commit 3d36bd5337e3421c052034e870598fcd5824a412 Author: ModelHub XC Date: Mon Jul 13 12:04:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SOVL_Llama3_8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b65f198 --- /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 +SOVL_Llama3_8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +SOVL_Llama3_8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e32705a --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: ResplendentAI/SOVL_Llama3_8B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + +static quants of https://huggingface.co/ResplendentAI/SOVL_Llama3_8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SOVL_Llama3_8B-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/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SOVL_Llama3_8B-GGUF/resolve/main/SOVL_Llama3_8B.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. + + diff --git a/SOVL_Llama3_8B.IQ3_M.gguf b/SOVL_Llama3_8B.IQ3_M.gguf new file mode 100644 index 0000000..39ff7e0 --- /dev/null +++ b/SOVL_Llama3_8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c94e2ad481f89e9710c0feb881ce40a12970a940a0f7716f242263f97b610e45 +size 3785336064 diff --git a/SOVL_Llama3_8B.IQ3_S.gguf b/SOVL_Llama3_8B.IQ3_S.gguf new file mode 100644 index 0000000..8a5cdd3 --- /dev/null +++ b/SOVL_Llama3_8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1068a34bf9154864ac8fb911fa01e411cc3b0e401653aa3d118334e3fb7d287 +size 3682837760 diff --git a/SOVL_Llama3_8B.IQ3_XS.gguf b/SOVL_Llama3_8B.IQ3_XS.gguf new file mode 100644 index 0000000..831728b --- /dev/null +++ b/SOVL_Llama3_8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b61e6099bb64c19c4577e7db914811d8ad9cf661fecc62b74b6fceb7bf5dca +size 3519259904 diff --git a/SOVL_Llama3_8B.IQ4_XS.gguf b/SOVL_Llama3_8B.IQ4_XS.gguf new file mode 100644 index 0000000..e700b0f --- /dev/null +++ b/SOVL_Llama3_8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:680897725dac662e7f342ae9cd1fe8a7e9507260ff490ea29ecc04225037796a +size 4484875520 diff --git a/SOVL_Llama3_8B.Q2_K.gguf b/SOVL_Llama3_8B.Q2_K.gguf new file mode 100644 index 0000000..b1048d1 --- /dev/null +++ b/SOVL_Llama3_8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b8df10b66fd4e98af4158ba62f82c00dac25b9b8ebeb8c93431039dafa5382 +size 3179644160 diff --git a/SOVL_Llama3_8B.Q3_K_L.gguf b/SOVL_Llama3_8B.Q3_K_L.gguf new file mode 100644 index 0000000..ff586bc --- /dev/null +++ b/SOVL_Llama3_8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be744650cdacdea9b50d5de6a5a25436351bd91734053283f55bcfadfa2e0ee +size 4322469120 diff --git a/SOVL_Llama3_8B.Q3_K_M.gguf b/SOVL_Llama3_8B.Q3_K_M.gguf new file mode 100644 index 0000000..e27f765 --- /dev/null +++ b/SOVL_Llama3_8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8870e5da71949ac6e287e0363a9fbea02c82d51c917aa349b373411b6c8348fd +size 4019430656 diff --git a/SOVL_Llama3_8B.Q3_K_S.gguf b/SOVL_Llama3_8B.Q3_K_S.gguf new file mode 100644 index 0000000..b7dfbc5 --- /dev/null +++ b/SOVL_Llama3_8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf445cf70b163936b58217458b89cf2bd1bb0a5368422645b6146079a342c264 +size 3665011968 diff --git a/SOVL_Llama3_8B.Q4_K_M.gguf b/SOVL_Llama3_8B.Q4_K_M.gguf new file mode 100644 index 0000000..289a005 --- /dev/null +++ b/SOVL_Llama3_8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8072e4923618fb67ddb8f69c4784d4e3b2d97cb80ee099a45c7f90d46fba82ea +size 4921246976 diff --git a/SOVL_Llama3_8B.Q4_K_S.gguf b/SOVL_Llama3_8B.Q4_K_S.gguf new file mode 100644 index 0000000..20b0c65 --- /dev/null +++ b/SOVL_Llama3_8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efd035c45f6528008ab387cff7cb94a8069f4444ea1e8ab05de9346d3dcd5831 +size 4693181696 diff --git a/SOVL_Llama3_8B.Q5_K_M.gguf b/SOVL_Llama3_8B.Q5_K_M.gguf new file mode 100644 index 0000000..26ddb47 --- /dev/null +++ b/SOVL_Llama3_8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dcbf68e771133b1d79489465cd4a1d186e5766d6e14cb96f7a04cb6bc1727fe +size 5733500160 diff --git a/SOVL_Llama3_8B.Q5_K_S.gguf b/SOVL_Llama3_8B.Q5_K_S.gguf new file mode 100644 index 0000000..02fa74f --- /dev/null +++ b/SOVL_Llama3_8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f5ea36dead953b4233d675cef3880118a3f762bd89e222eac89937868b02b2 +size 5599806720 diff --git a/SOVL_Llama3_8B.Q6_K.gguf b/SOVL_Llama3_8B.Q6_K.gguf new file mode 100644 index 0000000..911791a --- /dev/null +++ b/SOVL_Llama3_8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d801a331fda1030883f91d8b17f62bf99e5019eb6803a4937dfffe2e70bd5838 +size 6596519168 diff --git a/SOVL_Llama3_8B.Q8_0.gguf b/SOVL_Llama3_8B.Q8_0.gguf new file mode 100644 index 0000000..68942bc --- /dev/null +++ b/SOVL_Llama3_8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda6160eb0deaad33468137a8879ecb122eab1cb12ae29235bd170915e862af0 +size 8541283584 diff --git a/SOVL_Llama3_8B.f16.gguf b/SOVL_Llama3_8B.f16.gguf new file mode 100644 index 0000000..a050be5 --- /dev/null +++ b/SOVL_Llama3_8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00e6e1e40bc1421dae65a722eb834161c4614868629edb05b04fc3c7c607397 +size 16069403904