commit fd6aab9a2c3712b7c8c4861abebacf57940c6334 Author: ModelHub XC Date: Wed Jul 8 18:06:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-ninja-3.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1bdb496 --- /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-ninja-3.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-ninja-3.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5c22158 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: upvantage/llama-ninja-3.3 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/upvantage/llama-ninja-3.3 + + +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-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-ninja-3.3-GGUF/resolve/main/llama-ninja-3.3.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/llama-ninja-3.3.IQ4_XS.gguf b/llama-ninja-3.3.IQ4_XS.gguf new file mode 100644 index 0000000..bfdf13e --- /dev/null +++ b/llama-ninja-3.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a62c206ce11da1aebd55d46a788d11fc03ee88cf4823678afe85f8802997024c +size 4484368352 diff --git a/llama-ninja-3.3.Q2_K.gguf b/llama-ninja-3.3.Q2_K.gguf new file mode 100644 index 0000000..909ed83 --- /dev/null +++ b/llama-ninja-3.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedf112af11be41333eea298e020c2639d90f94bb1c6351ef9e6eca999274a25 +size 3179136992 diff --git a/llama-ninja-3.3.Q3_K_L.gguf b/llama-ninja-3.3.Q3_K_L.gguf new file mode 100644 index 0000000..d42f2d9 --- /dev/null +++ b/llama-ninja-3.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165126ad89b70161935d3fdabd75797e9c535c1ebdb3094f5c2bdb6dc1226dc7 +size 4321961952 diff --git a/llama-ninja-3.3.Q3_K_M.gguf b/llama-ninja-3.3.Q3_K_M.gguf new file mode 100644 index 0000000..b993f1c --- /dev/null +++ b/llama-ninja-3.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36bf5700173429f5b0aeaee418692ccecadf58c9b5db450c339b2a6b015ddcd4 +size 4018923488 diff --git a/llama-ninja-3.3.Q3_K_S.gguf b/llama-ninja-3.3.Q3_K_S.gguf new file mode 100644 index 0000000..4a7912c --- /dev/null +++ b/llama-ninja-3.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9f339286ef7772fddf6dcf65d94ca628b1d516e16cfc5240fe128454558c51 +size 3664504800 diff --git a/llama-ninja-3.3.Q4_K_M.gguf b/llama-ninja-3.3.Q4_K_M.gguf new file mode 100644 index 0000000..f6abf00 --- /dev/null +++ b/llama-ninja-3.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baee509dddc21919c32d74e0e806cffc0848076a5cb009bc21d16ef70cccaf7d +size 4920739808 diff --git a/llama-ninja-3.3.Q4_K_S.gguf b/llama-ninja-3.3.Q4_K_S.gguf new file mode 100644 index 0000000..6358721 --- /dev/null +++ b/llama-ninja-3.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80ac7ad8c9e26d46a5e58ac900be05e86df0ff478c6e0fd285d7dea552aa456e +size 4692674528 diff --git a/llama-ninja-3.3.Q5_K_M.gguf b/llama-ninja-3.3.Q5_K_M.gguf new file mode 100644 index 0000000..951034c --- /dev/null +++ b/llama-ninja-3.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7881c9e1f11ac7c05c52033e924758efb5e0c81cc9832c4393e5f420892b2a8 +size 5732992992 diff --git a/llama-ninja-3.3.Q5_K_S.gguf b/llama-ninja-3.3.Q5_K_S.gguf new file mode 100644 index 0000000..0be6bf3 --- /dev/null +++ b/llama-ninja-3.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00410fb0139276cf340540ab93c796a27da56786ec68d5658823edfab60dfe40 +size 5599299552 diff --git a/llama-ninja-3.3.Q6_K.gguf b/llama-ninja-3.3.Q6_K.gguf new file mode 100644 index 0000000..234f70c --- /dev/null +++ b/llama-ninja-3.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3a9d46d908eac45b0b90f7a46b8821dcda55448f75af8469bd7fabf4229676a +size 6596012000 diff --git a/llama-ninja-3.3.Q8_0.gguf b/llama-ninja-3.3.Q8_0.gguf new file mode 100644 index 0000000..9f5c657 --- /dev/null +++ b/llama-ninja-3.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969e7ad1a03d2de0cd1e9d741e5f391c01fcb05ded460700a0ef7b1c1b4c5ce4 +size 8540776416 diff --git a/llama-ninja-3.3.f16.gguf b/llama-ninja-3.3.f16.gguf new file mode 100644 index 0000000..f4ac536 --- /dev/null +++ b/llama-ninja-3.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71a9b929e248a047b4f38823f62a767fa65560992a653ca4991bc56f0f957d5b +size 16068896736