commit 3cefc90a543d12ea6be165ef3b390086a3e23cb6 Author: ModelHub XC Date: Sat Jul 18 12:35:08 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: unsloth/Seed-Coder-8B-Reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..f660075 --- /dev/null +++ b/README.md @@ -0,0 +1,125 @@ +--- +tags: +- unsloth +library_name: transformers +pipeline_tag: text-generation +license: mit +base_model: +- ByteDance-Seed/Seed-Coder-8B-Reasoning +--- +
+

+ Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. +

+
+ + + + + + + + + +
+
+ + +# Seed-Coder-8B-Reasoning + +
+ + Homepage + + + + Technical Report + + + + Hugging Face + + + + License + +
+ + +## Introduction +We are thrilled to introduce Seed-Coder, a powerful, transparent, and parameter-efficient family of open-source code models at the 8B scale, featuring base, instruct, and reasoning variants. Seed-Coder contributes to promote the evolution of open code models through the following highlights. + +- **Model-centric:** Seed-Coder predominantly leverages LLMs instead of hand-crafted rules for code data filtering, minimizing manual effort in pretraining data construction. +- **Transparent:** We openly share detailed insights into our model-centric data pipeline, including methods for curating GitHub data, commits data, and code-related web data. +- **Powerful:** Seed-Coder achieves state-of-the-art performance among open-source models of comparable size across a diverse range of coding tasks. + +

+ +

+ +This repo contains the **Seed-Coder-8B-Reasoning** model, which has the following features: +- Type: Causal language models +- Training Stage: Pretraining & Post-training +- Data Source: Public datasets +- Context Length: 65,536 + + +## Model Downloads +| Model Name | Length | Download | Notes | +|---------------------------------------------------------|-----------|------------------------------------|-----------------------| +| Seed-Coder-8B-Base | 32K | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Base) | Pretrained on our model-centric code data. | +| Seed-Coder-8B-Instruct | 32K | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct) | Instruction-tuned for alignment with user intent. | +| 👉 **Seed-Coder-8B-Reasoning** | 64K | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Reasoning) | RL trained to boost reasoning capabilities. | +| Seed-Coder-8B-Reasoning-bf16 | 64K | 🤗 [Model](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Reasoning-bf16) | RL trained to boost reasoning capabilities. | + + +## Requirements +You will need to install the latest versions of `transformers` and `accelerate`: + +```bash +pip install -U transformers accelerate +``` + +## Quickstart + +Here is a simple example demonstrating how to load the model and perform code generation using the Hugging Face `pipeline` API: + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "ByteDance-Seed/Seed-Coder-8B-Reasoning" + +tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True) + +messages = [ + {"role": "user", "content": "Write a quick sort algorithm."}, +] + +input_ids = tokenizer.apply_chat_template( + messages, + tokenize=True, + return_tensors="pt", + add_generation_prompt=True, +).to(model.device) + +outputs = model.generate(input_ids, max_new_tokens=16384) +response = tokenizer.decode(outputs[0][input_ids.shape[-1]:], skip_special_tokens=True) +print(response) +``` + +## Evaluation +Seed-Coder-8B-Reasoning strikes impressive performance on competitive programming, demonstrating that smaller LLMs can also be competent on complex reasoning tasks. Our model surpasses QwQ-32B and DeepSeek-R1 on IOI'2024, and achieves an ELO rating comparable to o1-mini on Codeforces contests. + +
+ + +
