Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Instructions to use lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155") model = AutoModelForCausalLM.from_pretrained("lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155") 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
- vLLM
How to use lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155
- SGLang
How to use lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155 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 "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155" \ --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": "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155", "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 "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155" \ --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": "lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155 with Docker Model Runner:
docker model run hf.co/lllqaq/R2EGym-32B-Agent-Coder-R2egym-mid-post-step155
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.0, | |
| "eval_steps": 500, | |
| "global_step": 540, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03710575139146568, | |
| "grad_norm": 75.80557250976562, | |
| "learning_rate": 1.6666666666666667e-06, | |
| "loss": 3.1368, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07421150278293136, | |
| "grad_norm": 7.823807716369629, | |
| "learning_rate": 3.5185185185185187e-06, | |
| "loss": 1.9929, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11131725417439703, | |
| "grad_norm": 1.7641185522079468, | |
| "learning_rate": 5.370370370370371e-06, | |
| "loss": 0.901, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14842300556586271, | |
| "grad_norm": 2.0621747970581055, | |
| "learning_rate": 7.222222222222223e-06, | |
| "loss": 0.5934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.18552875695732837, | |
| "grad_norm": 0.9267826676368713, | |
| "learning_rate": 9.074074074074075e-06, | |
| "loss": 0.396, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.22263450834879406, | |
| "grad_norm": 0.8804956078529358, | |
| "learning_rate": 9.997388623947927e-06, | |
| "loss": 0.3619, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2597402597402597, | |
| "grad_norm": 1.133553385734558, | |
| "learning_rate": 9.976513978965829e-06, | |
| "loss": 0.2826, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.29684601113172543, | |
| "grad_norm": 0.861992597579956, | |
| "learning_rate": 9.934851884702415e-06, | |
| "loss": 0.2703, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3339517625231911, | |
| "grad_norm": 0.6837931275367737, | |
| "learning_rate": 9.872576368333152e-06, | |
| "loss": 0.2481, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.37105751391465674, | |
| "grad_norm": 0.9555836319923401, | |
| "learning_rate": 9.789947561577445e-06, | |
| "loss": 0.2355, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.40816326530612246, | |
| "grad_norm": 1.1039456129074097, | |
| "learning_rate": 9.687310614099676e-06, | |
| "loss": 0.2368, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4452690166975881, | |
| "grad_norm": 0.8142388463020325, | |
| "learning_rate": 9.565094251780872e-06, | |
| "loss": 0.2282, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.48237476808905383, | |
| "grad_norm": 0.6265286803245544, | |
| "learning_rate": 9.423808985883289e-06, | |
| "loss": 0.2268, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5194805194805194, | |
| "grad_norm": 0.7751391530036926, | |
| "learning_rate": 9.264044980588415e-06, | |
| "loss": 0.2231, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5565862708719852, | |
| "grad_norm": 0.6618830561637878, | |
| "learning_rate": 9.086469587815904e-06, | |
| "loss": 0.2274, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5936920222634509, | |
| "grad_norm": 1.1778677701950073, | |
| "learning_rate": 8.891824559620801e-06, | |
| "loss": 0.2214, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6307977736549165, | |
| "grad_norm": 0.6525479555130005, | |
| "learning_rate": 8.680922949813177e-06, | |
| "loss": 0.2152, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6679035250463822, | |
| "grad_norm": 1.056062936782837, | |
| "learning_rate": 8.45464571774244e-06, | |
| "loss": 0.2148, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7050092764378478, | |
| "grad_norm": 0.506918728351593, | |
| "learning_rate": 8.213938048432697e-06, | |
| "loss": 0.2064, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.7421150278293135, | |
| "grad_norm": 0.6317462921142578, | |
| "learning_rate": 7.95980540444038e-06, | |
| "loss": 0.2136, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7792207792207793, | |
| "grad_norm": 0.888347864151001, | |
| "learning_rate": 7.69330932592594e-06, | |
| "loss": 0.2214, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 0.8190760612487793, | |
| "learning_rate": 7.415562996483193e-06, | |
| "loss": 0.2112, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8534322820037106, | |
| "grad_norm": 0.6531184315681458, | |
| "learning_rate": 7.127726593248337e-06, | |
| "loss": 0.204, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8905380333951762, | |
| "grad_norm": 0.6250878572463989, | |
| "learning_rate": 6.8310024407117405e-06, | |
| "loss": 0.2078, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.9276437847866419, | |
| "grad_norm": 0.590032160282135, | |
| "learning_rate": 6.526629988475567e-06, | |
