commit 55238bd89b1c1226f8058d6514cefe12cc5c9d3f Author: ModelHub XC Date: Sun Jun 21 15:57:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cddb35a --- /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_3.1_8b_MeDeepDive_V1.01.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_MeDeepDive_V1.01.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.IQ4_XS.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.IQ4_XS.gguf new file mode 100644 index 0000000..4365522 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0371dfb41990f2d838cf1aedadd84569b8c126f4e43ab41b24270f0af3244704 +size 4484542208 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q2_K.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q2_K.gguf new file mode 100644 index 0000000..f165e14 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53eac5ed81cb9d723bff8f0b1da57ce98d806e30a3d39aa98f2afa4d572e5c6 +size 3179284224 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_L.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_L.gguf new file mode 100644 index 0000000..3134682 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c1bc2499ed13041fc9cdd05d8bf119e7b33977ced89dacf6e7b951a5b28f9ab +size 4322122496 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_M.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_M.gguf new file mode 100644 index 0000000..f727be5 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d78721626e2331b30610abb236cb6681038665856d8b3bf6be53c1bf42f6a4a +size 4019084032 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_S.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_S.gguf new file mode 100644 index 0000000..f3fc20f --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752a77cdfd1b25ef629e9c107a275e0d70ce44ab055487886aa189adcea053e6 +size 3664665344 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_M.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_M.gguf new file mode 100644 index 0000000..e6f07fd --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b683336d64ab7aaffb0cb8fa19be73c41771def250ff8ad2df7b7382e47c24fa +size 4920917760 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_S.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_S.gguf new file mode 100644 index 0000000..4a49c14 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2acdcb62a2f31f2c2632aee8062329a3b862046461525cfbfb491d059d3faada +size 4692852480 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_M.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_M.gguf new file mode 100644 index 0000000..afc49f6 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a56801dcab918ffedef24638972b017a753974c0aad497dd52c64204305bca +size 5733187328 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_S.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_S.gguf new file mode 100644 index 0000000..38d50c6 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ad5e7d4371057c4ec63dd1ba3bfbb012f732b99ab8650dad7158e1d8902ab3 +size 5599493888 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q6_K.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q6_K.gguf new file mode 100644 index 0000000..e619764 --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6033cdb70687b3b7b83d6acba39fab3393cf0c727e26378b8208e83d3c59726a +size 6596223744 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.Q8_0.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.Q8_0.gguf new file mode 100644 index 0000000..69cb4dc --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04776c58e1264d8e498007155fcdac878aedd207ae22916927bc326c295c7bbd +size 8541051648 diff --git a/Llama_3.1_8b_MeDeepDive_V1.01.f16.gguf b/Llama_3.1_8b_MeDeepDive_V1.01.f16.gguf new file mode 100644 index 0000000..ccea8ed --- /dev/null +++ b/Llama_3.1_8b_MeDeepDive_V1.01.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd270ce5e13546249f9cdf7e533b09f31b525b6d91fb1e9693e5b626faa14771 +size 16069417728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ccc48df --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_MeDeepDive_V1.01 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_MeDeepDive_V1.01 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama_3.1_8b_MeDeepDive_V1.01-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-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_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_MeDeepDive_V1.01-GGUF/resolve/main/Llama_3.1_8b_MeDeepDive_V1.01.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. + +