commit 37d2ed4d3969d31421796e1f2e5860eb2942a209 Author: ModelHub XC Date: Sun Jun 14 23:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: abharadwaj123/sqlstorm-grpo-plan8192 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9f25299 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,37 @@ +*.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 +checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..386592c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: abharadwaj123/llama3-sql2plan +library_name: transformers +model_name: rl_grpo_output_plan8192 +tags: +- generated_from_trainer +- trl +- grpo +licence: license +--- + +# Model Card for rl_grpo_output_plan8192 + +This model is a fine-tuned version of [abharadwaj123/llama3-sql2plan](https://huggingface.co/abharadwaj123/llama3-sql2plan). +It has been trained using [TRL](https://github.com/huggingface/trl). + +## Quick start + +```python +from transformers import pipeline + +question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?" +generator = pipeline("text-generation", model="None", device="cuda") +output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] +print(output["generated_text"]) +``` + +## Training procedure + + + + + +This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). + +### Framework versions + +- TRL: 0.29.0 +- Transformers: 5.3.0 +- Pytorch: 2.10.0 +- Datasets: 4.8.3 +- Tokenizers: 0.22.2 + +## Citations + +Cite GRPO as: + +```bibtex +@article{shao2024deepseekmath, + title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, + author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, + year = 2024, + eprint = {arXiv:2402.03300}, +} + +``` + +Cite TRL as: + +```bibtex +@software{vonwerra2020trl, + title = {{TRL: Transformers Reinforcement Learning}}, + author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin}, + license = {Apache-2.0}, + url = {https://github.com/huggingface/trl}, + year = {2020} +} +``` \ No newline at end of file diff --git a/checkpoint-12/config.json b/checkpoint-12/config.json new file mode 100644 index 0000000..376d859 --- /dev/null +++ b/checkpoint-12/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/checkpoint-12/generation_config.json b/checkpoint-12/generation_config.json new file mode 100644 index 0000000..27f18a5 --- /dev/null +++ b/checkpoint-12/generation_config.json @@ -0,0 +1,12 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001 + ], + "pad_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.3.0" +} diff --git a/checkpoint-12/model.safetensors b/checkpoint-12/model.safetensors new file mode 100644 index 0000000..b58fa58 --- /dev/null +++ b/checkpoint-12/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed250bb930901325437e50b2b5edbab58f1e4f6743afe9c6694d696135fcc1fd +size 6425529112 diff --git a/checkpoint-12/tokenizer.json b/checkpoint-12/tokenizer.json new file mode 100644 index 0000000..df78232 --- /dev/null +++ b/checkpoint-12/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849c7a8f7db3c85f7ab0a8228f72f5d6f2e771af657bda892b6b54a86aca12a0 +size 17210089 diff --git a/checkpoint-12/tokenizer_config.json b/checkpoint-12/tokenizer_config.json new file mode 100644 index 0000000..f11592a --- /dev/null +++ b/checkpoint-12/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/checkpoint-12/trainer_state.json b/checkpoint-12/trainer_state.json new file mode 100644 index 0000000..b40fd88 --- /dev/null +++ b/checkpoint-12/trainer_state.json @@ -0,0 +1,61 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.48, + "eval_steps": 500, + "global_step": 12, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "clip_ratio/high_max": 0.0, + "clip_ratio/high_mean": 0.0, + "clip_ratio/low_mean": 0.0, + "clip_ratio/low_min": 0.0, + "clip_ratio/region_mean": 0.0, + "completions/clipped_ratio": 0.175, + "completions/max_length": 6298.7, + "completions/max_terminated_length": 4670.0, + "completions/mean_length": 3769.95, + "completions/mean_terminated_length": 2954.4666748046875, + "completions/min_length": 1554.8, + "completions/min_terminated_length": 1554.8, + "entropy": 4.061883237212896, + "epoch": 0.4, + "frac_reward_zero_std": 0.05, + "grad_norm": 0.3359375, + "learning_rate": 2.5e-06, + "loss": -0.07856913208961487, + "num_tokens": 166764.0, + "reward": 0.6544295579195023, + "reward_std": 0.040438423810701354, + "rewards/reward_func/mean": 0.6544295579195023, + "rewards/reward_func/std": 0.04043842608807609, + "step": 10, + "step_time": 292.8999413277721 + } + ], + "logging_steps": 10, + "max_steps": 12, + "num_input_tokens_seen": 210353, + "num_train_epochs": 1, + "save_steps": 200, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 0.0, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-12/training_args.bin b/checkpoint-12/training_args.bin new file mode 100644 index 0000000..f928c02 --- /dev/null +++ b/checkpoint-12/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd0777ba7dc2ef8d504066fe46d1b754448e30cfb2b6ab178c7c529bdfa7cf5 +size 6929 diff --git a/config.json b/config.json new file mode 100644 index 0000000..376d859 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 3072, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 24, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "pad_token_id": 128001, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.3.0", + "use_cache": false, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..27f18a5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001 + ], + "pad_token_id": 128001, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.3.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..b58fa58 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed250bb930901325437e50b2b5edbab58f1e4f6743afe9c6694d696135fcc1fd +size 6425529112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..df78232 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849c7a8f7db3c85f7ab0a8228f72f5d6f2e771af657bda892b6b54a86aca12a0 +size 17210089 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..f11592a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,14 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|end_of_text|>", + "is_local": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|end_of_text|>", + "tokenizer_class": "TokenizersBackend" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..f928c02 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dd0777ba7dc2ef8d504066fe46d1b754448e30cfb2b6ab178c7c529bdfa7cf5 +size 6929