| "loss": 0.2078, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.9647495361781077, | |
| "grad_norm": 0.8457366824150085, | |
| "learning_rate": 6.215880633935709e-06, | |
| "loss": 0.1985, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.721627950668335, | |
| "learning_rate": 5.900052411514257e-06, | |
| "loss": 0.195, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 1.0371057513914657, | |
| "grad_norm": 1.2528144121170044, | |
| "learning_rate": 5.5804645706261515e-06, | |
| "loss": 0.1468, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 1.0742115027829313, | |
| "grad_norm": 0.8960326910018921, | |
| "learning_rate": 5.258452065028473e-06, | |
| "loss": 0.1426, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 1.111317254174397, | |
| "grad_norm": 0.7007734775543213, | |
| "learning_rate": 4.9353599765709585e-06, | |
| "loss": 0.1366, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.1484230055658626, | |
| "grad_norm": 0.480663537979126, | |
| "learning_rate": 4.6125378966403465e-06, | |
| "loss": 0.1395, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 1.1855287569573283, | |
| "grad_norm": 0.47765257954597473, | |
| "learning_rate": 4.291334288767899e-06, | |
| "loss": 0.1372, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 1.222634508348794, | |
| "grad_norm": 1.1163313388824463, | |
| "learning_rate": 3.9730908559480904e-06, | |
| "loss": 0.1467, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 1.2597402597402598, | |
| "grad_norm": 0.9910896420478821, | |
| "learning_rate": 3.6591369361968127e-06, | |
| "loss": 0.1395, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 1.2968460111317255, | |
| "grad_norm": 0.852510929107666, | |
| "learning_rate": 3.350783949759462e-06, | |
| "loss": 0.1415, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.3339517625231911, | |
| "grad_norm": 0.5408625602722168, | |
| "learning_rate": 3.049319921163526e-06, | |
| "loss": 0.134, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.3710575139146568, | |
| "grad_norm": 0.5254811644554138, | |
| "learning_rate": 2.7560040989976894e-06, | |
| "loss": 0.1398, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 1.4081632653061225, | |
| "grad_norm": 0.8783926367759705, | |
| "learning_rate": 2.4720616958912054e-06, | |
| "loss": 0.1434, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 1.4452690166975881, | |
| "grad_norm": 1.284106969833374, | |
| "learning_rate": 2.1986787706652377e-06, | |
| "loss": 0.1377, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 1.4823747680890538, | |
| "grad_norm": 0.5269446969032288, | |
| "learning_rate": 1.936997274033986e-06, | |
| "loss": 0.1354, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.5194805194805194, | |
| "grad_norm": 0.5373296141624451, | |
| "learning_rate": 1.6881102785502618e-06, | |
| "loss": 0.1313, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 1.556586270871985, | |
| "grad_norm": 0.5133374333381653, | |
| "learning_rate": 1.453057412720536e-06, | |
| "loss": 0.1326, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.593692022263451, | |
| "grad_norm": 1.2796943187713623, | |
| "learning_rate": 1.2328205183616964e-06, | |
| "loss": 0.1403, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 1.6307977736549164, | |
| "grad_norm": 0.8333746790885925, | |
| "learning_rate": 1.0283195493391823e-06, | |
| "loss": 0.135, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 1.6679035250463823, | |
| "grad_norm": 0.5386627912521362, | |
| "learning_rate": 8.404087288179425e-07, | |
| "loss": 0.1317, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.7050092764378477, | |
| "grad_norm": 0.5091426968574524, | |
| "learning_rate": 6.698729810778065e-07, | |
| "loss": 0.1287, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.7421150278293136, | |
| "grad_norm": 0.4761359393596649, | |
| "learning_rate": 5.174246527979532e-07, | |
| "loss": 0.1312, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.7792207792207793, | |
| "grad_norm": 0.7398775219917297, | |
| "learning_rate": 3.837005375060482e-07, | |
| "loss": 0.128, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.816326530612245, | |
| "grad_norm": 0.614173948764801, | |
| "learning_rate": 2.6925921562124867e-07, | |
| "loss": 0.1305, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.8534322820037106, | |
| "grad_norm": 0.9018604159355164, | |
| "learning_rate": 1.745787212020178e-07, | |
| "loss": 0.136, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.8905380333951762, | |
| "grad_norm": 0.5306493639945984, | |
| "learning_rate": 1.0005454514499413e-07, | |
| "loss": 0.1221, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.927643784786642, | |
| "grad_norm": 0.5025076866149902, | |
| "learning_rate": 4.599798317577342e-08, | |
| "loss": 0.1307, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.9647495361781075, | |
| "grad_norm": 1.3446109294891357, | |
| "learning_rate": 1.2634835532233658e-08, | |
| "loss": 0.1358, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 1.5992753505706787, | |
| "learning_rate": 1.0446377197104174e-10, | |
| "loss": 0.1257, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 540, | |
| "total_flos": 2.1175585841610752e+17, | |
| "train_loss": 0.2914459398499242, | |
| "train_runtime": 58643.1461, | |
| "train_samples_per_second": 0.11, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 540, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.1175585841610752e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |