Instructions to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-14B-Instruct") model = PeftModel.from_pretrained(base_model, "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1") - Transformers
How to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1
- SGLang
How to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 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 "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1" \ --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": "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1", "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 "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1" \ --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": "ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1 with Docker Model Runner:
docker model run hf.co/ajChakrarborty/toolrl-rl-data-qwen2.5-14b-instruct-ft-1
| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 200, | |
| "global_step": 1900, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013157894736842105, | |
| "grad_norm": 0.7272480130195618, | |
| "learning_rate": 8.421052631578948e-05, | |
| "loss": 1.9563, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02631578947368421, | |
| "grad_norm": 0.3988882899284363, | |
| "learning_rate": 0.00017192982456140353, | |
| "loss": 0.78, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.039473684210526314, | |
| "grad_norm": 0.23908574879169464, | |
| "learning_rate": 0.00019995801573733038, | |
| "loss": 0.5912, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.05263157894736842, | |
| "grad_norm": 0.22981883585453033, | |
| "learning_rate": 0.00019974382771078473, | |
| "loss": 0.5734, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.06578947368421052, | |
| "grad_norm": 0.22677601873874664, | |
| "learning_rate": 0.00019934852677927834, | |
| "loss": 0.5326, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.07894736842105263, | |
| "grad_norm": 0.23226918280124664, | |
| "learning_rate": 0.00019877283072256436, | |
| "loss": 0.4978, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.09210526315789473, | |
| "grad_norm": 0.265936017036438, | |
| "learning_rate": 0.00019801778487836048, | |
| "loss": 0.5083, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.10526315789473684, | |
| "grad_norm": 0.2562519609928131, | |
| "learning_rate": 0.00019708476024424477, | |
| "loss": 0.5017, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.11842105263157894, | |
| "grad_norm": 0.24657155573368073, | |
| "learning_rate": 0.00019597545098822504, | |
| "loss": 0.5355, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.13157894736842105, | |
| "grad_norm": 0.2717723548412323, | |
| "learning_rate": 0.00019469187137250148, | |
| "loss": 0.5057, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.14473684210526316, | |
| "grad_norm": 0.14394891262054443, | |
| "learning_rate": 0.00019323635209600841, | |
| "loss": 0.5435, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.15789473684210525, | |
| "grad_norm": 0.2538720369338989, | |
| "learning_rate": 0.00019161153606237651, | |
| "loss": 0.4619, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.17105263157894737, | |
| "grad_norm": 0.2302940934896469, | |
| "learning_rate": 0.00018982037358099963, | |
| "loss": 0.5144, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.18421052631578946, | |
| "grad_norm": 0.23402678966522217, | |
| "learning_rate": 0.00018786611700992044, | |
| "loss": 0.5385, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.19736842105263158, | |
| "grad_norm": 0.2835828363895416, | |
| "learning_rate": 0.0001857523148502617, | |
| "loss": 0.5324, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.21052631578947367, | |
| "grad_norm": 0.2346741110086441, | |
| "learning_rate": 0.00018348280530292713, | |
| "loss": 0.5538, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2236842105263158, | |
| "grad_norm": 0.20240184664726257, | |
| "learning_rate": 0.00018106170929927035, | |
| "loss": 0.4757, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 0.23684210526315788, | |
| "grad_norm": 0.23748184740543365, | |
| "learning_rate": 0.0001784934230183882, | |
| "loss": 0.4722, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 0.24441654980182648, | |
| "learning_rate": 0.00017578260990462372, | |
| "loss": 0.4765, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 0.2631578947368421, | |
| "grad_norm": 0.21534137427806854, | |
| "learning_rate": 0.00017293419219977486, | |
| "loss": 0.511, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.27631578947368424, | |
| "grad_norm": 0.18411624431610107, | |
| "learning_rate": 0.0001699533420053832, | |
| "loss": 0.459, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 0.2894736842105263, | |
| "grad_norm": 0.22512228786945343, | |
| "learning_rate": 0.0001668454718913325, | |
