commit 276371a8f9bda2478568ae06e5d122e32b49bc45 Author: ModelHub XC Date: Wed Jun 24 18:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-GitVac-Turbo-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f60e37 --- /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-GitVac-Turbo-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-GitVac-Turbo-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-GitVac-Turbo-3B.IQ4_XS.gguf b/Llama-GitVac-Turbo-3B.IQ4_XS.gguf new file mode 100644 index 0000000..9d466a6 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3959690f7df7f39b532979f75bb33f36472f398df41718ba721d3e722ea9b911 +size 2050221536 diff --git a/Llama-GitVac-Turbo-3B.Q2_K.gguf b/Llama-GitVac-Turbo-3B.Q2_K.gguf new file mode 100644 index 0000000..38ee819 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eea88d33d493d6b53e4edfc5097a9ab36e48a338f82bda6e17f6f7106567340d +size 1493218784 diff --git a/Llama-GitVac-Turbo-3B.Q3_K_L.gguf b/Llama-GitVac-Turbo-3B.Q3_K_L.gguf new file mode 100644 index 0000000..05cb2dd --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ffa8a94f0402fba22e6581746b4bbb8237abcfb3d241bc7a0cb18f1cfe7954 +size 1984646624 diff --git a/Llama-GitVac-Turbo-3B.Q3_K_M.gguf b/Llama-GitVac-Turbo-3B.Q3_K_M.gguf new file mode 100644 index 0000000..1ac2a65 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7051bb1698f3dbb7a1c6b95c70576f21335e9362a20357e29a95f69f1db313 +size 1856458208 diff --git a/Llama-GitVac-Turbo-3B.Q3_K_S.gguf b/Llama-GitVac-Turbo-3B.Q3_K_S.gguf new file mode 100644 index 0000000..37a1ec3 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de690af6e5c259eb5990954cfcf5be0d21639aab337fae650468fd6398ff64ba +size 1712147936 diff --git a/Llama-GitVac-Turbo-3B.Q4_K_M.gguf b/Llama-GitVac-Turbo-3B.Q4_K_M.gguf new file mode 100644 index 0000000..d3bec3b --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438c1e3d69713657035e2fb540e8504aace7d90b48f42059ac964f24f09526cd +size 2241005024 diff --git a/Llama-GitVac-Turbo-3B.Q4_K_S.gguf b/Llama-GitVac-Turbo-3B.Q4_K_S.gguf new file mode 100644 index 0000000..a034a17 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c71414af024fea342ce6873ec280f6a3034d47a538195582e4cd13ba76d53a7 +size 2149828064 diff --git a/Llama-GitVac-Turbo-3B.Q5_K_M.gguf b/Llama-GitVac-Turbo-3B.Q5_K_M.gguf new file mode 100644 index 0000000..9a15d16 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e107717c77e84163912583fc2c27fe4917b29e4bb2b3b9ade9981630a9e6d0 +size 2593031648 diff --git a/Llama-GitVac-Turbo-3B.Q5_K_S.gguf b/Llama-GitVac-Turbo-3B.Q5_K_S.gguf new file mode 100644 index 0000000..a91f0c1 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef6b75bfac10a9bd9c4f3f46bec9bd1497b9f5360cccc42e723d48f6042ed1d +size 2540389856 diff --git a/Llama-GitVac-Turbo-3B.Q6_K.gguf b/Llama-GitVac-Turbo-3B.Q6_K.gguf new file mode 100644 index 0000000..ac8eb49 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f85c5b5bf1aae54dd6ef21f135460375ed91a19d76b6ad3768045bd68681fd6a +size 2967059936 diff --git a/Llama-GitVac-Turbo-3B.Q8_0.gguf b/Llama-GitVac-Turbo-3B.Q8_0.gguf new file mode 100644 index 0000000..c0fd99d --- /dev/null +++ b/Llama-GitVac-Turbo-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2841bf4b3b01c6280901da4a5140976f710d3b558ee17e4ad4bf2ee3777f91ee +size 3840527840 diff --git a/Llama-GitVac-Turbo-3B.f16.gguf b/Llama-GitVac-Turbo-3B.f16.gguf new file mode 100644 index 0000000..a8b6135 --- /dev/null +++ b/Llama-GitVac-Turbo-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca076f04d0d3190280b3a8869651d9a54ca492e2c1d2c0479c5ad7e4a6695489 +size 7221693920 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0bd2fa1 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: vkerkez/Llama-GitVac-Turbo-3B +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- unsloth +--- +## About + + + + + + +static quants of https://huggingface.co/vkerkez/Llama-GitVac-Turbo-3B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-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-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-GitVac-Turbo-3B-GGUF/resolve/main/Llama-GitVac-Turbo-3B.f16.gguf) | f16 | 7.3 | 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. + +