commit 4db3a212e4a6fea4fd8e5a0c90fe3530c73da15d Author: ModelHub XC Date: Mon Apr 20 09:55:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MobileLLaMA-2.7B-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e6f5d11 --- /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 +MobileLLaMA-2.7B-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MobileLLaMA-2.7B-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MobileLLaMA-2.7B-Base.IQ4_XS.gguf b/MobileLLaMA-2.7B-Base.IQ4_XS.gguf new file mode 100644 index 0000000..7df92c1 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b4044611d5a89481e9b11337e33df079a2315afa36e0a59d841355f778be70 +size 1471262688 diff --git a/MobileLLaMA-2.7B-Base.Q2_K.gguf b/MobileLLaMA-2.7B-Base.Q2_K.gguf new file mode 100644 index 0000000..6a69a0f --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:983da12e16cac323de16fce50d1f9b54d3aea494bd76e2fade89e5d8f86ff337 +size 1028229088 diff --git a/MobileLLaMA-2.7B-Base.Q3_K_L.gguf b/MobileLLaMA-2.7B-Base.Q3_K_L.gguf new file mode 100644 index 0000000..a22eb33 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c254660238e23167b8040cd362d6c3ad1cf300f401a0ca8679433413187feb39 +size 1448279008 diff --git a/MobileLLaMA-2.7B-Base.Q3_K_M.gguf b/MobileLLaMA-2.7B-Base.Q3_K_M.gguf new file mode 100644 index 0000000..7c4a0c9 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11cade14ca5baa46783f7b86b546ddd6f3c8e94cffadccf6e5616c035c64dd6 +size 1331133408 diff --git a/MobileLLaMA-2.7B-Base.Q3_K_S.gguf b/MobileLLaMA-2.7B-Base.Q3_K_S.gguf new file mode 100644 index 0000000..7890410 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:942ded2af7b611af2a3610279ee808b4be231e20b6a16b46c79297243a590966 +size 1194163168 diff --git a/MobileLLaMA-2.7B-Base.Q4_K_M.gguf b/MobileLLaMA-2.7B-Base.Q4_K_M.gguf new file mode 100644 index 0000000..6b7e803 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb91a8712aa2ceff840394238f82538379975e480ff88f9b16a09dd10386587 +size 1642086368 diff --git a/MobileLLaMA-2.7B-Base.Q4_K_S.gguf b/MobileLLaMA-2.7B-Base.Q4_K_S.gguf new file mode 100644 index 0000000..77fbd4e --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34998faf6e87900c7c934c71504478b0aafe8b7fa9e8ff67d322149fbc535d2 +size 1554186208 diff --git a/MobileLLaMA-2.7B-Base.Q5_K_M.gguf b/MobileLLaMA-2.7B-Base.Q5_K_M.gguf new file mode 100644 index 0000000..daaa5ae --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc82995cf1e63d8e1de68bf826b282a11a5622ba6d0f20cae248f776f303bebe +size 1921023968 diff --git a/MobileLLaMA-2.7B-Base.Q5_K_S.gguf b/MobileLLaMA-2.7B-Base.Q5_K_S.gguf new file mode 100644 index 0000000..4b378e9 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54fd75de447875aea57a2bc27c733a7522d085ce202670a100f43818447399a4 +size 1869496288 diff --git a/MobileLLaMA-2.7B-Base.Q6_K.gguf b/MobileLLaMA-2.7B-Base.Q6_K.gguf new file mode 100644 index 0000000..177d705 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8294e665b4d336c0dde9e66bfd6978a6fc0ab485eef7e3bceb858624423adc61 +size 2217395168 diff --git a/MobileLLaMA-2.7B-Base.Q8_0.gguf b/MobileLLaMA-2.7B-Base.Q8_0.gguf new file mode 100644 index 0000000..31e1d5c --- /dev/null +++ b/MobileLLaMA-2.7B-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d564f497560d0624b558e4671352bb4f45c4b72e302901e9e23cfc63dc8d9c +size 2871639008 diff --git a/MobileLLaMA-2.7B-Base.f16.gguf b/MobileLLaMA-2.7B-Base.f16.gguf new file mode 100644 index 0000000..33c5d46 --- /dev/null +++ b/MobileLLaMA-2.7B-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:672498b3897a255454ca6aa1eaa0a00175fb4fdc76233eac277c4374c3879cd9 +size 5404195808 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd6b9fe --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: loada/MobileLLaMA-2.7B-Base +datasets: +- togethercomputer/RedPajama-Data-1T +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/loada/MobileLLaMA-2.7B-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MobileLLaMA-2.7B-Base-GGUF).*** + +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/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q2_K.gguf) | Q2_K | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q3_K_M.gguf) | Q3_K_M | 1.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q3_K_L.gguf) | Q3_K_L | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.Q8_0.gguf) | Q8_0 | 3.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MobileLLaMA-2.7B-Base-GGUF/resolve/main/MobileLLaMA-2.7B-Base.f16.gguf) | f16 | 5.5 | 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. + +