commit 941c1d0ff90cd710077094139b0106b8712e01c6 Author: ModelHub XC Date: Tue Jun 2 14:20:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ewen3-4b-Instruct-2507-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..12d3cc5 --- /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 +Ewen3-4b-Instruct-2507.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ewen3-4b-Instruct-2507.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ewen3-4b-Instruct-2507.IQ4_XS.gguf b/Ewen3-4b-Instruct-2507.IQ4_XS.gguf new file mode 100644 index 0000000..fde5ca8 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f25ce2941615bcb26c5e441070b7ded462dccf13d6cfde0c1b9bfb8a6213c72d +size 2286315648 diff --git a/Ewen3-4b-Instruct-2507.Q2_K.gguf b/Ewen3-4b-Instruct-2507.Q2_K.gguf new file mode 100644 index 0000000..fa51755 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b9fce3c7f00cc4c8c514bf0cb67ea3cdae732764375744738514f98954dfae +size 1669499008 diff --git a/Ewen3-4b-Instruct-2507.Q3_K_L.gguf b/Ewen3-4b-Instruct-2507.Q3_K_L.gguf new file mode 100644 index 0000000..0a2532a --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:947a8a454afd3e5fe15e87dbf48802e6173c7a5dea6a47bf6bb0d5a8a7834d3c +size 2239785088 diff --git a/Ewen3-4b-Instruct-2507.Q3_K_M.gguf b/Ewen3-4b-Instruct-2507.Q3_K_M.gguf new file mode 100644 index 0000000..3b42535 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eef9561a77171da18607e28ee46a7d034fc528fa9b37327aa7bd312ea186617e +size 2075617408 diff --git a/Ewen3-4b-Instruct-2507.Q3_K_S.gguf b/Ewen3-4b-Instruct-2507.Q3_K_S.gguf new file mode 100644 index 0000000..15c94e1 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c817410b917883bb03fee6ce09ec11d76b57a996befd5edcc5d398b2885d9da +size 1886996608 diff --git a/Ewen3-4b-Instruct-2507.Q4_K_M.gguf b/Ewen3-4b-Instruct-2507.Q4_K_M.gguf new file mode 100644 index 0000000..861ebfd --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0066161231cbe8b13b27db2eac8a2d3f75e9948acfa89e2aed29c585f863109e +size 2497280128 diff --git a/Ewen3-4b-Instruct-2507.Q4_K_S.gguf b/Ewen3-4b-Instruct-2507.Q4_K_S.gguf new file mode 100644 index 0000000..9ab1655 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c9e666725ea9431a4439b3af8e71bf463ae442f069f15002075d4a836a67c29 +size 2383308928 diff --git a/Ewen3-4b-Instruct-2507.Q5_K_M.gguf b/Ewen3-4b-Instruct-2507.Q5_K_M.gguf new file mode 100644 index 0000000..7262679 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15fa6c944db71d04318dd109f0527d30fdd077d9a92d18fbe3095395ae971f21 +size 2889513088 diff --git a/Ewen3-4b-Instruct-2507.Q5_K_S.gguf b/Ewen3-4b-Instruct-2507.Q5_K_S.gguf new file mode 100644 index 0000000..d17e73c --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6ec99c21faa47a47e762842c84e2841bd67a4441c7ba8b6427e09eef7a3aa8 +size 2823710848 diff --git a/Ewen3-4b-Instruct-2507.Q6_K.gguf b/Ewen3-4b-Instruct-2507.Q6_K.gguf new file mode 100644 index 0000000..68bde00 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50cda7fc60aa52ce0ab15704f6f48a7db3415ddf9eaf4fb57090362495d3ab51 +size 3306260608 diff --git a/Ewen3-4b-Instruct-2507.Q8_0.gguf b/Ewen3-4b-Instruct-2507.Q8_0.gguf new file mode 100644 index 0000000..f8486e8 --- /dev/null +++ b/Ewen3-4b-Instruct-2507.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa4ed4eb35283d42b22200c3956d49042fd3404ad11a914c459c803e81bea0fc +size 4280404608 diff --git a/Ewen3-4b-Instruct-2507.f16.gguf b/Ewen3-4b-Instruct-2507.f16.gguf new file mode 100644 index 0000000..7bf371f --- /dev/null +++ b/Ewen3-4b-Instruct-2507.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6810121fe9ba03c871a9f97e2047c9bd292d16dd02ceb8f5985990523b61cb58 +size 8051284608 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8ee1f84 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Orion-zhen/Ewen3-4b-Instruct-2507 +datasets: +- Orion-zhen/harmful-data +language: +- zh +- en +library_name: transformers +license: agpl-3.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- heretic +- abliteration +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Orion-zhen/Ewen3-4b-Instruct-2507 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Ewen3-4b-Instruct-2507-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-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/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ewen3-4b-Instruct-2507-GGUF/resolve/main/Ewen3-4b-Instruct-2507.f16.gguf) | f16 | 8.2 | 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. + +