| "loss": 0.4602, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3026315789473684, | |
| "grad_norm": 0.3007086515426636, | |
| "learning_rate": 0.00016361622506780944, | |
| "loss": 0.4723, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 0.3157894736842105, | |
| "grad_norm": 0.24483013153076172, | |
| "learning_rate": 0.0001602714651384722, | |
| "loss": 0.4825, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.32894736842105265, | |
| "grad_norm": 0.19368383288383484, | |
| "learning_rate": 0.0001568172654534328, | |
| "loss": 0.5199, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 0.34210526315789475, | |
| "grad_norm": 0.27732446789741516, | |
| "learning_rate": 0.0001532598980813858, | |
| "loss": 0.4766, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.35526315789473684, | |
| "grad_norm": 0.2359321564435959, | |
| "learning_rate": 0.0001496058224209082, | |
| "loss": 0.4315, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 0.3684210526315789, | |
| "grad_norm": 0.25275617837905884, | |
| "learning_rate": 0.00014586167347160846, | |
| "loss": 0.4361, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.3815789473684211, | |
| "grad_norm": 0.1912153959274292, | |
| "learning_rate": 0.00014203424978642337, | |
| "loss": 0.4467, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 0.39473684210526316, | |
| "grad_norm": 0.23994949460029602, | |
| "learning_rate": 0.00013813050112693778, | |
| "loss": 0.4927, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.40789473684210525, | |
| "grad_norm": 0.23791591823101044, | |
| "learning_rate": 0.00013415751584414215, | |
| "loss": 0.4032, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 0.42105263157894735, | |
| "grad_norm": 0.2177554816007614, | |
| "learning_rate": 0.00013012250800754284, | |
| "loss": 0.5174, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4342105263157895, | |
| "grad_norm": 0.2537310719490051, | |
| "learning_rate": 0.0001260328043059947, | |
| "loss": 0.5024, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 0.4473684210526316, | |
| "grad_norm": 0.3210338056087494, | |
| "learning_rate": 0.00012189583074404174, | |
| "loss": 0.4572, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.4605263157894737, | |
| "grad_norm": 0.1832045167684555, | |
| "learning_rate": 0.0001177190991579223, | |
| "loss": 0.4374, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 0.47368421052631576, | |
| "grad_norm": 0.21890908479690552, | |
| "learning_rate": 0.00011351019357572274, | |
| "loss": 0.446, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.4868421052631579, | |
| "grad_norm": 0.2524813115596771, | |
| "learning_rate": 0.00010927675644644666, | |
| "loss": 0.4316, | |
| "step": 925 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.2024998813867569, | |
| "learning_rate": 0.0001050264747630043, | |
| "loss": 0.4264, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5131578947368421, | |
| "grad_norm": 0.23862822353839874, | |
| "learning_rate": 0.00010076706610432009, | |
| "loss": 0.4809, | |
| "step": 975 | |
| }, | |
| { | |
| "epoch": 0.5263157894736842, | |
| "grad_norm": 0.21620877087116241, | |
| "learning_rate": 9.650626462190294e-05, | |
| "loss": 0.4528, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5394736842105263, | |
| "grad_norm": 0.2496652454137802, | |
| "learning_rate": 9.2251806996324e-05, | |
| "loss": 0.5165, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 0.5526315789473685, | |
| "grad_norm": 0.18958808481693268, | |
| "learning_rate": 8.801141838910238e-05, | |
| "loss": 0.461, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.5657894736842105, | |
| "grad_norm": 0.2566398084163666, | |
| "learning_rate": 8.379279841550693e-05, | |
| "loss": 0.4917, | |
| "step": 1075 | |
| }, | |
| { | |
| "epoch": 0.5789473684210527, | |
| "grad_norm": 0.2727346122264862, | |
| "learning_rate": 7.960360716374442e-05, | |
| "loss": 0.4035, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5921052631578947, | |
| "grad_norm": 0.2812783718109131, | |
| "learning_rate": 7.54514512859201e-05, | |
| "loss": 0.4062, | |
| "step": 1125 | |
| }, | |
| { | |
| "epoch": 0.6052631578947368, | |
| "grad_norm": 0.13381074368953705, | |
| "learning_rate": 7.134387018602659e-05, | |
| "loss": 0.4147, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.618421052631579, | |
| "grad_norm": 0.24165485799312592, | |
| "learning_rate": 6.728832233004054e-05, | |
| "loss": 0.4694, | |
| "step": 1175 | |
| }, | |
| { | |
| "epoch": 0.631578947368421, | |
| "grad_norm": 0.1850873976945877, | |
| "learning_rate": 6.329217170298507e-05, | |
| "loss": 0.5144, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6447368421052632, | |
| "grad_norm": 0.3044758439064026, | |
| "learning_rate": 5.936267443754863e-05, | |
| "loss": 0.448, | |
| "step": 1225 | |
| }, | |
| { | |
| "epoch": 0.6578947368421053, | |
| "grad_norm": 0.25881174206733704, | |
