commit dcf6a22c47bbc3cb9159dbaa10ab475ad3f1adfb Author: ModelHub XC Date: Thu Aug 6 22:47:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-2-7B-RMU-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..44d2e00 --- /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-2-7B-RMU.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-2-7B-RMU.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-2-7B-RMU.IQ3_M.gguf b/Llama-2-7B-RMU.IQ3_M.gguf new file mode 100644 index 0000000..11fcdd8 --- /dev/null +++ b/Llama-2-7B-RMU.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25faa9a38698eb090fcb0c6e41cb70eb701994d10cc9bd0ba542cd77c9c6b6f7 +size 3114865824 diff --git a/Llama-2-7B-RMU.IQ3_S.gguf b/Llama-2-7B-RMU.IQ3_S.gguf new file mode 100644 index 0000000..5b3612a --- /dev/null +++ b/Llama-2-7B-RMU.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0f42a0b3a5d96efd77065731db70626cea2996db314adf127e7c218016e6aa +size 2948306080 diff --git a/Llama-2-7B-RMU.IQ3_XS.gguf b/Llama-2-7B-RMU.IQ3_XS.gguf new file mode 100644 index 0000000..308d9ba --- /dev/null +++ b/Llama-2-7B-RMU.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d620bd25731a6833f0e2384e5b533d201392995a7567d7ad88acbaea6d1490a +size 2796524704 diff --git a/Llama-2-7B-RMU.IQ4_XS.gguf b/Llama-2-7B-RMU.IQ4_XS.gguf new file mode 100644 index 0000000..55b69af --- /dev/null +++ b/Llama-2-7B-RMU.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a8e5a388fb6e76564be55635b7e7591c6b4bbdc20b45ac75107fd861fe6b22 +size 3647517856 diff --git a/Llama-2-7B-RMU.Q2_K.gguf b/Llama-2-7B-RMU.Q2_K.gguf new file mode 100644 index 0000000..15839f4 --- /dev/null +++ b/Llama-2-7B-RMU.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7488c82f7f8697883b1f24dd36eeb0fbd2b69e329b54b07bf7974818f638a385 +size 2532865184 diff --git a/Llama-2-7B-RMU.Q3_K_L.gguf b/Llama-2-7B-RMU.Q3_K_L.gguf new file mode 100644 index 0000000..bb52365 --- /dev/null +++ b/Llama-2-7B-RMU.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:100626421b2e6a3916b24c1fd8f957e47fe91f1a40e9bf3d948c531d710488b8 +size 3597112480 diff --git a/Llama-2-7B-RMU.Q3_K_M.gguf b/Llama-2-7B-RMU.Q3_K_M.gguf new file mode 100644 index 0000000..bd08c80 --- /dev/null +++ b/Llama-2-7B-RMU.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eb2d7a201b99207ba3754c1c86107df761bd04f8a8622308e76860139f3a8f +size 3298006176 diff --git a/Llama-2-7B-RMU.Q3_K_S.gguf b/Llama-2-7B-RMU.Q3_K_S.gguf new file mode 100644 index 0000000..e3b613e --- /dev/null +++ b/Llama-2-7B-RMU.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea37463824d80c72f4d9c1c81622b45fd9ccda241ca9770ab69ecde6e1926de +size 2948306080 diff --git a/Llama-2-7B-RMU.Q4_K_M.gguf b/Llama-2-7B-RMU.Q4_K_M.gguf new file mode 100644 index 0000000..d860a1e --- /dev/null +++ b/Llama-2-7B-RMU.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:106acb86c3d66e24fd29ff8edc4384517a918160f49468a8a854ec4f61801abb +size 4081005728 diff --git a/Llama-2-7B-RMU.Q4_K_S.gguf b/Llama-2-7B-RMU.Q4_K_S.gguf new file mode 100644 index 0000000..d4e1059 --- /dev/null +++ b/Llama-2-7B-RMU.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7249fc9c73ab9fa61ad78029b4e20420767a40b392bf15feab6b02ee5e08deb1 +size 3856741536 diff --git a/Llama-2-7B-RMU.Q5_K_M.gguf b/Llama-2-7B-RMU.Q5_K_M.gguf new file mode 100644 index 0000000..7cf9a95 --- /dev/null +++ b/Llama-2-7B-RMU.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf3b32a1b9deac278ccce2e6b7b9c24dc80963a0b919f9d927c1097f8c799fc +size 4783158432 diff --git a/Llama-2-7B-RMU.Q5_K_S.gguf b/Llama-2-7B-RMU.Q5_K_S.gguf new file mode 100644 index 0000000..04c4e68 --- /dev/null +++ b/Llama-2-7B-RMU.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61966a80b889c0da49ba6b45a1112ad48f98533b6df33a74af12a33178ab0ea4 +size 4651693216 diff --git a/Llama-2-7B-RMU.Q6_K.gguf b/Llama-2-7B-RMU.Q6_K.gguf new file mode 100644 index 0000000..d0b89b6 --- /dev/null +++ b/Llama-2-7B-RMU.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c6b754c475b66d238e9b7f6a77db3725c8964cccd428f23ba0a5004cf963f46 +size 5529195680 diff --git a/Llama-2-7B-RMU.Q8_0.gguf b/Llama-2-7B-RMU.Q8_0.gguf new file mode 100644 index 0000000..b66dd05 --- /dev/null +++ b/Llama-2-7B-RMU.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d69755729693e453b34281ce9e942fa23ce6a18d4f9a2121c28c7f128cd7534 +size 7161091232 diff --git a/Llama-2-7B-RMU.f16.gguf b/Llama-2-7B-RMU.f16.gguf new file mode 100644 index 0000000..38d6432 --- /dev/null +++ b/Llama-2-7B-RMU.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd43c643185b2943fa9189c02ce09b2edd6fd2ca4f538cdd08cce1331f09f1c +size 13478106272 diff --git a/README.md b/README.md new file mode 100644 index 0000000..de5d2d4 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: justinphan3110/Llama-2-7B-RMU +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/justinphan3110/Llama-2-7B-RMU + + +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-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.IQ3_XS.gguf) | IQ3_XS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.IQ3_S.gguf) | IQ3_S | 3.0 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.IQ3_M.gguf) | IQ3_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-2-7B-RMU-GGUF/resolve/main/Llama-2-7B-RMU.f16.gguf) | f16 | 13.6 | 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. + +