commit 59f7d3e0a336b82d01db4db2da36f6129ae2fe1b Author: ModelHub XC Date: Mon Jun 15 01:50:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ophtimus-Llama-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..583cefc --- /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-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ophtimus-Llama-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ophtimus-Llama-8B.IQ4_XS.gguf b/Ophtimus-Llama-8B.IQ4_XS.gguf new file mode 100644 index 0000000..bbeadd4 --- /dev/null +++ b/Ophtimus-Llama-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7db75a1c1db90748f3bc6f20889ced3556e8cfd6fab15d7bdc455d74ce3fb4b7 +size 4484367776 diff --git a/Ophtimus-Llama-8B.Q2_K.gguf b/Ophtimus-Llama-8B.Q2_K.gguf new file mode 100644 index 0000000..22d370b --- /dev/null +++ b/Ophtimus-Llama-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57ba9fde1162ebaa217294257d924c6c856a19d0c546564347178151a911535 +size 3179136416 diff --git a/Ophtimus-Llama-8B.Q3_K_L.gguf b/Ophtimus-Llama-8B.Q3_K_L.gguf new file mode 100644 index 0000000..2b36bd7 --- /dev/null +++ b/Ophtimus-Llama-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f272baf5a35777d6ae5541cab42355b9e83362dcd7dbe7852950e3dca431e0 +size 4321961376 diff --git a/Ophtimus-Llama-8B.Q3_K_M.gguf b/Ophtimus-Llama-8B.Q3_K_M.gguf new file mode 100644 index 0000000..bf2a0fb --- /dev/null +++ b/Ophtimus-Llama-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ae834c1c08875841c8742e1ed14105558b5103797c04be5d9641e1a60bf81e +size 4018922912 diff --git a/Ophtimus-Llama-8B.Q3_K_S.gguf b/Ophtimus-Llama-8B.Q3_K_S.gguf new file mode 100644 index 0000000..686e7d8 --- /dev/null +++ b/Ophtimus-Llama-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a0060094455500a46dbc59ef257734f07596b5179bd307e2ab290ef000b326d +size 3664504224 diff --git a/Ophtimus-Llama-8B.Q4_K_M.gguf b/Ophtimus-Llama-8B.Q4_K_M.gguf new file mode 100644 index 0000000..5a72c3f --- /dev/null +++ b/Ophtimus-Llama-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e86de971b2729486a34a3bf941974dd9945a0d55a9c09613cbde895f117ec722 +size 4920739232 diff --git a/Ophtimus-Llama-8B.Q4_K_S.gguf b/Ophtimus-Llama-8B.Q4_K_S.gguf new file mode 100644 index 0000000..bf99fdc --- /dev/null +++ b/Ophtimus-Llama-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db2b27ee994fb4ca91325b7f903e274b64a23702e44ac7689c4e33f429ad17a7 +size 4692673952 diff --git a/Ophtimus-Llama-8B.Q5_K_M.gguf b/Ophtimus-Llama-8B.Q5_K_M.gguf new file mode 100644 index 0000000..e167172 --- /dev/null +++ b/Ophtimus-Llama-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c60415fcd2fd98f40e4188d2f8c08a290b19b6bd85f7e3e7b9aaa52f88d9367 +size 5732992416 diff --git a/Ophtimus-Llama-8B.Q5_K_S.gguf b/Ophtimus-Llama-8B.Q5_K_S.gguf new file mode 100644 index 0000000..8a627c9 --- /dev/null +++ b/Ophtimus-Llama-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f78e4489c7f27cf449c4ba7a5fe444958d3143cad3ccdc6d5b2b873420cc3a75 +size 5599298976 diff --git a/Ophtimus-Llama-8B.Q6_K.gguf b/Ophtimus-Llama-8B.Q6_K.gguf new file mode 100644 index 0000000..c4bebd0 --- /dev/null +++ b/Ophtimus-Llama-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62fa2644d6c1f9edca0bde6d50e0a9d43a5dfa4be69d1d0e8ffbce10b93a018d +size 6596011424 diff --git a/Ophtimus-Llama-8B.Q8_0.gguf b/Ophtimus-Llama-8B.Q8_0.gguf new file mode 100644 index 0000000..52bed0a --- /dev/null +++ b/Ophtimus-Llama-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70601eb705976fd04fe2f568728856e75f427a6db6df0a02cfdaf428f97afff7 +size 8540775840 diff --git a/Ophtimus-Llama-8B.f16.gguf b/Ophtimus-Llama-8B.f16.gguf new file mode 100644 index 0000000..46c9d95 --- /dev/null +++ b/Ophtimus-Llama-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4372d7e6b62acf9c82f977db06ad375480b600b4f071baf1c56a625bc963e3c +size 16068896160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86abdaa --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: BaekSeungJu/Ophtimus-Llama-8B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/BaekSeungJu/Ophtimus-Llama-8B + + +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-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ophtimus-Llama-8B-GGUF/resolve/main/Ophtimus-Llama-8B.f16.gguf) | f16 | 16.2 | 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. + +