commit 6c8245ae244a21885f15bc009bfa9b6e2d289764 Author: ModelHub XC Date: Wed Sep 16 16:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..796fb28 --- /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 +Llama-3-8B-Instruct-Rumsan-RAG2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-Instruct-Rumsan-RAG2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_M.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_M.gguf new file mode 100644 index 0000000..23f2bb1 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e20d1f152b652a71fb0c0ca499402e2b0f074831308c7e277c1c2fe0908939b +size 3784864960 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_S.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_S.gguf new file mode 100644 index 0000000..aff6256 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f3cb432f1f827b0eee1914fb9ae48d1a7a5aaf3112efa5ce1d7d6c9807d037 +size 3682366656 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_XS.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_XS.gguf new file mode 100644 index 0000000..3e072a8 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce0391e9919d69016ce02ea632ba2ef1bcdf0058794bb91daf67f7f83e14a7a +size 3518788800 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.IQ4_XS.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ4_XS.gguf new file mode 100644 index 0000000..be8c389 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536e8e93c45dab3a16e768e3f23d586c8da636e87a194e2fa6deef0356b9d644 +size 4484407744 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q2_K.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q2_K.gguf new file mode 100644 index 0000000..c54da9c --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7d49c8d491ee6b4e5e5d695eb2d5ffebd65dab0dba86c827c63e7ce9f21c01 +size 3179169728 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_L.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_L.gguf new file mode 100644 index 0000000..421cb20 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51ad064f2dd2a451e173f4d5319847bca2688ba580a47e2c4121a507a457455e +size 4321998016 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_M.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_M.gguf new file mode 100644 index 0000000..77f6af0 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e82d9a82849bdba401839b4b61939cba11cf135c9d7f215d60620852f3f0d05b +size 4018959552 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_S.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_S.gguf new file mode 100644 index 0000000..c56b0de --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ab55a425c263d3072dca424b53bfde981991d9d56f6989d7ddbe8e6cd77a21 +size 3664540864 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_M.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_M.gguf new file mode 100644 index 0000000..19e9c65 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8085358c6b7dcccc90a67843a227175983026fc037bb83ee0c9a92cc0dda89b6 +size 4920780224 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_S.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_S.gguf new file mode 100644 index 0000000..fbd1e8f --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dea188fbdb5258e8d1043afa46f6d4d3fe83185df05641c13e8fb092ed39642 +size 4692714944 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_M.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_M.gguf new file mode 100644 index 0000000..4249f2a --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6630bbcf196f33118b6320e484b71edcbb999a726aca2cdcdf121c1c30a2144e +size 5733037504 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_S.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_S.gguf new file mode 100644 index 0000000..af4d65c --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f07c1ca3cbe73ef2989cfe7c92338ea0f4ec16662f0a4bad0f55b7442a5c47a6 +size 5599344064 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q6_K.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q6_K.gguf new file mode 100644 index 0000000..9fe8327 --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a2b97af09a6728ada50c362b960c45878e9a7daf15939969ebb1dd82165df4 +size 6596060864 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.Q8_0.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.Q8_0.gguf new file mode 100644 index 0000000..da7663e --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bed339a42af55b8c2724b25f399aa10a33fa89e749b0e95b523cca2aebb2e3 +size 8540841152 diff --git a/Llama-3-8B-Instruct-Rumsan-RAG2.f16.gguf b/Llama-3-8B-Instruct-Rumsan-RAG2.f16.gguf new file mode 100644 index 0000000..4f2fbac --- /dev/null +++ b/Llama-3-8B-Instruct-Rumsan-RAG2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf257175c49d4872c08d27f79ad28825ab1ffd3a98c26cddd9b5f9316fdebecd +size 16069022912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0982958 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: sakshi-rumsan/Llama-3-8B-Instruct-Rumsan-RAG2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/sakshi-rumsan/Llama-3-8B-Instruct-Rumsan-RAG2 + + +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/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-Rumsan-RAG2-GGUF/resolve/main/Llama-3-8B-Instruct-Rumsan-RAG2.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. + +