commit 0595a289f483b0908f3aee696645f12a7fb035e2 Author: ModelHub XC Date: Wed Oct 14 05:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Xitcar-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5d225ba --- /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-3.2-3B-Xitcar.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Xitcar.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Xitcar.IQ4_XS.gguf b/Llama-3.2-3B-Xitcar.IQ4_XS.gguf new file mode 100644 index 0000000..b9d2e25 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de21e16fa3ad5d85d972f2732d62367a04cf0056f9f35ca094d56fe8cd3ea3b1 +size 1840908064 diff --git a/Llama-3.2-3B-Xitcar.Q2_K.gguf b/Llama-3.2-3B-Xitcar.Q2_K.gguf new file mode 100644 index 0000000..5c846af --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f4dd68531a1b7a6e435a338d71190b8f7b47aebac234ed12d78f2c93804d762 +size 1363937056 diff --git a/Llama-3.2-3B-Xitcar.Q3_K_L.gguf b/Llama-3.2-3B-Xitcar.Q3_K_L.gguf new file mode 100644 index 0000000..c8e0fd2 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77bbf772234d9932fbf004c28b69faf9379eecd4db066b7c51ce7d876a2b094 +size 1815349024 diff --git a/Llama-3.2-3B-Xitcar.Q3_K_M.gguf b/Llama-3.2-3B-Xitcar.Q3_K_M.gguf new file mode 100644 index 0000000..eb5ba30 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5dd04771286a719985d99ea882d60d5d324644275c6440835ad02678bbc151b +size 1687160608 diff --git a/Llama-3.2-3B-Xitcar.Q3_K_S.gguf b/Llama-3.2-3B-Xitcar.Q3_K_S.gguf new file mode 100644 index 0000000..b23bccd --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151123615b05f572f45987ec44c7bf8ca2133dee94506a79f3e5cd241f372728 +size 1542850336 diff --git a/Llama-3.2-3B-Xitcar.Q4_K_M.gguf b/Llama-3.2-3B-Xitcar.Q4_K_M.gguf new file mode 100644 index 0000000..a217b33 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92de5c8036837d8bbba21cd64ab03a69b4369e8d01c6189f47df5d5e5dd7c023 +size 2019378976 diff --git a/Llama-3.2-3B-Xitcar.Q4_K_S.gguf b/Llama-3.2-3B-Xitcar.Q4_K_S.gguf new file mode 100644 index 0000000..679d0c1 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:654b6be2fc9a0625ceefd8ef46107714a3289986a87533d2c29abc3755636f7f +size 1928202016 diff --git a/Llama-3.2-3B-Xitcar.Q5_K_M.gguf b/Llama-3.2-3B-Xitcar.Q5_K_M.gguf new file mode 100644 index 0000000..0be393b --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:648118e960ebc02234ba27e41341594567298d1b79d62f86b667f25d9107506a +size 2322155296 diff --git a/Llama-3.2-3B-Xitcar.Q5_K_S.gguf b/Llama-3.2-3B-Xitcar.Q5_K_S.gguf new file mode 100644 index 0000000..2df6e34 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e97f13e777b5c989acff46a19dc589aba4299b9f8f85c640f1149b2561bce7 +size 2269513504 diff --git a/Llama-3.2-3B-Xitcar.Q6_K.gguf b/Llama-3.2-3B-Xitcar.Q6_K.gguf new file mode 100644 index 0000000..30cd4a8 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c756ff3986a0e17dc9cc23f464e9fb7ef7bbcb99e50ba1e6c4275fdcb98b7e6 +size 2643855136 diff --git a/Llama-3.2-3B-Xitcar.Q8_0.gguf b/Llama-3.2-3B-Xitcar.Q8_0.gguf new file mode 100644 index 0000000..673fc51 --- /dev/null +++ b/Llama-3.2-3B-Xitcar.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003eb40272eb387a4c11f1ebd6e9b46af5b062359be65f8389b6027fa268afb9 +size 3421900576 diff --git a/Llama-3.2-3B-Xitcar.f16.gguf b/Llama-3.2-3B-Xitcar.f16.gguf new file mode 100644 index 0000000..13275ac --- /dev/null +++ b/Llama-3.2-3B-Xitcar.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:144935b05c50bddfff7b21871ebed25988aed90c357609ff64c7f6352d7618b6 +size 6433689376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..406e5dd --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: asiburye/Llama-3.2-3B-Xitcar +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/asiburye/Llama-3.2-3B-Xitcar + + +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-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Xitcar-GGUF/resolve/main/Llama-3.2-3B-Xitcar.f16.gguf) | f16 | 6.5 | 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. + +