+ + +For detailed benchmark performance, please refer to our [📑 Technical Report](https://github.com/ByteDance-Seed/Seed-Coder/blob/master/Seed-Coder.pdf). + +## License + +This project is licensed under the MIT License. See the [LICENSE file](https://github.com/ByteDance-Seed/Seed-Coder/blob/master/LICENSE) for details. diff --git a/Seed-Coder-8B-Reasoning-BF16.gguf b/Seed-Coder-8B-Reasoning-BF16.gguf new file mode 100644 index 0000000..72e2308 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:166cb2d8526a49ae259050a2b8d92dddc47de0236462f356285de4b1ba1dbbf8 +size 16507720736 diff --git a/Seed-Coder-8B-Reasoning-IQ4_NL.gguf b/Seed-Coder-8B-Reasoning-IQ4_NL.gguf new file mode 100644 index 0000000..a5532de --- /dev/null +++ b/Seed-Coder-8B-Reasoning-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c964226c320465bb6b1e0968ac430f18dced9fd02f3b0ad1a976409e6dfc7ed8 +size 4828665152 diff --git a/Seed-Coder-8B-Reasoning-IQ4_XS.gguf b/Seed-Coder-8B-Reasoning-IQ4_XS.gguf new file mode 100644 index 0000000..ed68219 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ca9649652a6ddb800fe6dd0746eeaf9916aecd0a6829782f46fbf72b72fbcc +size 4614755648 diff --git a/Seed-Coder-8B-Reasoning-Q2_K.gguf b/Seed-Coder-8B-Reasoning-Q2_K.gguf new file mode 100644 index 0000000..aabf04b --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55787f5ae0b0e2a1fd5e6988cc187fab28b9a1652e9f9eb6a4abd4e5f1d77b5a +size 3304002880 diff --git a/Seed-Coder-8B-Reasoning-Q2_K_L.gguf b/Seed-Coder-8B-Reasoning-Q2_K_L.gguf new file mode 100644 index 0000000..bdc2c4f --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50042d6ad88206359ff370c54b35bbea0d0b21622f71d69471c4c2f778da1495 +size 3452933440 diff --git a/Seed-Coder-8B-Reasoning-Q3_K_M.gguf b/Seed-Coder-8B-Reasoning-Q3_K_M.gguf new file mode 100644 index 0000000..a2becb0 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dd1e3c6ed53ea3e2fef84b768a96a04234f10b4eaab3e38fed5a74203c60e95 +size 4154971456 diff --git a/Seed-Coder-8B-Reasoning-Q3_K_S.gguf b/Seed-Coder-8B-Reasoning-Q3_K_S.gguf new file mode 100644 index 0000000..fe7c885 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55bd5b570eae93e2630a62b88a3152f82e7859cc1999335f204482f02ab57097 +size 3800552768 diff --git a/Seed-Coder-8B-Reasoning-Q4_1.gguf b/Seed-Coder-8B-Reasoning-Q4_1.gguf new file mode 100644 index 0000000..5754488 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2957233c63c238ec53b5bb393b83699363ac75cf26ba6eeb7619e27c2f461503 +size 5287810368 diff --git a/Seed-Coder-8B-Reasoning-Q4_K_M.gguf b/Seed-Coder-8B-Reasoning-Q4_K_M.gguf new file mode 100644 index 0000000..82167b5 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:160a295c3b0d3ae149f82ca1fc38fb9a73ccfc3392871dc788f0284e8e30e43e +size 5071410496 diff --git a/Seed-Coder-8B-Reasoning-Q4_K_S.gguf b/Seed-Coder-8B-Reasoning-Q4_K_S.gguf new file mode 100644 index 0000000..24f808f --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4410dddaf0211496b7fa08a17a7648163026f02ae29d921128e23afc65ec879c +size 4843345216 diff --git a/Seed-Coder-8B-Reasoning-Q5_K_M.gguf b/Seed-Coder-8B-Reasoning-Q5_K_M.gguf new file mode 100644 index 0000000..fbfb8f1 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520897b50fd6edaa6bb9b5fa5a523c67777173ff9462b79494f1a311a3d376fa +size 5897426240 diff --git a/Seed-Coder-8B-Reasoning-Q5_K_S.gguf b/Seed-Coder-8B-Reasoning-Q5_K_S.gguf new file mode 100644 index 0000000..45a7816 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08d758b8f42f225adac0ce45f66d7268838c8dbfb3a2870dcd2139df5bbe0b03 +size 5763732800 diff --git a/Seed-Coder-8B-Reasoning-Q6_K.gguf b/Seed-Coder-8B-Reasoning-Q6_K.gguf new file mode 100644 index 0000000..8741269 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc2e7a3fdad0d3bac2d0361e5ccc1cfc03f83f9d8b98bbd8c5363732d07bdb3 +size 6775067968 diff --git a/Seed-Coder-8B-Reasoning-Q8_0.gguf b/Seed-Coder-8B-Reasoning-Q8_0.gguf new file mode 100644 index 0000000..9792744 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee020895118665cc0da3f4c88af7bd8e08bc33cf026f7a59f923885f0eda21de +size 8773162304 diff --git a/Seed-Coder-8B-Reasoning-UD-IQ1_M.gguf b/Seed-Coder-8B-Reasoning-UD-IQ1_M.gguf new file mode 100644 index 0000000..3532797 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cf0a0c3fb5696cb8b282e4a4ab71c3b770128a5f9220479ea3d3342a76c7fe7 +size 2420053312 diff --git a/Seed-Coder-8B-Reasoning-UD-IQ1_S.gguf b/Seed-Coder-8B-Reasoning-UD-IQ1_S.gguf new file mode 100644 index 0000000..cde72b0 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60bb475c6d02417716a9607661bcfa7e5b04b2b141445c7fb0139950f35bfc7f +size 2293896512 diff --git a/Seed-Coder-8B-Reasoning-UD-IQ2_M.gguf b/Seed-Coder-8B-Reasoning-UD-IQ2_M.gguf new file mode 100644 index 0000000..022b674 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:574c7614d925587d18569893df248ffd4e12032bdaa50745331f5db187f6aa86 +size 3125155136 diff --git a/Seed-Coder-8B-Reasoning-UD-IQ2_XXS.gguf b/Seed-Coder-8B-Reasoning-UD-IQ2_XXS.gguf new file mode 100644 index 0000000..4b9e9ed --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfa6099c1745beca1bb46048e79be5f2d2d7c1341e3babdda10a7f7de2eebf11 +size 2630423872 diff --git a/Seed-Coder-8B-Reasoning-UD-IQ3_XXS.gguf b/Seed-Coder-8B-Reasoning-UD-IQ3_XXS.gguf new file mode 100644 index 0000000..c5e5b7b --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1a0e8ed6cb374b8bdc68467e37220c036b0f4c2fb95f28ed921dab9c4d9a59c +size 3443201344 diff --git a/Seed-Coder-8B-Reasoning-UD-Q2_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q2_K_XL.gguf new file mode 100644 index 0000000..a37e99d --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q2_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05ac8a4bd343da04f0c3945295ec05091f44d6e25dfe5a1717dc50023b510197 +size 3539440960 diff --git a/Seed-Coder-8B-Reasoning-UD-Q3_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q3_K_XL.gguf new file mode 100644 index 0000000..5978b30 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba962e1db1cbf20526f518eead762e0476250bffdaf663c4d789f7726b15dae4 +size 4342486336 diff --git a/Seed-Coder-8B-Reasoning-UD-Q4_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q4_K_XL.gguf new file mode 100644 index 0000000..a7a4b91 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd179306d1485269af8ecf038496afcd12f6bb886c61c24ce881a311f1aa30e +size 5144876352 diff --git a/Seed-Coder-8B-Reasoning-UD-Q5_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q5_K_XL.gguf new file mode 100644 index 0000000..568144c --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cda6ef9a5a46553cf65f68c74f588c77150846a4082a767437986d7532c38ba5 +size 5888349504 diff --git a/Seed-Coder-8B-Reasoning-UD-Q6_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q6_K_XL.gguf new file mode 100644 index 0000000..e62bb14 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3567f365fd5f8e1b0cc3e8a422f3615747f0a8f1fcffedbc7497c56b5aa31486 +size 7562319168 diff --git a/Seed-Coder-8B-Reasoning-UD-Q8_K_XL.gguf b/Seed-Coder-8B-Reasoning-UD-Q8_K_XL.gguf new file mode 100644 index 0000000..427cb79 --- /dev/null +++ b/Seed-Coder-8B-Reasoning-UD-Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3c0231fd53e1d3088da780efbea02439b964998970b2113a1acecf6c295c9b3 +size 11014493504 diff --git a/config.json b/config.json new file mode 100644 index 0000000..53e7e72 --- /dev/null +++ b/config.json @@ -0,0 +1,33 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0, + "bos_token_id": 0, + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.009882118, + "intermediate_size": 14336, + "layer_norm_eps": null, + "max_position_embeddings": 65536, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "pad_token_id": 1, + "pretraining_tp": 1, + "resid_pdrop": 0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.51.3", + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 155136 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/imatrix_unsloth.dat b/imatrix_unsloth.dat new file mode 100644 index 0000000..53b5487 Binary files /dev/null and b/imatrix_unsloth.dat differ