commit 004504e3db1a085b14ed26321efe15d54fd172a1 Author: ModelHub XC Date: Thu May 14 09:09:47 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Express.1-Merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..04ab091 --- /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-Express.1-Merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Express.1-Merged.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Express.1-Merged.IQ4_XS.gguf b/Llama-Express.1-Merged.IQ4_XS.gguf new file mode 100644 index 0000000..9770bd3 --- /dev/null +++ b/Llama-Express.1-Merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8057b7ef810795f5891867ee6d4f6688e81b9c9237542b62e8a2a6f47d25d67f +size 748385856 diff --git a/Llama-Express.1-Merged.Q2_K.gguf b/Llama-Express.1-Merged.Q2_K.gguf new file mode 100644 index 0000000..803d51d --- /dev/null +++ b/Llama-Express.1-Merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:604673ecf7f8aaf7cc3d99ac58a88f800f1f8a6a6910d601c6363f2632c8ecbe +size 580875840 diff --git a/Llama-Express.1-Merged.Q3_K_L.gguf b/Llama-Express.1-Merged.Q3_K_L.gguf new file mode 100644 index 0000000..4467e21 --- /dev/null +++ b/Llama-Express.1-Merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a253f20048640345b6a19f90eb911ad7d16a2ab378d373d8685d7ae3c535bf1 +size 732526144 diff --git a/Llama-Express.1-Merged.Q3_K_M.gguf b/Llama-Express.1-Merged.Q3_K_M.gguf new file mode 100644 index 0000000..ebe9e1a --- /dev/null +++ b/Llama-Express.1-Merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00843868caddf174ad3a8f81b942b96a315b525453651c70b943d8d728db6b3c +size 690845248 diff --git a/Llama-Express.1-Merged.Q3_K_S.gguf b/Llama-Express.1-Merged.Q3_K_S.gguf new file mode 100644 index 0000000..4ea48c6 --- /dev/null +++ b/Llama-Express.1-Merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddfeed3877e83647157635cc93afb15f46317c9d254ae57be48f0e6826ba0795 +size 641693248 diff --git a/Llama-Express.1-Merged.Q4_K_M.gguf b/Llama-Express.1-Merged.Q4_K_M.gguf new file mode 100644 index 0000000..29750c2 --- /dev/null +++ b/Llama-Express.1-Merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1b04e958cc8ea64663fd8982536e60261a49f7a81dfcf467e3cad580263d3f1 +size 807695936 diff --git a/Llama-Express.1-Merged.Q4_K_S.gguf b/Llama-Express.1-Merged.Q4_K_S.gguf new file mode 100644 index 0000000..4cd7a92 --- /dev/null +++ b/Llama-Express.1-Merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d18fe5e18bb0daaa3ef94989b680d2747b798237ccf85a89e9df72eefb2ab39 +size 775648832 diff --git a/Llama-Express.1-Merged.Q5_K_M.gguf b/Llama-Express.1-Merged.Q5_K_M.gguf new file mode 100644 index 0000000..731b572 --- /dev/null +++ b/Llama-Express.1-Merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8764e8b1f08df8c84ce0cc09b51b58e32bfac970508361c6afa643342d678bbb +size 911504960 diff --git a/Llama-Express.1-Merged.Q5_K_S.gguf b/Llama-Express.1-Merged.Q5_K_S.gguf new file mode 100644 index 0000000..354085f --- /dev/null +++ b/Llama-Express.1-Merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c0fb8790aa90bb306e7539b3a037084f26803ac2e01939fa3ea53328ad8871 +size 892565056 diff --git a/Llama-Express.1-Merged.Q6_K.gguf b/Llama-Express.1-Merged.Q6_K.gguf new file mode 100644 index 0000000..a3f815d --- /dev/null +++ b/Llama-Express.1-Merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c951b74749fea12bdf74fa376fed1a4e74f1ea1807c66d7058922dff8996cdb +size 1021802048 diff --git a/Llama-Express.1-Merged.Q8_0.gguf b/Llama-Express.1-Merged.Q8_0.gguf new file mode 100644 index 0000000..71f863b --- /dev/null +++ b/Llama-Express.1-Merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3c36f891134848bf32e2f5b414d639613e707538b13d40f81eb55a63e1c96bc +size 1321084480 diff --git a/Llama-Express.1-Merged.f16.gguf b/Llama-Express.1-Merged.f16.gguf new file mode 100644 index 0000000..977cee3 --- /dev/null +++ b/Llama-Express.1-Merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b775b1782ce9f7410ee4bd91c8022690dcce0d71d8596b6b4bfc04d992b6151 +size 2479597120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ab45963 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: prithivMLmods/Llama-Express.1-Merged +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Llama-Express.1-Merged + + +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-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Express.1-Merged-GGUF/resolve/main/Llama-Express.1-Merged.f16.gguf) | f16 | 2.6 | 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. + +