commit bd4951a39c8d5d2ed020f3e30f7433ae77a46364 Author: ModelHub XC Date: Tue Jul 7 07:54:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLama3.1-Rhino-8B-RAG-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f738a4 --- /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 +LLama3.1-Rhino-8B-RAG.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLama3.1-Rhino-8B-RAG.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLama3.1-Rhino-8B-RAG.IQ4_XS.gguf b/LLama3.1-Rhino-8B-RAG.IQ4_XS.gguf new file mode 100644 index 0000000..3a8c4c6 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:719eef04cf32c9c20676e32a8dd90dad153d2d427f40a2ac02bd5d6c5bdd5800 +size 4484368384 diff --git a/LLama3.1-Rhino-8B-RAG.Q2_K.gguf b/LLama3.1-Rhino-8B-RAG.Q2_K.gguf new file mode 100644 index 0000000..1b94cb6 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0455433d45ad257a66ce29e7237ccc316c0edd84b43ff946180288b62f1ae3a +size 3179137024 diff --git a/LLama3.1-Rhino-8B-RAG.Q3_K_L.gguf b/LLama3.1-Rhino-8B-RAG.Q3_K_L.gguf new file mode 100644 index 0000000..d6229c2 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3cccca08845a60aa0d9dbe9e0aa641e147dfba8c1cca2e2392d8fd281a89b6f +size 4321961984 diff --git a/LLama3.1-Rhino-8B-RAG.Q3_K_M.gguf b/LLama3.1-Rhino-8B-RAG.Q3_K_M.gguf new file mode 100644 index 0000000..af3da66 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3802bfaa97019c427a9518e2eec4aef055d66ebea1712a4e39dffa06003fbba +size 4018923520 diff --git a/LLama3.1-Rhino-8B-RAG.Q3_K_S.gguf b/LLama3.1-Rhino-8B-RAG.Q3_K_S.gguf new file mode 100644 index 0000000..df358ac --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30439b53e10efde82927646d82f851efde4750a929c24ce8672ad0f4c7ebb489 +size 3664504832 diff --git a/LLama3.1-Rhino-8B-RAG.Q4_K_M.gguf b/LLama3.1-Rhino-8B-RAG.Q4_K_M.gguf new file mode 100644 index 0000000..fecf9dc --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e35b11d5ff32d9db43d40c8e894a37f0df90019e421e5769fa78b71c8db12d +size 4920739840 diff --git a/LLama3.1-Rhino-8B-RAG.Q4_K_S.gguf b/LLama3.1-Rhino-8B-RAG.Q4_K_S.gguf new file mode 100644 index 0000000..dbe7ed2 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8c49c46df8813461500774b9cda829036b21b5a1a03003d42f44cdf664e7c9 +size 4692674560 diff --git a/LLama3.1-Rhino-8B-RAG.Q5_K_M.gguf b/LLama3.1-Rhino-8B-RAG.Q5_K_M.gguf new file mode 100644 index 0000000..1f3b07e --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0bc0a09d496b6055315a673ebacfbcffa122eb7c34ee63c9d399f70dc22d79 +size 5732993024 diff --git a/LLama3.1-Rhino-8B-RAG.Q5_K_S.gguf b/LLama3.1-Rhino-8B-RAG.Q5_K_S.gguf new file mode 100644 index 0000000..ae4ec2a --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc5385a41815f16cb46524f40e8dc5f31cafbf6c3ea421576ba004520067868 +size 5599299584 diff --git a/LLama3.1-Rhino-8B-RAG.Q6_K.gguf b/LLama3.1-Rhino-8B-RAG.Q6_K.gguf new file mode 100644 index 0000000..015823b --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef8046186dee9eb5c33ac60fa5247bbabf8c2046a18222a8a075c8af7b99ce7f +size 6596012032 diff --git a/LLama3.1-Rhino-8B-RAG.Q8_0.gguf b/LLama3.1-Rhino-8B-RAG.Q8_0.gguf new file mode 100644 index 0000000..7a0e8c1 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d22014d64ac581963b8f77e4dc985b63e7d8b66d9f7af89be1245ef4a34ae2 +size 8540776448 diff --git a/LLama3.1-Rhino-8B-RAG.f16.gguf b/LLama3.1-Rhino-8B-RAG.f16.gguf new file mode 100644 index 0000000..af41f38 --- /dev/null +++ b/LLama3.1-Rhino-8B-RAG.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:217ec67b760421f2b8b57dbbabc5a44ac2bd3f2faf01f9b08974697336b9efeb +size 16068896768 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c84acc2 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: QomSSLab/LLama3.1-Rhino-8B-RAG +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/QomSSLab/LLama3.1-Rhino-8B-RAG + + +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/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLama3.1-Rhino-8B-RAG-GGUF/resolve/main/LLama3.1-Rhino-8B-RAG.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. + +