commit a47597238e93afb5d382afa71934d461a8df68cc Author: ModelHub XC Date: Sat Jul 4 13:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ophtimus-Llama-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2cbd5ae --- /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 +Ophtimus-Llama-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ophtimus-Llama-1B.IQ4_XS.gguf b/Ophtimus-Llama-1B.IQ4_XS.gguf new file mode 100644 index 0000000..a527cee --- /dev/null +++ b/Ophtimus-Llama-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea356eae1e86877e14be993a85a3ade96a4546e0aae50588acee806cdf99dc77 +size 748384288 diff --git a/Ophtimus-Llama-1B.Q2_K.gguf b/Ophtimus-Llama-1B.Q2_K.gguf new file mode 100644 index 0000000..9c8faaa --- /dev/null +++ b/Ophtimus-Llama-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b8843ebc22ad93336c2d1b05c3d079bfbe7b8d9a6e5c2540be9d0af3d2a0621 +size 580874272 diff --git a/Ophtimus-Llama-1B.Q3_K_L.gguf b/Ophtimus-Llama-1B.Q3_K_L.gguf new file mode 100644 index 0000000..d199c6f --- /dev/null +++ b/Ophtimus-Llama-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1495fa4131fcf28f0657cd226a4e8aa1eee2f6b99e617a05d27fdb8884a85b1 +size 732524576 diff --git a/Ophtimus-Llama-1B.Q3_K_M.gguf b/Ophtimus-Llama-1B.Q3_K_M.gguf new file mode 100644 index 0000000..18decd7 --- /dev/null +++ b/Ophtimus-Llama-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a2dfbcd4174cba4b5ecff095a6dbcd2f0fca31e0798ef39a4edff8442ce562 +size 690843680 diff --git a/Ophtimus-Llama-1B.Q3_K_S.gguf b/Ophtimus-Llama-1B.Q3_K_S.gguf new file mode 100644 index 0000000..6c3ac8b --- /dev/null +++ b/Ophtimus-Llama-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0d9ca95a888c9b812b176ed5eacc88f01db37df6e006f170d428d0492d9c2b +size 641691680 diff --git a/Ophtimus-Llama-1B.Q4_K_M.gguf b/Ophtimus-Llama-1B.Q4_K_M.gguf new file mode 100644 index 0000000..a575344 --- /dev/null +++ b/Ophtimus-Llama-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42cf43ed1f062af5c87bf68d9ac196630b93e340d4e826ef8fe983cd937029ac +size 807694368 diff --git a/Ophtimus-Llama-1B.Q4_K_S.gguf b/Ophtimus-Llama-1B.Q4_K_S.gguf new file mode 100644 index 0000000..7c70e1f --- /dev/null +++ b/Ophtimus-Llama-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f52c87d93062e1cfae0a0bd4c8501f69652e9b08bff669f212761aacc3dc061f +size 775647264 diff --git a/Ophtimus-Llama-1B.Q5_K_M.gguf b/Ophtimus-Llama-1B.Q5_K_M.gguf new file mode 100644 index 0000000..a0243bd --- /dev/null +++ b/Ophtimus-Llama-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf1dbbdd5438e491112e2c5891ceaf1355415e8b0e23b0f594fa4814306cbfe +size 911503392 diff --git a/Ophtimus-Llama-1B.Q5_K_S.gguf b/Ophtimus-Llama-1B.Q5_K_S.gguf new file mode 100644 index 0000000..22baa5b --- /dev/null +++ b/Ophtimus-Llama-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f08591ac009722e46c684224b1dc895b34b67ca9a7db670a718edf67d378ae9c +size 892563488 diff --git a/Ophtimus-Llama-1B.Q6_K.gguf b/Ophtimus-Llama-1B.Q6_K.gguf new file mode 100644 index 0000000..18f2c3f --- /dev/null +++ b/Ophtimus-Llama-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0af8b10afa504f10295cfc11c11fbd0792973f1165e5bfc0cbfb4ba72bf1bad4 +size 1021800480 diff --git a/Ophtimus-Llama-1B.Q8_0.gguf b/Ophtimus-Llama-1B.Q8_0.gguf new file mode 100644 index 0000000..71913e8 --- /dev/null +++ b/Ophtimus-Llama-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d2eb8d10ea689f2f95190ecdfb0b87116a6d21e9901525446b6f228a25f1cc +size 1321082912 diff --git a/Ophtimus-Llama-1B.f16.gguf b/Ophtimus-Llama-1B.f16.gguf new file mode 100644 index 0000000..b2a7e2f --- /dev/null +++ b/Ophtimus-Llama-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62e8d37d0c249d9360d7671104a51f32343c09866c4638ef66720dfe1b79d0b1 +size 2479595552 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f8a407c --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: BaekSeungJu/Ophtimus-Llama-1B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BaekSeungJu/Ophtimus-Llama-1B + + +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/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-1B-GGUF/resolve/main/Ophtimus-Llama-1B.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. + +