commit 8b0d37e29355405d20d42bba048b5879cc142388 Author: ModelHub XC Date: Sun Jun 14 20:27:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Hercules-Coder-E4B-it-V2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33c4c1e --- /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 +Hercules-Coder-E4B-it-V2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Hercules-Coder-E4B-it-V2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Hercules-Coder-E4B-it-V2.IQ4_XS.gguf b/Hercules-Coder-E4B-it-V2.IQ4_XS.gguf new file mode 100644 index 0000000..d743b58 --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1f97dee92a5845fa28ccb6c87076c3be53da7e85313a2649e475b576c17beab +size 3915995552 diff --git a/Hercules-Coder-E4B-it-V2.Q2_K.gguf b/Hercules-Coder-E4B-it-V2.Q2_K.gguf new file mode 100644 index 0000000..eb01c4c --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e341798d6b7f4b986c577089b1ac22c612847e764c19ebd8c478d0ac90c56af +size 2757319072 diff --git a/Hercules-Coder-E4B-it-V2.Q3_K_L.gguf b/Hercules-Coder-E4B-it-V2.Q3_K_L.gguf new file mode 100644 index 0000000..5616b4f --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76cf1efd11331faed20e257b67ccaf29b7a0c022ef8c43b4f564666c7e96f50 +size 3601996192 diff --git a/Hercules-Coder-E4B-it-V2.Q3_K_M.gguf b/Hercules-Coder-E4B-it-V2.Q3_K_M.gguf new file mode 100644 index 0000000..97a4335 --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8507f3515a046fbb66531e9cc7a889e0f7f2110f38a03de141128d2cc22ff5de +size 3440908704 diff --git a/Hercules-Coder-E4B-it-V2.Q3_K_S.gguf b/Hercules-Coder-E4B-it-V2.Q3_K_S.gguf new file mode 100644 index 0000000..5d9c76b --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d482a6e16c2bf96144ed472774ab05bfe1da0fb51345c7e5972bab8030ea4fe +size 3251911072 diff --git a/Hercules-Coder-E4B-it-V2.Q4_K_M.gguf b/Hercules-Coder-E4B-it-V2.Q4_K_M.gguf new file mode 100644 index 0000000..8276b25 --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dca040be3f59ac1c9b3164c290eedcd18332691f57011938e6999fc3210feb2 +size 4237064608 diff --git a/Hercules-Coder-E4B-it-V2.Q4_K_S.gguf b/Hercules-Coder-E4B-it-V2.Q4_K_S.gguf new file mode 100644 index 0000000..fc1c64f --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4afd862cfaf9aca719c7117a90e58d09292d4153dafd8d0d60944d6cecb9a97 +size 4102707616 diff --git a/Hercules-Coder-E4B-it-V2.Q5_K_M.gguf b/Hercules-Coder-E4B-it-V2.Q5_K_M.gguf new file mode 100644 index 0000000..b68f6ca --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec64919c5d1195a8678c5d318c4eb6c537677a9d59d114d8ce117a1d0684acad +size 4947999136 diff --git a/Hercules-Coder-E4B-it-V2.Q5_K_S.gguf b/Hercules-Coder-E4B-it-V2.Q5_K_S.gguf new file mode 100644 index 0000000..0ab302d --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:058139bbedea2fe45260699b52672c406586d4edb59197a36e9178758aad5dd6 +size 4869872032 diff --git a/Hercules-Coder-E4B-it-V2.Q6_K.gguf b/Hercules-Coder-E4B-it-V2.Q6_K.gguf new file mode 100644 index 0000000..63e61a3 --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a260c27389291fc934d252d28e5d4daa33867b97bd4a26b9f00f0b6fdd5b1b0 +size 5703367072 diff --git a/Hercules-Coder-E4B-it-V2.Q8_0.gguf b/Hercules-Coder-E4B-it-V2.Q8_0.gguf new file mode 100644 index 0000000..bb9135c --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3cf591bbbe3103a576e967ab65cda2f6c2a2f44e053f7017ddb7e825739452 +size 7353293216 diff --git a/Hercules-Coder-E4B-it-V2.f16.gguf b/Hercules-Coder-E4B-it-V2.f16.gguf new file mode 100644 index 0000000..540d4c5 --- /dev/null +++ b/Hercules-Coder-E4B-it-V2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:828a9875caa605e3966827400c10f13c3df2840c1f10ff22bc65eda200b865bb +size 13740104096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7b1ac27 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: EpistemeAI/Hercules-Coder-E4B-it-V2 +datasets: +- open-r1/codeforces-cots +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +no_imatrix: 'llama_model_quantize: failed to quantize: Missing importance matrix for + tensor blk.20.attn_k.weight in a very low-bit quantization' +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3n +--- +## About + + + + + + + + + +static quants of https://huggingface.co/EpistemeAI/Hercules-Coder-E4B-it-V2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Hercules-Coder-E4B-it-V2-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/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q2_K.gguf) | Q2_K | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q5_K_S.gguf) | Q5_K_S | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Hercules-Coder-E4B-it-V2-GGUF/resolve/main/Hercules-Coder-E4B-it-V2.f16.gguf) | f16 | 13.8 | 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. + +