Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am wild lethal ocelot
trl
conversational
text-generation-inference
Instructions to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot") model = AutoModelForCausalLM.from_pretrained("wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot", 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]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot
- SGLang
How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot 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 "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot" \ --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": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot", "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 "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot" \ --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": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with Docker Model Runner:
docker model run hf.co/wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot
| { | |
| "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": 217.9375, | |
| "epoch": 0.1, | |
| "grad_norm": 26.588115692138672, | |
| "kl": 0.0, | |
| "learning_rate": 4.965903258506806e-07, | |
| "loss": -0.0, | |
| "reward": 3.9238121116068214, | |
| "reward_std": 0.4984353088802891, | |
| "rewards/concensus_correctness_reward_func": 1.1453749984502792, | |
| "rewards/consensus_reward_func": 1.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.6629996267147362, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.203125, | |
| "rewards/xmlcount_reward_func": 0.7248125001788139, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 153.125, | |
| "epoch": 0.2, | |
| "grad_norm": 3096.6826171875, | |
| "kl": 127.40181041706819, | |
| "learning_rate": 4.698684378016222e-07, | |
| "loss": 0.1274, | |
| "reward": 6.899618923664093, | |
| "reward_std": 0.24133055911806878, | |
| "rewards/concensus_correctness_reward_func": 2.1158749982714653, | |
| "rewards/consensus_reward_func": 2.0, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.8959314632229507, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.375, | |
| "rewards/xmlcount_reward_func": 1.200312502682209, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 198.40625, | |
| "epoch": 0.3, | |
| "grad_norm": 1606.969970703125, | |
| "kl": 795.1475641654106, | |
| "learning_rate": 4.193203929064353e-07, | |
| "loss": 0.7951, | |
| "reward": 5.769073113799095, | |
| "reward_std": 0.7471559516125126, | |
| "rewards/concensus_correctness_reward_func": 1.5693749859929085, | |
| "rewards/consensus_reward_func": 1.75, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.1875, | |
| "rewards/question_recreation_reward_func": 0.8377606067806482, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.0806875005364418, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 152.0, | |
| "epoch": 0.4, | |
| "grad_norm": 40.196903228759766, | |
| "kl": 13.456765508046374, | |
| "learning_rate": 3.5042385616324236e-07, | |
| "loss": 0.0135, | |
| "reward": 6.106819957494736, | |
| "reward_std": 0.7433944554068148, | |
| "rewards/concensus_correctness_reward_func": 1.8684999831020832, | |
| "rewards/consensus_reward_func": 1.8125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.7426948631182313, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.375, | |
| "rewards/xmlcount_reward_func": 1.1831250041723251, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 131.21875, | |
| "epoch": 0.5, | |
| "grad_norm": 295.4882507324219, | |
| "kl": 10.536870398558676, | |
| "learning_rate": 2.706448363680831e-07, | |
| "loss": 0.0105, | |
| "reward": 6.271051615476608, | |
| "reward_std": 0.6707179503282532, | |
| "rewards/concensus_correctness_reward_func": 1.9781250059604645, | |
| "rewards/consensus_reward_func": 1.9375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0625, | |
| "rewards/question_recreation_reward_func": 0.7211140692234039, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.40625, | |
| "rewards/xmlcount_reward_func": 1.1655625030398369, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 152.90625, | |
| "epoch": 0.6, | |
| "grad_norm": 40.68523025512695, | |
| "kl": 1.2147540808655322, | |
| "learning_rate": 1.886286282148002e-07, | |
| "loss": 0.0012, | |
| "reward": 6.223801136016846, | |
| "reward_std": 0.5582126578883617, | |
| "rewards/concensus_correctness_reward_func": 1.8157499795779586, | |
| "rewards/consensus_reward_func": 1.875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.7773010907694697, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.4375, | |
| "rewards/xmlcount_reward_func": 1.1932500004768372, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 145.09375, | |
| "epoch": 0.7, | |
| "grad_norm": 45.17070770263672, | |
| "kl": 4.149055448011495, | |
| "learning_rate": 1.1326296046939333e-07, | |
| "loss": 0.0041, | |
| "reward": 6.308409869670868, | |
| "reward_std": 0.6662825503153726, | |
| "rewards/concensus_correctness_reward_func": 1.9175625070929527, | |
| "rewards/consensus_reward_func": 1.75, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.375, | |
| "rewards/question_recreation_reward_func": 0.8150973552837968, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.1382500194013119, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 148.96875, | |
| "epoch": 0.8, | |
| "grad_norm": 51.33207321166992, | |
| "kl": 1.3372775473326328, | |
| "learning_rate": 5.271487265090163e-08, | |
| "loss": 0.0013, | |
| "reward": 6.160888954997063, | |
| "reward_std": 0.6417121767881326, | |
| "rewards/concensus_correctness_reward_func": 1.8831249922513962, | |
| "rewards/consensus_reward_func": 1.875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.8388577756704763, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.34375, | |
| "rewards/xmlcount_reward_func": 1.095156254246831, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 165.5, | |
| "epoch": 0.9, | |
| "grad_norm": 38.135047912597656, | |
| "kl": 1.0823733173310757, | |
| "learning_rate": 1.3545689574841341e-08, | |
| "loss": 0.0011, | |
| "reward": 6.3814394772052765, | |
| "reward_std": 0.5592010340260458, | |
| "rewards/concensus_correctness_reward_func": 2.0731874965131283, | |
| "rewards/consensus_reward_func": 1.6875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.8645332593005151, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.28125, | |
| "rewards/xmlcount_reward_func": 1.1624687686562538, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 132.875, | |
| "epoch": 1.0, | |
| "grad_norm": 36.65176773071289, | |
| "kl": 5.834113052580506, | |
| "learning_rate": 0.0, | |
| "loss": 0.0058, | |
| "reward": 6.213781073689461, | |
| "reward_std": 0.47957354108802974, | |
| "rewards/concensus_correctness_reward_func": 1.863249994814396, | |
| "rewards/consensus_reward_func": 1.8125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.8057811510516331, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.421875, | |
| "rewards/xmlcount_reward_func": 1.1853750050067902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 20, | |
| "total_flos": 0.0, | |
| "train_loss": 0.09601817332440987, | |
| "train_runtime": 1148.53, | |
| "train_samples_per_second": 0.279, | |
| "train_steps_per_second": 0.017 | |
| } | |
| ], | |
| "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 | |
| } | |