commit 1b5006a2aed3c6bfbdf836ce0cfceb57cd0a8ca0 Author: ModelHub XC Date: Thu Jun 18 06:22:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c408974 --- /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 +llama1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7f073ec --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Yebin46/llama1B +datasets: +- taeshahn/ko-lima +language: +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Yebin46/llama1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama1B-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/llama1B-GGUF/resolve/main/llama1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama1B-GGUF/resolve/main/llama1B.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. + + diff --git a/llama1B.IQ4_XS.gguf b/llama1B.IQ4_XS.gguf new file mode 100644 index 0000000..47b3839 --- /dev/null +++ b/llama1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:980b89029b8b899b1304105e83f17f08b02f794a0ea6b21e7872ce2ee8f8e88d +size 748385664 diff --git a/llama1B.Q2_K.gguf b/llama1B.Q2_K.gguf new file mode 100644 index 0000000..e9ffbfc --- /dev/null +++ b/llama1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:977dda70b71fa1322fca0d86ac28b535050d539496cf4f8c65acf98864be3fa2 +size 580875648 diff --git a/llama1B.Q3_K_L.gguf b/llama1B.Q3_K_L.gguf new file mode 100644 index 0000000..0ecba30 --- /dev/null +++ b/llama1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c70ae2db25a6c16da5b7088654c767482e22b76ab5da85bbdd8d1e603bb58ed +size 732525952 diff --git a/llama1B.Q3_K_M.gguf b/llama1B.Q3_K_M.gguf new file mode 100644 index 0000000..c7e8569 --- /dev/null +++ b/llama1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4569005dec6e3e576f4012e86dcc34081384c3dbcca9b49c7fba578e5f75c401 +size 690845056 diff --git a/llama1B.Q3_K_S.gguf b/llama1B.Q3_K_S.gguf new file mode 100644 index 0000000..6ffb8cd --- /dev/null +++ b/llama1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc5cb9f23f99bfc07bb92a5112cf0141d337fb104a966493961fffd14ffd7fb +size 641693056 diff --git a/llama1B.Q4_K_M.gguf b/llama1B.Q4_K_M.gguf new file mode 100644 index 0000000..90fda7f --- /dev/null +++ b/llama1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:736c8cbb8da18d46651b969ce57542fa226abeda60e6a79866ceac27d0fb83e0 +size 807695744 diff --git a/llama1B.Q4_K_S.gguf b/llama1B.Q4_K_S.gguf new file mode 100644 index 0000000..3cda1d5 --- /dev/null +++ b/llama1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ec4576cf44b919dc96cdcfd2b22c5a710513cf9c9c85c72e825d226cd66d6d +size 775648640 diff --git a/llama1B.Q5_K_M.gguf b/llama1B.Q5_K_M.gguf new file mode 100644 index 0000000..0160c27 --- /dev/null +++ b/llama1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d9d2dd982d869f58e4c58a0e72e542ba88264693e4efe9c802bb5c4e956ae75 +size 911504768 diff --git a/llama1B.Q5_K_S.gguf b/llama1B.Q5_K_S.gguf new file mode 100644 index 0000000..7d173f8 --- /dev/null +++ b/llama1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a04e1011c7421c9e7557c760111acb9ebf10bb34300d4a7ecb180b9194bcfa88 +size 892564864 diff --git a/llama1B.Q6_K.gguf b/llama1B.Q6_K.gguf new file mode 100644 index 0000000..00d06c5 --- /dev/null +++ b/llama1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a45691217352e8c57e04538342a6e827477306c32ec8a82484e026958cfe4ab2 +size 1021801856 diff --git a/llama1B.Q8_0.gguf b/llama1B.Q8_0.gguf new file mode 100644 index 0000000..c8705f9 --- /dev/null +++ b/llama1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1f1e7e4db6af14625b698d7f3ec46a38799f009178c6138ad8ed2d47a8e426 +size 1321084288 diff --git a/llama1B.f16.gguf b/llama1B.f16.gguf new file mode 100644 index 0000000..5d64f48 --- /dev/null +++ b/llama1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:581d55b971b3325f23c09943018face1267838fa7d6db1503d51f8c34ef5c3d0 +size 2479596928