commit b1c7c3cda15262b16d185fcac699ea0d16589eef Author: ModelHub XC Date: Wed Jun 3 13:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-O-3.1-8B-levent-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..99ee526 --- /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 +Llama-O-3.1-8B-levent.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-O-3.1-8B-levent.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-O-3.1-8B-levent.IQ4_XS.gguf b/Llama-O-3.1-8B-levent.IQ4_XS.gguf new file mode 100644 index 0000000..28ffd83 --- /dev/null +++ b/Llama-O-3.1-8B-levent.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f0908443a6caa63c23fdb87d050a14d519b12e4cebcd7ae8b37d038c8d6712 +size 4484374624 diff --git a/Llama-O-3.1-8B-levent.Q2_K.gguf b/Llama-O-3.1-8B-levent.Q2_K.gguf new file mode 100644 index 0000000..2928cc7 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37eeb94b21b68d01ff0c72680fb037ded3b70ded91e5424de5252f9d44b42240 +size 3179141600 diff --git a/Llama-O-3.1-8B-levent.Q3_K_L.gguf b/Llama-O-3.1-8B-levent.Q3_K_L.gguf new file mode 100644 index 0000000..a6b9e4a --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ed5aaa9baca1c9cfea2d4edf314dea0cc0b3eedc820fb470d5cab0a5035d38 +size 4321967392 diff --git a/Llama-O-3.1-8B-levent.Q3_K_M.gguf b/Llama-O-3.1-8B-levent.Q3_K_M.gguf new file mode 100644 index 0000000..4ac147b --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e774fbcdcec70416abc5831cb1728e3123079e7244b155fccf903e41279eafd6 +size 4018928928 diff --git a/Llama-O-3.1-8B-levent.Q3_K_S.gguf b/Llama-O-3.1-8B-levent.Q3_K_S.gguf new file mode 100644 index 0000000..2785379 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a78587a6ea78d4f6c2019fa777ef0bcfc2601926512a68dc27e1fd405647ada +size 3664510240 diff --git a/Llama-O-3.1-8B-levent.Q4_K_M.gguf b/Llama-O-3.1-8B-levent.Q4_K_M.gguf new file mode 100644 index 0000000..5ca3459 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f0c1bde71e5a1efd29181a91786ea693a320218701563310fb7de3711d09c30 +size 4920746336 diff --git a/Llama-O-3.1-8B-levent.Q4_K_S.gguf b/Llama-O-3.1-8B-levent.Q4_K_S.gguf new file mode 100644 index 0000000..cd35767 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e3e4a2c02888ef870d7860c6025e7ecd913732ad8e553ee9e296466c12073d +size 4692681056 diff --git a/Llama-O-3.1-8B-levent.Q5_K_M.gguf b/Llama-O-3.1-8B-levent.Q5_K_M.gguf new file mode 100644 index 0000000..233b3ae --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72b9d74537cf8a6f1af1716deee471f5262eaa5d7647420710534faefd8851c +size 5733000544 diff --git a/Llama-O-3.1-8B-levent.Q5_K_S.gguf b/Llama-O-3.1-8B-levent.Q5_K_S.gguf new file mode 100644 index 0000000..6a64de8 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40e78e8c3aa8efc3add9509a7f4c57b6b47ca49da692cb8fcf17cfe9d6c06aba +size 5599307104 diff --git a/Llama-O-3.1-8B-levent.Q6_K.gguf b/Llama-O-3.1-8B-levent.Q6_K.gguf new file mode 100644 index 0000000..1a9e425 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc2bf8283e169141ef9cd06a2a212e732e5f29c4503a6e4a0293f032b0f5876a +size 6596020640 diff --git a/Llama-O-3.1-8B-levent.Q8_0.gguf b/Llama-O-3.1-8B-levent.Q8_0.gguf new file mode 100644 index 0000000..d314fc1 --- /dev/null +++ b/Llama-O-3.1-8B-levent.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4d0c79fd6cc582f28a0bec8d225e4bb2b25e4ea25757beb47b052919fc804be +size 8540789024 diff --git a/Llama-O-3.1-8B-levent.f16.gguf b/Llama-O-3.1-8B-levent.f16.gguf new file mode 100644 index 0000000..b3bdee4 --- /dev/null +++ b/Llama-O-3.1-8B-levent.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b775315d68cb75e066f1e6a9c59e89727dbcc193cd28fae7647fc494c95743 +size 16068924704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c78920 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: lserinol/Llama-O-3.1-8B-levent +language: +- en +- tr +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/lserinol/Llama-O-3.1-8B-levent + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-O-3.1-8B-levent-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/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-O-3.1-8B-levent-GGUF/resolve/main/Llama-O-3.1-8B-levent.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. + +