commit 40f2bad2b681875861e7543863a8d2e353a2eb58 Author: ModelHub XC Date: Sat Oct 3 19:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..16027a2 --- /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 +md-veronica-1-llama-3.2-3b-instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +md-veronica-1-llama-3.2-3b-instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..c2f76fa --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: edgar9810/md-veronica-1-llama-3.2-3b-instruct +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/edgar9810/md-veronica-1-llama-3.2-3b-instruct + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-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/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/md-veronica-1-llama-3.2-3b-instruct-GGUF/resolve/main/md-veronica-1-llama-3.2-3b-instruct.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. + + diff --git a/md-veronica-1-llama-3.2-3b-instruct.IQ4_XS.gguf b/md-veronica-1-llama-3.2-3b-instruct.IQ4_XS.gguf new file mode 100644 index 0000000..09c54ed --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f466314b4f66781476cdba4ec5555530a6d2db0126daf5e188a936c9134c311f +size 1840907616 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q2_K.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q2_K.gguf new file mode 100644 index 0000000..47b4fbd --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64fe2387b6f02a2ebbf3c712ef4e3898cbd212744080af22c6355c771a82d31a +size 1363936608 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q3_K_L.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_L.gguf new file mode 100644 index 0000000..efc5464 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ab830310322b19f41a436b323e924e0ea5c4320b80ee0e632194ef849058e1 +size 1815348576 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q3_K_M.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_M.gguf new file mode 100644 index 0000000..fa181e3 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f43cdd13ef17ef8ac7ed31fd34c01308aa041730de5642446830b3db796068b +size 1687160160 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q3_K_S.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_S.gguf new file mode 100644 index 0000000..8433181 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a6e6a2710c321d657702b4bee274112142bcdca8bebb8fd85a8873ce937ffb +size 1542849888 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q4_K_M.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q4_K_M.gguf new file mode 100644 index 0000000..5a6a1f4 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60959dbc022a681752f572bcaedd49dd5f1ed9bb88b0af1f70541b9c411c52f6 +size 2019378528 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q4_K_S.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q4_K_S.gguf new file mode 100644 index 0000000..69022e4 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28474d36d6cb63666a20954b14ffddec0d3de12bd2250192ee11315c2090f825 +size 1928201568 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q5_K_M.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q5_K_M.gguf new file mode 100644 index 0000000..8221366 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:647f6fd067acd6a08ea1e360e4569fcae26fc8bc84448a109e32d80f9e9315af +size 2322154848 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q5_K_S.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q5_K_S.gguf new file mode 100644 index 0000000..b5d7d5d --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d45bc7e0ac2f03071c3e69daad66707f233769b3d9679ed417f331b4b97dad3 +size 2269513056 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q6_K.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q6_K.gguf new file mode 100644 index 0000000..f281868 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3b89501dd506fccd32e6f1191c70f97a293fad3e4ff1c00a7449cf1b955f34d +size 2643854688 diff --git a/md-veronica-1-llama-3.2-3b-instruct.Q8_0.gguf b/md-veronica-1-llama-3.2-3b-instruct.Q8_0.gguf new file mode 100644 index 0000000..b8f2898 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b91d490c1827dfded6f2fca1e42a1b6886656c4320e922dcca2ed8004265b3 +size 3421900128 diff --git a/md-veronica-1-llama-3.2-3b-instruct.f16.gguf b/md-veronica-1-llama-3.2-3b-instruct.f16.gguf new file mode 100644 index 0000000..8ed2137 --- /dev/null +++ b/md-veronica-1-llama-3.2-3b-instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96f9744cce80d440c43468f786a0d1745da01674f235b30567455d779592b871 +size 6433688928