commit 25698b36ae3649b60474e59f2164ebb1297492dc Author: ModelHub XC Date: Sun Jun 14 17:16:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-SOLAR-v0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef12945 --- /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 +Llama-3-SOLAR-v0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-SOLAR-v0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-SOLAR-v0.1.IQ4_XS.gguf b/Llama-3-SOLAR-v0.1.IQ4_XS.gguf new file mode 100644 index 0000000..63c1119 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01d7fa1b20841612ae3d53042fc0181cc0ac16827c87f453c59a878df285823f +size 4484363328 diff --git a/Llama-3-SOLAR-v0.1.Q2_K.gguf b/Llama-3-SOLAR-v0.1.Q2_K.gguf new file mode 100644 index 0000000..c73d3e5 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b40e4b1c1a593db404da94ef9123c4b2854f78375b1fb518aabe4ecfb2f6b9 +size 3179131968 diff --git a/Llama-3-SOLAR-v0.1.Q3_K_L.gguf b/Llama-3-SOLAR-v0.1.Q3_K_L.gguf new file mode 100644 index 0000000..6655cfa --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d94ce92bd0676e07e575353faff75ff311d6a88ec52c8bc447e09432362209c9 +size 4321956928 diff --git a/Llama-3-SOLAR-v0.1.Q3_K_M.gguf b/Llama-3-SOLAR-v0.1.Q3_K_M.gguf new file mode 100644 index 0000000..1b404e0 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1041467fd97ab3a3c81a72a5c12ef194b0085fab02178af339ea08d2eb8a0bf8 +size 4018918464 diff --git a/Llama-3-SOLAR-v0.1.Q3_K_S.gguf b/Llama-3-SOLAR-v0.1.Q3_K_S.gguf new file mode 100644 index 0000000..4229f3d --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06897ef3353463ef4aac078795a7ca8046bf356d75eb77e5ad9beac6a499e604 +size 3664499776 diff --git a/Llama-3-SOLAR-v0.1.Q4_K_M.gguf b/Llama-3-SOLAR-v0.1.Q4_K_M.gguf new file mode 100644 index 0000000..930e233 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce696c0d3f85ad903a7bfa1a041e2355ba7ecc99b9873bc2cea82a6cadae84d0 +size 4920734784 diff --git a/Llama-3-SOLAR-v0.1.Q4_K_S.gguf b/Llama-3-SOLAR-v0.1.Q4_K_S.gguf new file mode 100644 index 0000000..e99f1a8 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95690651b1b76cff3dc5d41fca41444096616a72496569c50aed9b90396e777 +size 4692669504 diff --git a/Llama-3-SOLAR-v0.1.Q5_K_M.gguf b/Llama-3-SOLAR-v0.1.Q5_K_M.gguf new file mode 100644 index 0000000..88d3754 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d69f035c7ff92dcf7b75df014c971def9189b73d4f38b8f0604b12525a7bce7 +size 5732987968 diff --git a/Llama-3-SOLAR-v0.1.Q5_K_S.gguf b/Llama-3-SOLAR-v0.1.Q5_K_S.gguf new file mode 100644 index 0000000..0690247 --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14894370e24dc6adc7419d5e18c08b78c181884f8fc057dd01f77da335ce2891 +size 5599294528 diff --git a/Llama-3-SOLAR-v0.1.Q6_K.gguf b/Llama-3-SOLAR-v0.1.Q6_K.gguf new file mode 100644 index 0000000..4ba15de --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25e5a501a6bbc90f4db7586be6ebc46dc386fb8d16897435b28e2b5f95545b50 +size 6596006976 diff --git a/Llama-3-SOLAR-v0.1.Q8_0.gguf b/Llama-3-SOLAR-v0.1.Q8_0.gguf new file mode 100644 index 0000000..9ea18ab --- /dev/null +++ b/Llama-3-SOLAR-v0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec56e37aa1ebd94357491e45acbb841a18dec4e1bfed53537433b07b7daf076c +size 8540771392 diff --git a/Llama-3-SOLAR-v0.1.f16.gguf b/Llama-3-SOLAR-v0.1.f16.gguf new file mode 100644 index 0000000..8df6cbd --- /dev/null +++ b/Llama-3-SOLAR-v0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78ddea8b4dcb91dd18f00708ae5c53fb8ca2c9c9a4b97fc6952d60748664ce7 +size 16068891712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bb7ce5e --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: cookinai/Llama-3-SOLAR-v0.1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/cookinai/Llama-3-SOLAR-v0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-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/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-SOLAR-v0.1-GGUF/resolve/main/Llama-3-SOLAR-v0.1.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. + +