commit 4db5b3edba6e696c60e3a44d05ddb5fcdb2f6764 Author: ModelHub XC Date: Wed Jun 17 12:26:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f170dda --- /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_3.1_8b_Hermedive_R1_V1.01.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama_3.1_8b_Hermedive_R1_V1.01.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.IQ4_XS.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.IQ4_XS.gguf new file mode 100644 index 0000000..29b0fa3 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f70ff5b2428825158885d5bb22620c73fd7ce973d0fbe7f77fc98f60c784073 +size 4484375616 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q2_K.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q2_K.gguf new file mode 100644 index 0000000..fe1333b --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb87ce9c2b7759f568af3b19d121a672f904f470e55003dde72af825517f348 +size 3179142592 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_L.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_L.gguf new file mode 100644 index 0000000..f7650b7 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ce5ee59b58d4a44c04f9516a7381b30dd86648f05204b2a159e79c46c7e5ce9 +size 4321968384 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_M.gguf new file mode 100644 index 0000000..e750a93 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:627ed7dc35aea94546a57f1cab43c2746b298000fff28684cd913956bab3cc42 +size 4018929920 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_S.gguf new file mode 100644 index 0000000..1bda0ee --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e17110857faa780523513193ebb1f9f8cc4b28c282a847a99b5ff8740aa6e1 +size 3664511232 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_M.gguf new file mode 100644 index 0000000..987ef24 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffdfc0e6554c93a25d9e9923b56622f10361d4686b73b3650363fc3a3516e3f8 +size 4920747328 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_S.gguf new file mode 100644 index 0000000..7979aaf --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da2afe4e8bb84ae50d6a50e3bb379c07948411a7cac8ed4ddcc6e954684934b3 +size 4692682048 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_M.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_M.gguf new file mode 100644 index 0000000..825c836 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e958a9a2e4cfede210aaba883e38a2f32f6e9dc309b6f4338ded0c05075a527e +size 5733001536 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_S.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_S.gguf new file mode 100644 index 0000000..b8fde85 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eda28d63e4e2ef0055f8a8d754fcf8dde498e4b2ca52f41662ab1bb33d751b56 +size 5599308096 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q6_K.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q6_K.gguf new file mode 100644 index 0000000..089fd75 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47e4a29e2822df882c5c00f7713718dc470eff52d538a8937755773051b1b07 +size 6596021632 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.Q8_0.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.Q8_0.gguf new file mode 100644 index 0000000..23afd7c --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9daec73a4c2e8043ab5f34ec643b6943d48799b73df23b37ef02b026a1a79cf3 +size 8540790016 diff --git a/Llama_3.1_8b_Hermedive_R1_V1.01.f16.gguf b/Llama_3.1_8b_Hermedive_R1_V1.01.f16.gguf new file mode 100644 index 0000000..d341811 --- /dev/null +++ b/Llama_3.1_8b_Hermedive_R1_V1.01.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae1f1997a2dafced97a6b7cd9c5230da6b2a3355f1284476573baeb4c512e8d +size 16068925696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..adbca9b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Nexesenex/Llama_3.1_8b_Hermedive_R1_V1.01 +language: +- en +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Llama_3.1_8b_Hermedive_R1_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_Hermedive_R1_V1.01-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_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_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_V1.01.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama_3.1_8b_Hermedive_R1_V1.01-GGUF/resolve/main/Llama_3.1_8b_Hermedive_R1_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. + +