commit d5438ce49e248a220009b2ba855da5a565a41b81 Author: ModelHub XC Date: Sat Apr 18 21:31:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..71548ae --- /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 +Cygnis-Alpha-2-8B-v0.3.f16.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cygnis-Alpha-2-8B-v0.3.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cygnis-Alpha-2-8B-v0.3.IQ4_XS.gguf b/Cygnis-Alpha-2-8B-v0.3.IQ4_XS.gguf new file mode 100644 index 0000000..ae0e22d --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fbd5d13689a58a2cfcde7b13ef3df78407020aa8340c785aa46311976e4b177 +size 4484454624 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q2_K.gguf b/Cygnis-Alpha-2-8B-v0.3.Q2_K.gguf new file mode 100644 index 0000000..41b7338 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c934c7d1e9d2d025bd24e92d9c37fad7c4af2ea39bb6eff833e31e49d3867f0 +size 3179209952 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q3_K_L.gguf b/Cygnis-Alpha-2-8B-v0.3.Q3_K_L.gguf new file mode 100644 index 0000000..4470471 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:973cc2d049a9be0add84143271aa03ec5e6726b87af0bfb1a26d06d99cfceb3b +size 4322041568 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q3_K_M.gguf b/Cygnis-Alpha-2-8B-v0.3.Q3_K_M.gguf new file mode 100644 index 0000000..921664d --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3d67533ebfb32ff907b90495193304ac4b1c51cb314be5e95a1bf20ee9a68a +size 4019003104 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q3_K_S.gguf b/Cygnis-Alpha-2-8B-v0.3.Q3_K_S.gguf new file mode 100644 index 0000000..8035034 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f35daf94271b1e30b83d145aa6a584aa2da84189026eab48c7bf1a7fe3ab2022 +size 3664584416 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q4_K_M.gguf b/Cygnis-Alpha-2-8B-v0.3.Q4_K_M.gguf new file mode 100644 index 0000000..7c6185b --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f347d576ece556a1275a51116128dd257c19b4a91f4aba9e0b3904fc9888c4 +size 4920828128 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q4_K_S.gguf b/Cygnis-Alpha-2-8B-v0.3.Q4_K_S.gguf new file mode 100644 index 0000000..611d5c3 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5856ec018d91bd273013a9be7946d9ac86be8350444f9c14defdb379ddc35dd +size 4692762848 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q5_K_M.gguf b/Cygnis-Alpha-2-8B-v0.3.Q5_K_M.gguf new file mode 100644 index 0000000..9a8dfb0 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37675fc03c14f47c987467c55310221703656b423252f6933da6bd6f5f142d05 +size 5733089504 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q5_K_S.gguf b/Cygnis-Alpha-2-8B-v0.3.Q5_K_S.gguf new file mode 100644 index 0000000..f58dd73 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:245f94a657bab44896922391057596e9e2a3e972916e47367cec45239064e388 +size 5599396064 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q6_K.gguf b/Cygnis-Alpha-2-8B-v0.3.Q6_K.gguf new file mode 100644 index 0000000..49f1cd0 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ea272e5b10f97663409ea935175d22fdaee3cfafd1083c0c0394ace123ad3ca +size 6596117216 diff --git a/Cygnis-Alpha-2-8B-v0.3.Q8_0.gguf b/Cygnis-Alpha-2-8B-v0.3.Q8_0.gguf new file mode 100644 index 0000000..e1b8941 --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1a9dfcf801ff90a94fc70d1f0145069ea3fba53392276d616b45b884276cee +size 8540913376 diff --git a/Cygnis-Alpha-2-8B-v0.3.f16.gguf b/Cygnis-Alpha-2-8B-v0.3.f16.gguf new file mode 100644 index 0000000..f388b4b --- /dev/null +++ b/Cygnis-Alpha-2-8B-v0.3.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:494649f0c644677cfac8fbde7865298d8b01763c22625a79bc4274a5ea29a10e +size 16069156576 diff --git a/README.md b/README.md new file mode 100644 index 0000000..911ed5f --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: Simonc-44/Cygnis-Alpha-2-8B-v0.3 +datasets: +- Simonc-44/Cygnis-Alpha2-Instruct-Mix +- Simonc-44/Cygnis-Identity-SFT +language: +- en +- fr +library_name: transformers +license: apache-2.0 +model_name: Cygnis-Alpha 2 (8B) v0.3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- transformers +- unsloth +- llama-3.1 +- sft +- reasoning +- cot +- 8b +- cygnis-alpha +- sovereign-ai +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Simonc-44/Cygnis-Alpha-2-8B-v0.3 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cygnis-Alpha-2-8B-v0.3-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-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/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cygnis-Alpha-2-8B-v0.3-GGUF/resolve/main/Cygnis-Alpha-2-8B-v0.3.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. + +