Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
rl-swarm
grpo
gensyn
I am endangered gregarious wolf
trl
genrl-swarm
I am endangered_gregarious_wolf
conversational
text-generation-inference
Instructions to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf") model = AutoModelForCausalLM.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", 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 Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf
- SGLang
How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf 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 "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf" \ --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": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", "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 "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf" \ --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": "Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with Docker Model Runner:
docker model run hf.co/Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 5.0, | |
| "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": 221.59375, | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 60.60015106201172, | |
| "kl": 0.0, | |
| "learning_rate": 5e-07, | |
| "loss": 0.0, | |
| "reward": 3.4653576016426086, | |
| "reward_std": 0.8209123063861625, | |
| "rewards/concensus_correctness_reward_func": 0.7468749945983291, | |
| "rewards/consensus_reward_func": 1.0625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0625, | |
| "rewards/question_recreation_reward_func": 0.654263935983181, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.125, | |
| "rewards/xmlcount_reward_func": 0.8142187604680657, | |
| "step": 2 | |
| }, | |
| { | |
| "completion_length": 165.20833333333334, | |
| "epoch": 1.0, | |
| "grad_norm": 150909.671875, | |
| "kl": 5585.012409599808, | |
| "learning_rate": 4.864543104251586e-07, | |
| "loss": 4.1888, | |
| "reward": 4.646159549554189, | |
| "reward_std": 1.7369201476685703, | |
| "rewards/concensus_correctness_reward_func": 1.6091666668653488, | |
| "rewards/consensus_reward_func": 1.3333333333333333, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.5225345126042763, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.16666666666666666, | |
| "rewards/xmlcount_reward_func": 1.0144583334525425, | |
| "step": 4 | |
| }, | |
| { | |
| "completion_length": 178.1875, | |
| "epoch": 1.5714285714285714, | |
| "grad_norm": 33501.27734375, | |
| "kl": 14449.912984883413, | |
| "learning_rate": 4.472851273490984e-07, | |
| "loss": 14.4499, | |
| "reward": 5.632774636149406, | |
| "reward_std": 0.9981047324836254, | |
| "rewards/concensus_correctness_reward_func": 1.7074375040829182, | |
| "rewards/consensus_reward_func": 1.4375, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.125, | |
| "rewards/question_recreation_reward_func": 0.921055871527642, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.1292812526226044, | |
| "step": 6 | |
| }, | |
| { | |
| "completion_length": 180.75, | |
| "epoch": 2.0, | |
| "grad_norm": 35.281227111816406, | |
| "kl": 170.07763784006238, | |
| "learning_rate": 3.867370395306068e-07, | |
| "loss": 0.1276, | |
| "reward": 4.981932123502095, | |
| "reward_std": 0.7679674559306781, | |
| "rewards/concensus_correctness_reward_func": 1.2675833149502675, | |
| "rewards/consensus_reward_func": 1.5833333333333333, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.787265474597613, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.09375, | |
| "step": 8 | |
| }, | |
| { | |
| "completion_length": 161.96875, | |
| "epoch": 2.571428571428571, | |
| "grad_norm": 9011.3623046875, | |
| "kl": 28157.17834121408, | |
| "learning_rate": 3.1137137178519977e-07, | |
| "loss": 28.1572, | |
| "reward": 4.997823455370963, | |
| "reward_std": 0.4187893490015995, | |
| "rewards/concensus_correctness_reward_func": 1.4683750048279762, | |
| "rewards/consensus_reward_func": 1.125, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.3125, | |
