commit 8473bd4168450d9f29a4cb8f797e8116f57d3609 Author: ModelHub XC Date: Sun Jun 21 12:50:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.3-Octet-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..97b93b6 --- /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-3.3-Octet.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.3-Octet.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.3-Octet.IQ4_XS.gguf b/Llama-3.3-Octet.IQ4_XS.gguf new file mode 100644 index 0000000..4300180 --- /dev/null +++ b/Llama-3.3-Octet.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d3aacc8974ef0f9fd590c34c6abf271a231f0c6acb6551849ef6b4e967d6b5 +size 4484363840 diff --git a/Llama-3.3-Octet.Q2_K.gguf b/Llama-3.3-Octet.Q2_K.gguf new file mode 100644 index 0000000..95bf627 --- /dev/null +++ b/Llama-3.3-Octet.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807af7038ba61a71bc63a3398cf425e400e2de304f3d89d04ab9c255ed8df97b +size 3179132480 diff --git a/Llama-3.3-Octet.Q3_K_L.gguf b/Llama-3.3-Octet.Q3_K_L.gguf new file mode 100644 index 0000000..b3cffb0 --- /dev/null +++ b/Llama-3.3-Octet.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be6d860f31201209cc4a3ca63ede3fc0a9394a8a3a5b5f849b92e79abc5a2a8 +size 4321957440 diff --git a/Llama-3.3-Octet.Q3_K_M.gguf b/Llama-3.3-Octet.Q3_K_M.gguf new file mode 100644 index 0000000..d31d931 --- /dev/null +++ b/Llama-3.3-Octet.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961a0c78fc952a5a253e62c9eb81d1b8d01c646dd1f8e332c3e2408746188992 +size 4018918976 diff --git a/Llama-3.3-Octet.Q3_K_S.gguf b/Llama-3.3-Octet.Q3_K_S.gguf new file mode 100644 index 0000000..e34a34d --- /dev/null +++ b/Llama-3.3-Octet.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2b16081ddfc9c5c6b69583226c83fd4dd65c9664e8da84874a4c03fdb0bb21 +size 3664500288 diff --git a/Llama-3.3-Octet.Q4_K_M.gguf b/Llama-3.3-Octet.Q4_K_M.gguf new file mode 100644 index 0000000..9cf9619 --- /dev/null +++ b/Llama-3.3-Octet.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5712f672bfe3dbf36003a957d25169a3dee2dd907d0ce9c9094dd201471664c4 +size 4920735296 diff --git a/Llama-3.3-Octet.Q4_K_S.gguf b/Llama-3.3-Octet.Q4_K_S.gguf new file mode 100644 index 0000000..af86705 --- /dev/null +++ b/Llama-3.3-Octet.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b12f2f0b27395a2853924f860fa9d875c9818f685957833963d8adf283c9410 +size 4692670016 diff --git a/Llama-3.3-Octet.Q5_K_M.gguf b/Llama-3.3-Octet.Q5_K_M.gguf new file mode 100644 index 0000000..ab358c5 --- /dev/null +++ b/Llama-3.3-Octet.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6402ea5318c3757d93c7d597fca19bfe1eae2acd218bcab3c93cc241e52cca5b +size 5732988480 diff --git a/Llama-3.3-Octet.Q5_K_S.gguf b/Llama-3.3-Octet.Q5_K_S.gguf new file mode 100644 index 0000000..cd4880b --- /dev/null +++ b/Llama-3.3-Octet.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d8a282ea44219bfd87d57a195d0d9bf5cd2cc05e2c713f98a1e5fabad6ceb7d +size 5599295040 diff --git a/Llama-3.3-Octet.Q6_K.gguf b/Llama-3.3-Octet.Q6_K.gguf new file mode 100644 index 0000000..9cbbc6e --- /dev/null +++ b/Llama-3.3-Octet.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d145508c22844e7a11964460ee55f2d9b28e20896d896a705a9882d6860107d6 +size 6596007488 diff --git a/Llama-3.3-Octet.Q8_0.gguf b/Llama-3.3-Octet.Q8_0.gguf new file mode 100644 index 0000000..66eb776 --- /dev/null +++ b/Llama-3.3-Octet.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cb64443aaf980d85d9b5c0ff6546864d00c60ef77e2e2abbe80a53342c9e7c +size 8540771904 diff --git a/Llama-3.3-Octet.f16.gguf b/Llama-3.3-Octet.f16.gguf new file mode 100644 index 0000000..2e9e6bf --- /dev/null +++ b/Llama-3.3-Octet.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c10b4a5bd1ed68740b8adffe958edc8f6b50aa84d137930a0cc23870ef760b3 +size 16068892224 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34e263f --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: blascotobasco/Llama-3.3-Octet +language: +- en +library_name: transformers +model_name: Jackdaw-Llama-8B +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- unsloth +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/blascotobasco/Llama-3.3-Octet + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.3-Octet-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.3-Octet-i1-GGUF +## 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-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.3-Octet-GGUF/resolve/main/Llama-3.3-Octet.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. + +