Instructions to use xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew")
model = AutoModelForCausalLM.from_pretrained("xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew", 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 xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew

SGLang

How to use xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew 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 "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew" \
    --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": "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew",
		"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 "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew" \
        --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": "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew with Docker Model Runner:
```
docker model run hf.co/xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew
```

Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew / trainer_state.json

xaobai

End of training

9634b65 verified over 1 year ago

Raw

History Blame Contribute Delete

8.53 kB

	{
	"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": 188.25,
	"epoch": 0.5714285714285714,
	"grad_norm": 294.656005859375,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": 0.0,
	"reward": 2.8357814326882362,
	"reward_std": 1.259905411321597,
	"rewards/concensus_correctness_reward_func": 0.5761874951422215,
	"rewards/consensus_reward_func": 0.6875,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.6327814008109272,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.109375,
	"rewards/xmlcount_reward_func": 0.7674374980852008,
	"step": 2
	},
	{
	"completion_length": 146.91666666666666,
	"epoch": 1.0,
	"grad_norm": 76.77713775634766,
	"kl": 13.654948055744171,
	"learning_rate": 4.864543104251586e-07,
	"loss": 0.0102,
	"reward": 5.330667932828267,
	"reward_std": 0.8708862774074078,
	"rewards/concensus_correctness_reward_func": 1.5764166563749313,
	"rewards/consensus_reward_func": 1.3333333333333333,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.3333333333333333,
	"rewards/question_recreation_reward_func": 0.7261679470539093,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.3125,
	"rewards/xmlcount_reward_func": 1.0489166676998138,
	"step": 4
	},
	{
	"completion_length": 131.78125,
	"epoch": 1.5714285714285714,
	"grad_norm": 89.60893249511719,
	"kl": 9.794984132546233,
	"learning_rate": 4.472851273490984e-07,
	"loss": 0.0098,
	"reward": 5.313216768205166,
	"reward_std": 0.6214285232999828,
	"rewards/concensus_correctness_reward_func": 1.4918124936521053,
	"rewards/consensus_reward_func": 1.375,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.25,
	"rewards/question_recreation_reward_func": 0.7866854909807444,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.328125,
	"rewards/xmlcount_reward_func": 1.0815937519073486,
	"step": 6
	},
	{
	"completion_length": 122.29166666666667,
	"epoch": 2.0,
	"grad_norm": 195.7334747314453,
	"kl": 20.494624653520685,
	"learning_rate": 3.867370395306068e-07,
	"loss": 0.0154,
	"reward": 3.7418640603621802,
	"reward_std": 0.8505224600958172,
	"rewards/concensus_correctness_reward_func": 1.0169999940941732,
	"rewards/consensus_reward_func": 0.9166666666666666,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.6136973790513972,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.2708333333333333,
	"rewards/xmlcount_reward_func": 0.9236666659514109,
	"step": 8
	},
	{
	"completion_length": 133.28125,
	"epoch": 2.571428571428571,
	"grad_norm": 5171.01611328125,
	"kl": 821.5899913753092,
	"learning_rate": 3.1137137178519977e-07,
	"loss": 0.8216,
	"reward": 4.067712027579546,
	"reward_std": 0.522601830016356,
	"rewards/concensus_correctness_reward_func": 0.9896249957382679,
	"rewards/consensus_reward_func": 1.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.6928683569421992,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.265625,
	"rewards/xmlcount_reward_func": 0.9945937469601631,
	"step": 10
	},
	{
	"completion_length": 123.5,
	"epoch": 3.0,
	"grad_norm": 221.9038848876953,
	"kl": 7.754779587810238,
	"learning_rate": 2.2935516363191693e-07,
	"loss": 0.0058,
	"reward": 5.002866193652153,
	"reward_std": 0.8892809633786479,
	"rewards/concensus_correctness_reward_func": 1.5877499878406525,
	"rewards/consensus_reward_func": 1.1666666666666667,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.16666666666666666,
	"rewards/question_recreation_reward_func": 0.7837411157476405,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.2708333333333333,
	"rewards/xmlcount_reward_func": 1.027208335697651,
	"step": 12
	},
	{
	"completion_length": 141.25,
	"epoch": 3.571428571428571,
	"grad_norm": 143.69752502441406,
	"kl": 15.431037136120722,
	"learning_rate": 1.4957614383675767e-07,
	"loss": 0.0154,
	"reward": 4.483005654066801,
	"reward_std": 1.070481608647242,
	"rewards/concensus_correctness_reward_func": 1.249812494032085,
	"rewards/consensus_reward_func": 1.0625,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.25,
	"rewards/question_recreation_reward_func": 0.6482555402908474,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.28125,
	"rewards/xmlcount_reward_func": 0.9911874998360872,
	"step": 14
	},
	{
	"completion_length": 111.625,
	"epoch": 4.0,
	"grad_norm": 69.18689727783203,
	"kl": 1.4936193202932675,
	"learning_rate": 8.067960709356478e-08,
	"loss": 0.0011,
	"reward": 4.76157025496165,
	"reward_std": 0.3775015217446101,
	"rewards/concensus_correctness_reward_func": 1.3215833256642024,
	"rewards/consensus_reward_func": 1.25,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.7950703254900873,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.3125,
	"rewards/xmlcount_reward_func": 1.0824166635672252,
	"step": 16
	},
	{
	"completion_length": 106.75,
	"epoch": 4.571428571428571,
	"grad_norm": 186.60618591308594,
	"kl": 2.3649307107552886,
	"learning_rate": 3.013156219837776e-08,
	"loss": 0.0024,
	"reward": 4.832870416343212,
	"reward_std": 0.8347923850524239,
	"rewards/concensus_correctness_reward_func": 1.4267499893903732,
	"rewards/consensus_reward_func": 1.1875,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.7312766302493401,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.3125,
	"rewards/xmlcount_reward_func": 1.0498437508940697,
	"step": 18
	},
	{
	"completion_length": 149.45833333333334,
	"epoch": 5.0,
	"grad_norm": 980.093017578125,
	"kl": 18.321802072227,
	"learning_rate": 3.4096741493194193e-09,
	"loss": 0.0137,
	"reward": 4.157890935738881,
	"reward_std": 0.9452465834910981,
	"rewards/concensus_correctness_reward_func": 1.1503333300352097,
	"rewards/consensus_reward_func": 0.9166666666666666,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.16666666666666666,
	"rewards/question_recreation_reward_func": 0.6799325756728649,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.2916666666666667,
	"rewards/xmlcount_reward_func": 0.9526249965031942,
	"step": 20
	},
	{
	"epoch": 5.0,
	"step": 20,
	"total_flos": 0.0,
	"train_loss": 0.08954811465227977,
	"train_runtime": 132.9611,
	"train_samples_per_second": 2.407,
	"train_steps_per_second": 0.15
	}
	],
	"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
	}