From 173ea1cc76087c2578f04edcd4dcb4103c8f06d0 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 12 Jun 2026 05:18:12 +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: princeton-nlp/SWE-Llama-7b Source: Original Platform --- .gitattributes | 47 ++++++++++++++++++++++++++++++ README.md | 49 ++++++++++++++++++++++++++++++++ config.json | 26 +++++++++++++++++ configuration.json | 1 + generation_config.json | 7 +++++ pytorch_model-00001-of-00002.bin | 3 ++ pytorch_model-00002-of-00002.bin | 3 ++ pytorch_model.bin.index.json | 3 ++ special_tokens_map.json | 23 +++++++++++++++ tokenizer.model | 3 ++ tokenizer_config.json | 37 ++++++++++++++++++++++++ 11 files changed, 202 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00002.bin create mode 100644 pytorch_model-00002-of-00002.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json 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..d6d01e2 --- /dev/null +++ b/README.md @@ -0,0 +1,49 @@ +language: en + +datasets: +- 37 popular Python code repositories +- See princeton-nlp/SWE-bench train split +- See the `make_datasets` documentation on SWE-bench's [GitHub](https://github.com/princeton-nlp/SWE-bench/tree/main/inference/make_datasets) for details on formatting input. + +--- + +# SWE-Llama + +SWE-Llama are variants of the [CodeLlama](https://arxiv.org/abs/2308.12950) model fine-tuned on software engineering tasks extracted from real-world GitHub issues and pull requests. They were introduced and evaluated on the SWE-bench benchmark in this [paper](https://arxiv.org/abs/2310.06770). + +## Model Details + +- **Architecture:** Transformer, based on [CodeLlama](https://arxiv.org/abs/2308.12950) architecture +- **Parameters:** 7 billion for SWE-Llama-7b, 13 billion for SWE-Llama-13b +- **Objective:** Generating patches to resolve GitHub issues, conditioned on issue description and code context + +## Training Data + +SWE-Llama was fine-tuned on 19,000 issues and pull requests collected from 37 popular Python code repositories on GitHub, disjoint from those used in SWE-bench. + +## Training Procedure + +- Fine-tuned only the attention matrices using LoRA method +- Trained for 4 epochs with a batch size of 32 +- Selected best checkpoint based on validation perplexity + +## Evaluation Results + +When evaluated on the SWE-bench benchmark: + +- SWE-Llama-7b achieved 3.0% issue resolution rate using oracle context retrieval +- SWE-Llama-13b achieved 4.0% issue resolution rate using oracle context retrieval + +## BibTeX Entry +```tex +@misc{jimenez2023swebench, + title={SWE-bench: Can Language Models Resolve Real-World GitHub Issues?}, + author={Carlos E. Jimenez and John Yang + and Alexander Wettig and Shunyu Yao + and Kexin Pei and Ofir Press and Karthik Narasimhan}, + year={2023}, + eprint={2310.06770}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} +``` \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3280369 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "princeton-nlp/SWE-Llama-7b", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 16384, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} 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..3bf005e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.34.0.dev0", + "use_cache": ".cache" +} diff --git a/pytorch_model-00001-of-00002.bin b/pytorch_model-00001-of-00002.bin new file mode 100644 index 0000000..24a507e --- /dev/null +++ b/pytorch_model-00001-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed280174adf8fc9a9e59ef0ee664ff0588ff572658f83ed8ef4e7efb8eea27a +size 9976620122 diff --git a/pytorch_model-00002-of-00002.bin b/pytorch_model-00002-of-00002.bin new file mode 100644 index 0000000..9ead2da --- /dev/null +++ b/pytorch_model-00002-of-00002.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3830ecb732f96750b87bea33aebbcfd93031ed69ef9a8cdc829321c524acdad1 +size 3500310787 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..9902e1a --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e572e08c4d4e81c7916197f6fcd2956a2f05e5919f28d72c9ba4f351efae1e29 +size 23950 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..16ada5c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,37 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "use_default_system_prompt": true +}