_M.gguf b/Llama-3-6B-Granite-v0.1.IQ3_M.gguf new file mode 100644 index 0000000..0ba34b2 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ba4bf0314a633a5477620b490d20f8373d145dd977cfbab1a31d34728d714f +size 3004743776 diff --git a/Llama-3-6B-Granite-v0.1.IQ3_S.gguf b/Llama-3-6B-Granite-v0.1.IQ3_S.gguf new file mode 100644 index 0000000..1c21852 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720fdc8e1af7a3c8a2ecdfd5ae252ef2fd458837851945bea51eb89e71226190 +size 2927870048 diff --git a/Llama-3-6B-Granite-v0.1.IQ3_XS.gguf b/Llama-3-6B-Granite-v0.1.IQ3_XS.gguf new file mode 100644 index 0000000..9277e5e --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:770d03fb54b23da8c820946cfd009e942ec2d96588590f7c68c901e5ebf83339 +size 2805186656 diff --git a/Llama-3-6B-Granite-v0.1.IQ4_XS.gguf b/Llama-3-6B-Granite-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..87f59d5 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd064be6243056810825e26f75964580de606fde047087d93b18aebe39eb1546 +size 3542736992 diff --git a/Llama-3-6B-Granite-v0.1.Q2_K.gguf b/Llama-3-6B-Granite-v0.1.Q2_K.gguf new file mode 100644 index 0000000..a596805 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e1125f79b574932cffa3616ba6a33244141a32634f797ffe0bd7fb068e83a6b +size 2537136224 diff --git a/Llama-3-6B-Granite-v0.1.Q3_K_L.gguf b/Llama-3-6B-Granite-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..a982ab8 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca27a227ebe65a5fe2311517663ed889106e3fc62be098e614a013eeb301cdf +size 3407593568 diff --git a/Llama-3-6B-Granite-v0.1.Q3_K_M.gguf b/Llama-3-6B-Granite-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..ea09eee --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d04b6910f4431d3b65e319a9de9ee8104f4ff75048d88982bed00c54616d7b7c +size 3176906848 diff --git a/Llama-3-6B-Granite-v0.1.Q3_K_S.gguf b/Llama-3-6B-Granite-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..e98a6c4 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f04738256613f00ebc82130b834a37ae93898d318ebf3f150aa24ed958ae205 +size 2914500704 diff --git a/Llama-3-6B-Granite-v0.1.Q4_K_M.gguf b/Llama-3-6B-Granite-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..94c4336 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5359b3feb5d717ba68e02877de9fa72b6b87d7867036a9069613b755e521e12 +size 3874119776 diff --git a/Llama-3-6B-Granite-v0.1.Q4_K_S.gguf b/Llama-3-6B-Granite-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..5736bc1 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a9d90916902203573b405edc971fba6e4ea47112d3f2f11ec1ccb8b007e32d +size 3703595104 diff --git a/Llama-3-6B-Granite-v0.1.Q5_K_M.gguf b/Llama-3-6B-Granite-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..d6c3c76 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46eaf053f3d03e83a7d2b07df0dc45efd302a919581bc3bd0d6c87f83c2dc8eb +size 4499726432 diff --git a/Llama-3-6B-Granite-v0.1.Q5_K_S.gguf b/Llama-3-6B-Granite-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..173dbdb --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97a4cc216fa3e1ad2f2e9050492af9ab4480be1f1e995eaaa2ce0a83d0944c2 +size 4399456352 diff --git a/Llama-3-6B-Granite-v0.1.Q6_K.gguf b/Llama-3-6B-Granite-v0.1.Q6_K.gguf new file mode 100644 index 0000000..4925923 --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9feab4331f4bc1b10ee265ed34205469d8c6e3cf9a54ecc55ee7b425b1d5f23a +size 5164433504 diff --git a/Llama-3-6B-Granite-v0.1.Q8_0.gguf b/Llama-3-6B-Granite-v0.1.Q8_0.gguf new file mode 100644 index 0000000..3056f6a --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e83533ac5f2ba957ad4cbc32012f7b39f561c1906a8c3a1b486442f237778bf +size 6686621792 diff --git a/Llama-3-6B-Granite-v0.1.f16.gguf b/Llama-3-6B-Granite-v0.1.f16.gguf new file mode 100644 index 0000000..d25cb1d --- /dev/null +++ b/Llama-3-6B-Granite-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:693cff1a559dec31277c456eea9f03dd47803f0f4c3c2d3c3f21aa590c3f9eed +size 12578963552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5185f82 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: prince-canuma/Llama-3-6B-Granite-v0.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/prince-canuma/Llama-3-6B-Granite-v0.1 + + +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-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.IQ3_M.gguf) | IQ3_M | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q3_K_M.gguf) | Q3_K_M | 3.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q3_K_L.gguf) | Q3_K_L | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.IQ4_XS.gguf) | IQ4_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q4_K_S.gguf) | Q4_K_S | 3.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q4_K_M.gguf) | Q4_K_M | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q5_K_S.gguf) | Q5_K_S | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q5_K_M.gguf) | Q5_K_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q6_K.gguf) | Q6_K | 5.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.Q8_0.gguf) | Q8_0 | 6.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-6B-Granite-v0.1-GGUF/resolve/main/Llama-3-6B-Granite-v0.1.f16.gguf) | f16 | 12.7 | 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. + +