| "rewards/question_recreation_reward_func": 0.7822921997867525, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.296875, | |
| "rewards/xmlcount_reward_func": 1.0127812502905726, | |
| "step": 10 | |
| }, | |
| { | |
| "completion_length": 157.5, | |
| "epoch": 3.0, | |
| "grad_norm": 4991.70263671875, | |
| "kl": 138.71271182348332, | |
| "learning_rate": 2.2935516363191693e-07, | |
| "loss": 0.104, | |
| "reward": 5.47919899225235, | |
| "reward_std": 0.46974249742925167, | |
| "rewards/concensus_correctness_reward_func": 1.6604999899864197, | |
| "rewards/consensus_reward_func": 1.75, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7041156962513924, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.20833333333333334, | |
| "rewards/xmlcount_reward_func": 1.15625, | |
| "step": 12 | |
| }, | |
| { | |
| "completion_length": 180.3125, | |
| "epoch": 3.571428571428571, | |
| "grad_norm": 53.90495300292969, | |
| "kl": 796.3256631409749, | |
| "learning_rate": 1.4957614383675767e-07, | |
| "loss": 0.7963, | |
| "reward": 5.196396499872208, | |
| "reward_std": 0.8098996949993307, | |
| "rewards/concensus_correctness_reward_func": 1.4756874996237457, | |
| "rewards/consensus_reward_func": 1.5625, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7931465404108167, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.25, | |
| "rewards/xmlcount_reward_func": 1.1150625012814999, | |
| "step": 14 | |
| }, | |
| { | |
| "completion_length": 174.83333333333334, | |
| "epoch": 4.0, | |
| "grad_norm": 29.16839027404785, | |
| "kl": 1.8292740272978942, | |
| "learning_rate": 8.067960709356478e-08, | |
| "loss": 0.0014, | |
| "reward": 5.595823963483174, | |
| "reward_std": 1.0394487765928109, | |
| "rewards/concensus_correctness_reward_func": 1.6602499932050705, | |
| "rewards/consensus_reward_func": 1.5, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.16666666666666666, | |
| "rewards/question_recreation_reward_func": 0.8422823200623194, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.2916666666666667, | |
| "rewards/xmlcount_reward_func": 1.1349583268165588, | |
| "step": 16 | |
| }, | |
| { | |
| "completion_length": 172.03125, | |
| "epoch": 4.571428571428571, | |
| "grad_norm": 11252.7509765625, | |
| "kl": 134.45813744235784, | |
| "learning_rate": 3.013156219837776e-08, | |
| "loss": 0.1345, | |
| "reward": 5.485393404960632, | |
| "reward_std": 0.7980908276222181, | |
| "rewards/concensus_correctness_reward_func": 1.589249990414828, | |
| "rewards/consensus_reward_func": 1.6875, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.0, | |
| "rewards/question_recreation_reward_func": 0.7450809078291059, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.3125, | |
| "rewards/xmlcount_reward_func": 1.1510625034570694, | |
| "step": 18 | |
| }, | |
| { | |
| "completion_length": 193.04166666666666, | |
| "epoch": 5.0, | |
| "grad_norm": 30.57774543762207, | |
| "kl": 200.24465695520243, | |
| "learning_rate": 3.4096741493194193e-09, | |
| "loss": 0.1502, | |
| "reward": 5.304450035095215, | |
| "reward_std": 0.765751785133034, | |
| "rewards/concensus_correctness_reward_func": 1.5927500029404957, | |
| "rewards/consensus_reward_func": 1.4166666666666667, | |
| "rewards/cumulative_reward_2": 0.0, | |
| "rewards/final_correctness_reward_func": 0.25, | |
| "rewards/question_recreation_reward_func": 0.7779916717360417, | |
| "rewards/soft_format_reward_func": 0.0, | |
| "rewards/strict_format_reward_func": 0.22916666666666666, | |
| "rewards/xmlcount_reward_func": 1.0378750016291935, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "step": 20, | |
| "total_flos": 0.0, | |
| "train_loss": 4.810982779075857, | |
| "train_runtime": 118.2668, | |
| "train_samples_per_second": 2.706, | |
| "train_steps_per_second": 0.169 | |
| } | |
| ], | |
| "logging_steps": 2, | |
| "max_steps": 20, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 7, | |
| "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 | |
| } | |