Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am deadly deadly dingo
trl
conversational
text-generation-inference
Instructions to use haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo") model = AutoModelForCausalLM.from_pretrained("haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo
- SGLang
How to use haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo with Docker Model Runner:
docker model run hf.co/haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 20, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "completion_length": 193.34375, | |
| "epoch": 0.1, | |
| "grad_norm": 25.437278747558594, | |
| "kl": 0.0, | |
| "learning_rate": 4.965903258506806e-07, | |
| "loss": 0.0, | |
| "reward": 3.6266137938946486, | |
| "reward_std": 0.8307934795739129, | |
| "rewards/concensus_correctness_reward_func": 0.9024999998509884, | |
| "rewards/consensus_reward_func": 0.875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.6582388319075108, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.234375, | |
| "rewards/xmlcount_reward_func": 0.7689999984577298, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 228.46875, | |
| "epoch": 0.2, | |
| "grad_norm": 39.24359130859375, | |
| "kl": 1.5343358425889164, | |
| "learning_rate": 4.698684378016222e-07, | |
| "loss": 0.0015, | |
| "reward": 6.112734526395798, | |
| "reward_std": 1.0056872393470258, | |
| "rewards/concensus_correctness_reward_func": 1.8086874820291996, | |
| "rewards/consensus_reward_func": 1.75, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.9244220145046711, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.0515000000596046, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 166.5625, | |
| "epoch": 0.3, | |
| "grad_norm": 138.03665161132812, | |
| "kl": 2.744431208819151, | |
| "learning_rate": 4.193203929064353e-07, | |
| "loss": 0.0027, | |
| "reward": 5.025258347392082, | |
| "reward_std": 0.2811972763593076, | |
| "rewards/concensus_correctness_reward_func": 1.3959999848157167, | |
| "rewards/consensus_reward_func": 1.5, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7735082694562152, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.328125, | |
| "rewards/xmlcount_reward_func": 1.027624998241663, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 173.75, | |
| "epoch": 0.4, | |
| "grad_norm": 67.41569519042969, | |
| "kl": 6.022588826715946, | |
| "learning_rate": 3.5042385616324236e-07, | |
| "loss": 0.006, | |
| "reward": 6.697861954569817, | |
| "reward_std": 0.6546344570815563, | |
| "rewards/concensus_correctness_reward_func": 1.997437495738268, | |
| "rewards/consensus_reward_func": 1.8125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.375, | |
| "rewards/question_recreation_reward_func": 0.913518188521266, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.421875, | |
| "rewards/xmlcount_reward_func": 1.1775312554091215, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 136.65625, | |
| "epoch": 0.5, | |
| "grad_norm": 332.54534912109375, | |
| "kl": 17.14331202954054, | |
| "learning_rate": 2.706448363680831e-07, | |
| "loss": 0.0171, | |
| "reward": 7.414227694272995, | |
| "reward_std": 0.496162755342084, | |
| "rewards/concensus_correctness_reward_func": 2.4219999983906746, | |
| "rewards/consensus_reward_func": 1.9375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.625, | |
| "rewards/question_recreation_reward_func": 0.7981027774512768, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.4375, | |
| "rewards/xmlcount_reward_func": 1.1941250003874302, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 160.6875, | |
| "epoch": 0.6, | |
| "grad_norm": 29.822416305541992, | |
| "kl": 28.22160056978464, | |
| "learning_rate": 1.886286282148002e-07, | |
| "loss": 0.0282, | |
| "reward": 6.131470635533333, | |
| "reward_std": 1.1960517894112854, | |
| "rewards/concensus_correctness_reward_func": 1.8389999866485596, | |
| "rewards/consensus_reward_func": 1.625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.8451581280678511, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.375, | |
| "rewards/xmlcount_reward_func": 1.1348125003278255, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 183.0, | |
| "epoch": 0.7, | |
| "grad_norm": 36.994346618652344, | |
| "kl": 8.928391239605844, | |
| "learning_rate": 1.1326296046939333e-07, | |
| "loss": 0.0089, | |
| "reward": 6.382866933941841, | |
| "reward_std": 0.9713909234851599, | |
| "rewards/concensus_correctness_reward_func": 2.0543750189244747, | |
| "rewards/consensus_reward_func": 1.6875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.375, | |
| "rewards/question_recreation_reward_func": 0.8999295085668564, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.0066875014454126, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 148.59375, | |
| "epoch": 0.8, | |
| "grad_norm": 33.646080017089844, | |
| "kl": 0.7313799187541008, | |
| "learning_rate": 5.271487265090163e-08, | |
| "loss": 0.0007, | |
| "reward": 6.244778722524643, | |
| "reward_std": 0.8219166721682996, | |
| "rewards/concensus_correctness_reward_func": 1.810937486588955, | |
| "rewards/consensus_reward_func": 1.875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.8629974937066436, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.359375, | |
| "rewards/xmlcount_reward_func": 1.1489687487483025, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 125.125, | |
| "epoch": 0.9, | |
| "grad_norm": 263.7424011230469, | |
| "kl": 0.666266948916018, | |
| "learning_rate": 1.3545689574841341e-08, | |
| "loss": 0.0007, | |
| "reward": 5.990852370858192, | |
| "reward_std": 0.24256473960122094, | |
| "rewards/concensus_correctness_reward_func": 1.8007499873638153, | |
| "rewards/consensus_reward_func": 1.75, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7682274281978607, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.46875, | |
| "rewards/xmlcount_reward_func": 1.203125, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 130.875, | |
| "epoch": 1.0, | |
| "grad_norm": 75.74906921386719, | |
| "kl": 1.873372424626723, | |
| "learning_rate": 0.0, | |
| "loss": 0.0019, | |
| "reward": 6.883746221661568, | |
| "reward_std": 0.35684540566580836, | |
| "rewards/concensus_correctness_reward_func": 2.11268749833107, | |
| "rewards/consensus_reward_func": 1.8125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.375, | |
| "rewards/question_recreation_reward_func": 0.9117461740970612, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.453125, | |
| "rewards/xmlcount_reward_func": 1.218687504529953, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 0.0, | |
| "train_loss": 0.006785672821570188, | |
| "train_runtime": 1090.6448, | |
| "train_samples_per_second": 0.293, | |
| "train_steps_per_second": 0.018 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "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": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |