commit a797fb80f43a4a73c111cb91dd427c908ee5f964 Author: ModelHub XC Date: Thu Apr 23 18:03:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Draco-CoderMini-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52b2feb --- /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 +Draco-CoderMini-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Draco-CoderMini-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Draco-CoderMini-3B.IQ4_XS.gguf b/Draco-CoderMini-3B.IQ4_XS.gguf new file mode 100644 index 0000000..ba171ce --- /dev/null +++ b/Draco-CoderMini-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f96f0c2440ecfc85c2aa1c662c23642ef037cf9841c5eaa4900564d2fbcbcec +size 1753182976 diff --git a/Draco-CoderMini-3B.Q2_K.gguf b/Draco-CoderMini-3B.Q2_K.gguf new file mode 100644 index 0000000..d883e2b --- /dev/null +++ b/Draco-CoderMini-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e7d1e63bcb05229582f0624a82206573a5c80f02afd231fe61645e42d0bf60 +size 1274753792 diff --git a/Draco-CoderMini-3B.Q3_K_L.gguf b/Draco-CoderMini-3B.Q3_K_L.gguf new file mode 100644 index 0000000..4d6f997 --- /dev/null +++ b/Draco-CoderMini-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fdad34a8789dfdfe9794d72bc8dd1605017ccfece1da1d6e699ef0eb6df0f7b +size 1707389696 diff --git a/Draco-CoderMini-3B.Q3_K_M.gguf b/Draco-CoderMini-3B.Q3_K_M.gguf new file mode 100644 index 0000000..8db7827 --- /dev/null +++ b/Draco-CoderMini-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8c0faf526016f2140dbe8571f903421178a569c7ee100fa0028953c7460e84 +size 1590473472 diff --git a/Draco-CoderMini-3B.Q3_K_S.gguf b/Draco-CoderMini-3B.Q3_K_S.gguf new file mode 100644 index 0000000..cfc9e89 --- /dev/null +++ b/Draco-CoderMini-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b06626dce17507770340a5091bd7686873e5f4622dd7f7daf29883f2f47d277 +size 1454355200 diff --git a/Draco-CoderMini-3B.Q4_K_M.gguf b/Draco-CoderMini-3B.Q4_K_M.gguf new file mode 100644 index 0000000..a3752f9 --- /dev/null +++ b/Draco-CoderMini-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0f5a21a14e05ff28b106c4a9b57119a92599d169c2cfb3fa9b1e78ee6f2721 +size 1929900800 diff --git a/Draco-CoderMini-3B.Q4_K_S.gguf b/Draco-CoderMini-3B.Q4_K_S.gguf new file mode 100644 index 0000000..f12d2ca --- /dev/null +++ b/Draco-CoderMini-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81923dfa97cddcda0a274a54c415db427d7b649c7ae974c1178c42889105190f +size 1834382080 diff --git a/Draco-CoderMini-3B.Q5_K_M.gguf b/Draco-CoderMini-3B.Q5_K_M.gguf new file mode 100644 index 0000000..997f69f --- /dev/null +++ b/Draco-CoderMini-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40c806a64d953471c14f5fbb700bd2c4196f0badeed31c179a4ce7f4f83c9677 +size 2224812800 diff --git a/Draco-CoderMini-3B.Q5_K_S.gguf b/Draco-CoderMini-3B.Q5_K_S.gguf new file mode 100644 index 0000000..5fd16f3 --- /dev/null +++ b/Draco-CoderMini-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4732318d13392cd9a5df632c1009cd35a7f01feb6cb7b982db01ec1a34e815bb +size 2169664256 diff --git a/Draco-CoderMini-3B.Q6_K.gguf b/Draco-CoderMini-3B.Q6_K.gguf new file mode 100644 index 0000000..97a4333 --- /dev/null +++ b/Draco-CoderMini-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ea826de53ad001acde646594ca6fc61554a1ef01d180b39bc830a794f3a904 +size 2538156800 diff --git a/Draco-CoderMini-3B.Q8_0.gguf b/Draco-CoderMini-3B.Q8_0.gguf new file mode 100644 index 0000000..9fc54ed --- /dev/null +++ b/Draco-CoderMini-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:176b2f68068253d460c2e4f4e701971b64b12692f61a8c535881c339b453f9ab +size 3285474048 diff --git a/Draco-CoderMini-3B.f16.gguf b/Draco-CoderMini-3B.f16.gguf new file mode 100644 index 0000000..75f51e5 --- /dev/null +++ b/Draco-CoderMini-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ecd571fce93c6b9ad24a6fa1e24ad849312dde6edf2e3a6c6e412815e39cb55 +size 6178315008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..86ccea7 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: prithivMLmods/Draco-CoderMini-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- problem-solve +- text-generation-inference +- code +- math +--- +## About + + + + + + +static quants of https://huggingface.co/prithivMLmods/Draco-CoderMini-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Draco-CoderMini-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Draco-CoderMini-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/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Draco-CoderMini-3B-GGUF/resolve/main/Draco-CoderMini-3B.f16.gguf) | f16 | 6.3 | 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. + +