| "learning_rate": 5.550696563854032e-05, | |
| "loss": 0.4331, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.6710526315789473, | |
| "grad_norm": 0.1471320539712906, | |
| "learning_rate": 5.173204642710514e-05, | |
| "loss": 0.4162, | |
| "step": 1275 | |
| }, | |
| { | |
| "epoch": 0.6842105263157895, | |
| "grad_norm": 0.23026077449321747, | |
| "learning_rate": 4.804477122822432e-05, | |
| "loss": 0.4321, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6973684210526315, | |
| "grad_norm": 0.2941257655620575, | |
| "learning_rate": 4.4451835324583326e-05, | |
| "loss": 0.4041, | |
| "step": 1325 | |
| }, | |
| { | |
| "epoch": 0.7105263157894737, | |
| "grad_norm": 0.2662881016731262, | |
| "learning_rate": 4.0959762699407766e-05, | |
| "loss": 0.4282, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7236842105263158, | |
| "grad_norm": 0.27813515067100525, | |
| "learning_rate": 3.7574894190341404e-05, | |
| "loss": 0.4424, | |
| "step": 1375 | |
| }, | |
| { | |
| "epoch": 0.7368421052631579, | |
| "grad_norm": 0.25936228036880493, | |
| "learning_rate": 3.430337597587622e-05, | |
| "loss": 0.4325, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.2591690421104431, | |
| "learning_rate": 3.1151148415241035e-05, | |
| "loss": 0.4389, | |
| "step": 1425 | |
| }, | |
| { | |
| "epoch": 0.7631578947368421, | |
| "grad_norm": 0.2798675298690796, | |
| "learning_rate": 2.8123935262012447e-05, | |
| "loss": 0.4832, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.7763157894736842, | |
| "grad_norm": 0.28093063831329346, | |
| "learning_rate": 2.5227233271034322e-05, | |
| "loss": 0.4171, | |
| "step": 1475 | |
| }, | |
| { | |
| "epoch": 0.7894736842105263, | |
| "grad_norm": 0.292204350233078, | |
| "learning_rate": 2.2466302217517133e-05, | |
| "loss": 0.4802, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8026315789473685, | |
| "grad_norm": 0.2873384654521942, | |
| "learning_rate": 1.984615534644032e-05, | |
| "loss": 0.4688, | |
| "step": 1525 | |
| }, | |
| { | |
| "epoch": 0.8157894736842105, | |
| "grad_norm": 0.23933933675289154, | |
| "learning_rate": 1.7371550269599323e-05, | |
| "loss": 0.4687, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.8289473684210527, | |
| "grad_norm": 0.27426981925964355, | |
| "learning_rate": 1.50469803268267e-05, | |
| "loss": 0.4475, | |
| "step": 1575 | |
| }, | |
| { | |
| "epoch": 0.8421052631578947, | |
| "grad_norm": 0.2896619439125061, | |
| "learning_rate": 1.2876666427072703e-05, | |
| "loss": 0.4643, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8552631578947368, | |
| "grad_norm": 0.15856152772903442, | |
| "learning_rate": 1.0864549384160927e-05, | |
| "loss": 0.4614, | |
| "step": 1625 | |
| }, | |
| { | |
| "epoch": 0.868421052631579, | |
| "grad_norm": 0.32572880387306213, | |
| "learning_rate": 9.014282761135084e-06, | |
| "loss": 0.3922, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.881578947368421, | |
| "grad_norm": 0.2075156420469284, | |
| "learning_rate": 7.329226236190201e-06, | |
| "loss": 0.4834, | |
| "step": 1675 | |
| }, | |
| { | |
| "epoch": 0.8947368421052632, | |
| "grad_norm": 0.2609516978263855, | |
| "learning_rate": 5.81243950223419e-06, | |
| "loss": 0.4424, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9078947368421053, | |
| "grad_norm": 0.27902549505233765, | |
| "learning_rate": 4.4666767111569474e-06, | |
| "loss": 0.4107, | |
| "step": 1725 | |
| }, | |
| { | |
| "epoch": 0.9210526315789473, | |
| "grad_norm": 0.1807645708322525, | |
| "learning_rate": 3.294381472894781e-06, | |
| "loss": 0.4095, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.9342105263157895, | |
| "grad_norm": 0.27969783544540405, | |
| "learning_rate": 2.2976824183709835e-06, | |
| "loss": 0.4665, | |
| "step": 1775 | |
| }, | |
| { | |
| "epoch": 0.9473684210526315, | |
| "grad_norm": 0.27561429142951965, | |
| "learning_rate": 1.4783893343691458e-06, | |
| "loss": 0.4077, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9605263157894737, | |
| "grad_norm": 0.2988797426223755, | |
| "learning_rate": 8.379898773574924e-07, | |
| "loss": 0.4332, | |
| "step": 1825 | |
| }, | |
| { | |
| "epoch": 0.9736842105263158, | |
| "grad_norm": 0.2036939263343811, | |
| "learning_rate": 3.7764687223110773e-07, | |
| "loss": 0.401, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.9868421052631579, | |
| "grad_norm": 0.21864855289459229, | |
| "learning_rate": 9.8196200877132e-08, | |
| "loss": 0.4638, | |
| "step": 1875 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.2675096392631531, | |
| "learning_rate": 1.452843966354145e-10, | |
| "loss": 0.465, | |
| "step": 1900 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 1900, | |
| "num_input_tokens_seen": 0, | |
| "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": 2.7343723267668173e+17, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |