From 19892201403f7410259552045176402e874acd88 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 19 Sep 2026 19:48:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: dphn/dolphincoder-starcoder2-15b Source: Original Platform --- .gitattributes | 35 +++++++++++++++ README.md | 77 ++++++++++++++++++++++++++++++++ added_tokens.json | 4 ++ config.json | 32 +++++++++++++ configuration.json | 1 + generation_config.json | 7 +++ merges.txt | 3 ++ pytorch_model-00001-of-00007.bin | 3 ++ pytorch_model-00002-of-00007.bin | 3 ++ pytorch_model-00003-of-00007.bin | 3 ++ pytorch_model-00004-of-00007.bin | 3 ++ pytorch_model-00005-of-00007.bin | 3 ++ pytorch_model-00006-of-00007.bin | 3 ++ pytorch_model-00007-of-00007.bin | 3 ++ pytorch_model.bin.index.json | 3 ++ special_tokens_map.json | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 3 ++ vocab.json | 3 ++ 19 files changed, 195 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 pytorch_model-00001-of-00007.bin create mode 100644 pytorch_model-00002-of-00007.bin create mode 100644 pytorch_model-00003-of-00007.bin create mode 100644 pytorch_model-00004-of-00007.bin create mode 100644 pytorch_model-00005-of-00007.bin create mode 100644 pytorch_model-00006-of-00007.bin create mode 100644 pytorch_model-00007-of-00007.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..705f759 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +datasets: +- cognitivecomputations/dolphin +- jondurbin/airoboros-2.2.1 +- cognitivecomputations/dolphin-coder +- teknium/openhermes +- ise-uiuc/Magicoder-OSS-Instruct-75K +- ise-uiuc/Magicoder-Evol-Instruct-110K +- m-a-p/Code-Feedback +- m-a-p/CodeFeedback-Filtered-Instruction +language: +- en +license: bigcode-openrail-m +--- + +DolphinCoder StarCoder2 15b 🐬 + +sponsored by [latitude.sh](https://www.latitude.sh/). + +[![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations) +Discord: https://discord.gg/cognitivecomputations + + + +This model is based on StarCoder2-15b and is subject to bigcode-openrail-m license. + +This Dolphin is *really good* at coding, I trained with a lot of coding data. + +This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models +You are responsible for any content you create using this model. Enjoy responsibly. + +## Training +It took 3 days to train 3 epochs on 8x H100s using qLoRA and Axolotl + +Prompt format: +This model uses ChatML prompt format. +``` +<|im_start|>system +You are DolphinCoder, a helpful AI programming assistant.<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant + +``` + +Example: +``` +<|im_start|>system +You are DolphinCoder, a master at software engineering and coding in any programming language. +<|im_start|>user +Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file. +<|im_start|>assistant +``` + +## Quantized models + +- [gguf](https://huggingface.co/dagbs/dolphincoder-starcoder2-15b-GGUF) + +- [ExLlamaV2](https://huggingface.co/bartowski/dolphincoder-starcoder2-15b-exl2) + +## Gratitude +- This model was made possible by the generous sponsorship of [latitude.sh](https://www.latitude.sh/). +- Huge thank you to [BigCode](https://www.bigcode-project.org/) for training and publishing the weights of StarCoder2 +- HUGE Thank you to the dataset authors: @ise-uiuc, @teknium, @m-a-p +- And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework! +- [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) +- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way. + +## Example Output + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/9Yhoy6PYoreqX8KocaDWb.png) + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/lz0fXODictCmW5pNultqq.png) + +[If you would like to financially support my efforts](https://ko-fi.com/erichartford) + +[swag](https://fa7113.myshopify.com/) \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e72b6dd --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "<|im_end|>": 49152, + "<|im_start|>": 49153 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..aaeb0f6 --- /dev/null +++ b/config.json @@ -0,0 +1,32 @@ +{ + "_name_or_path": "/home/ubuntu/models/starcoder2-15b", + "architectures": [ + "Starcoder2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "embedding_dropout": 0.0, + "eos_token_id": 0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 6144, + "initializer_range": 0.01275, + "intermediate_size": 24576, + "max_position_embeddings": 16384, + "mlp_type": "default", + "model_type": "starcoder2", + "norm_epsilon": 1e-05, + "norm_type": "layer_norm", + "num_attention_heads": 48, + "num_hidden_layers": 40, + "num_key_value_heads": 4, + "residual_dropout": 0.0, + "rms_norm_eps": 1e-05, + "rope_theta": 100000, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.39.0.dev0", + "use_bias": true, + "use_cache": false, + "vocab_size": 49154 +} 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/generation_config.json b/generation_config.json new file mode 100644 index 0000000..36a3f07 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "do_sample": true, + "eos_token_id": 50256, + "transformers_version": "4.39.0.dev0" +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..966b9fd --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac9dfb2c5bd3b10bd46aa7fdaa8c54e8e1bcfe1618d9288320ebc82c518442fc +size 441705 diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin new file mode 100644 index 0000000..1fa5835 --- /dev/null +++ b/pytorch_model-00001-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1414ca0cd503eeedf3870d3b123102ad65bd6d3b68e15f203b77e7890c48ff +size 4908152736 diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin new file mode 100644 index 0000000..053560b --- /dev/null +++ b/pytorch_model-00002-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4269051c492354399dfa12ff801be01d28ab6ffe007ded8f5d165694a8d9bfda +size 4996351634 diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin new file mode 100644 index 0000000..b23cfef --- /dev/null +++ b/pytorch_model-00003-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597d0af842e44651a3222663179ae4d00d78661132de4ebd1e936c09d5508398 +size 4983751762 diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin new file mode 100644 index 0000000..d7f7250 --- /dev/null +++ b/pytorch_model-00004-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5557359a9d16a4492a62476e6e87987f81479d6c018e36fc5a4327ebda111be +size 4996351698 diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin new file mode 100644 index 0000000..42a76d4 --- /dev/null +++ b/pytorch_model-00005-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78503484662eb7031a9490aa1a81b2b33cd80714da27edf77cf3635fdef1a135 +size 4983751762 diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin new file mode 100644 index 0000000..5c09d2b --- /dev/null +++ b/pytorch_model-00006-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6acc382c1e5aca6ef8594b608b2073d206b22a6837afa37dfec7df40918becc0 +size 4996351698 diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin new file mode 100644 index 0000000..c58019d --- /dev/null +++ b/pytorch_model-00007-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd2612589a81fa3be40e9bbfb086a018f590b4a8c86709a9c6692165b9594075 +size 2051333876 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..104f360 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4803cae9d300567c78a7d00bc5ab883767a8a930849c34a2ac3a9c7bd458bef +size 52083 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a05b556 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37ae42a388d1dd49123659589f68b983bd9d5a872a0917f4dc71c4ddb366383 +size 1443 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..d9d3789 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bddca77eedeaf0af3aaa1754027c3de4e7b01f0f679c02df2e4f9843600bb94d +size 2061295 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ce3ac5d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f52272ab17f8402567ffd92d6da18e3980ec92cc1f1ed52d43368cc4b6a882f +size 8919 diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..56972d7 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:542ee3f8b27b3a825754728b4dc59eff31065fecce843a93f09b98f13dbd7de9 +size 777202