commit 386b0ea390d824a304c61ef8901addf1a7b8b603 Author: ModelHub XC Date: Sun Apr 12 17:35:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Light-mind_v1_LLAMA-700m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b6f7829 --- /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 +Light-mind_v1_LLAMA-700m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Light-mind_v1_LLAMA-700m.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Light-mind_v1_LLAMA-700m.IQ4_XS.gguf b/Light-mind_v1_LLAMA-700m.IQ4_XS.gguf new file mode 100644 index 0000000..533c383 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1110e9aa7ff87765fa99906ad9365284e80468813dffcdde432ea1e58eb402b +size 598154592 diff --git a/Light-mind_v1_LLAMA-700m.Q2_K.gguf b/Light-mind_v1_LLAMA-700m.Q2_K.gguf new file mode 100644 index 0000000..931c2f3 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:521dea39992fc2c64308acb523bd96e1b2cef34d0bbc10c86b2fec775be8ee71 +size 573261152 diff --git a/Light-mind_v1_LLAMA-700m.Q3_K_L.gguf b/Light-mind_v1_LLAMA-700m.Q3_K_L.gguf new file mode 100644 index 0000000..59cc9fe --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101a965cb3894165d9c8ed49e90139d52fe351e54d304ab9b4fec09e55cbd1f5 +size 629693792 diff --git a/Light-mind_v1_LLAMA-700m.Q3_K_M.gguf b/Light-mind_v1_LLAMA-700m.Q3_K_M.gguf new file mode 100644 index 0000000..159d69f --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e664a6eab1a090cb3506a6c2426c14e3cd73b9342947540034e542c1f06d13f9 +size 602096992 diff --git a/Light-mind_v1_LLAMA-700m.Q3_K_S.gguf b/Light-mind_v1_LLAMA-700m.Q3_K_S.gguf new file mode 100644 index 0000000..767bf6c --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22fd48fd77f10e8fa4be3c233b65aa2aa9cdb125d8d15baa487f35afe2e6596c +size 571909472 diff --git a/Light-mind_v1_LLAMA-700m.Q4_K_M.gguf b/Light-mind_v1_LLAMA-700m.Q4_K_M.gguf new file mode 100644 index 0000000..0af42fd --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ecbd1ff3b4a89cffc52c6ce2fc5e6314244d6411f7501878446e8f12c2ba8aa +size 676326752 diff --git a/Light-mind_v1_LLAMA-700m.Q4_K_S.gguf b/Light-mind_v1_LLAMA-700m.Q4_K_S.gguf new file mode 100644 index 0000000..b049ed9 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786269d61b274d310f5b29bbde143cca80cc7b424ed2fea19d5d63959b1e884f +size 654024032 diff --git a/Light-mind_v1_LLAMA-700m.Q5_K_M.gguf b/Light-mind_v1_LLAMA-700m.Q5_K_M.gguf new file mode 100644 index 0000000..8c4b0a6 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c5b3f578ae99240b500311cf1d2ec9ef86e9b8f9d7ccc0985ba9a56dad3e4e4 +size 717890912 diff --git a/Light-mind_v1_LLAMA-700m.Q5_K_S.gguf b/Light-mind_v1_LLAMA-700m.Q5_K_S.gguf new file mode 100644 index 0000000..34ae055 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29ea97d95bbcf9176fbd89e896f37810f709b9b0279675c8d24c6fe729ddc2fe +size 704712032 diff --git a/Light-mind_v1_LLAMA-700m.Q6_K.gguf b/Light-mind_v1_LLAMA-700m.Q6_K.gguf new file mode 100644 index 0000000..c4e1186 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9e335f884f439a8a3ec702ab7b72764ca05a2823743b62410c59e3e5ef2075f +size 861844832 diff --git a/Light-mind_v1_LLAMA-700m.Q8_0.gguf b/Light-mind_v1_LLAMA-700m.Q8_0.gguf new file mode 100644 index 0000000..80cb11a --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6e116379c8225cf7040214fcde9f55a7ec226a7a1a80a060b3dd6d9eb0aab0 +size 914222432 diff --git a/Light-mind_v1_LLAMA-700m.f16.gguf b/Light-mind_v1_LLAMA-700m.f16.gguf new file mode 100644 index 0000000..9d6c3a4 --- /dev/null +++ b/Light-mind_v1_LLAMA-700m.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87a907211445eaff0774f19b3b5f286670e223156e16475bcb84090e719ed7a9 +size 1713825632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..375e371 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: v-ShivaPrasad/Light-mind_v1_LLAMA-700m +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/v-ShivaPrasad/Light-mind_v1_LLAMA-700m + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Light-mind_v1_LLAMA-700m-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/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q5_K_S.gguf) | Q5_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q5_K_M.gguf) | Q5_K_M | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.Q8_0.gguf) | Q8_0 | 1.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Light-mind_v1_LLAMA-700m-GGUF/resolve/main/Light-mind_v1_LLAMA-700m.f16.gguf) | f16 | 1.8 | 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. + +