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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Ertman/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-iridescent_tropical_starfish

SGLang

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

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

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

Ertman

End of training

025c6f7 verified about 1 year ago

Raw

History Blame

9.58 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.46511627906976744,
	"eval_steps": 500,
	"global_step": 10,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"clip_ratio/high_max": 0.0,
	"clip_ratio/high_mean": 0.0,
	"clip_ratio/low_mean": 0.0,
	"clip_ratio/low_min": 0.0,
	"clip_ratio/region_mean": 0.0,
	"completions/clipped_ratio": 0.0,
	"completions/max_length": 102.5,
	"completions/max_terminated_length": 102.5,
	"completions/mean_length": 46.5,
	"completions/mean_terminated_length": 46.5,
	"completions/min_length": 17.0,
	"completions/min_terminated_length": 17.0,
	"epoch": 0.09302325581395349,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 26.819913864135742,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": 0.1038,
	"num_tokens": 1396.0,
	"reward": 0.03198886290192604,
	"reward_std": 0.010370630770921707,
	"rewards/concensus_correctness_reward_func/mean": 0.0,
	"rewards/concensus_correctness_reward_func/std": 0.0,
	"rewards/consensus_reward_func/mean": 0.0,
	"rewards/consensus_reward_func/std": 0.0,
	"rewards/cumulative_reward_2/mean": 0.0,
	"rewards/cumulative_reward_2/std": 0.0,
	"rewards/final_correctness_reward_func/mean": 0.0,
	"rewards/final_correctness_reward_func/std": 0.0,
	"rewards/question_recreation_reward_func/mean": 0.03198886290192604,
	"rewards/question_recreation_reward_func/std": 0.011841414961963892,
	"rewards/soft_format_reward_func/mean": 0.0,
	"rewards/soft_format_reward_func/std": 0.0,
	"rewards/strict_format_reward_func/mean": 0.0,
	"rewards/strict_format_reward_func/std": 0.0,
	"rewards/xmlcount_reward_func/mean": 0.0,
	"rewards/xmlcount_reward_func/std": 0.0,
	"step": 2
	},
	{
	"clip_ratio/high_max": 0.0,
	"clip_ratio/high_mean": 0.0,
	"clip_ratio/low_mean": 0.0,
	"clip_ratio/low_min": 0.0,
	"clip_ratio/region_mean": 0.0,
	"completions/clipped_ratio": 0.0,
	"completions/max_length": 31.5,
	"completions/max_terminated_length": 31.5,
	"completions/mean_length": 22.375,
	"completions/mean_terminated_length": 22.375,
	"completions/min_length": 16.0,
	"completions/min_terminated_length": 16.0,
	"epoch": 0.18604651162790697,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 47.122337341308594,
	"kl": 0.009030564804561436,
	"learning_rate": 4.415111107797445e-07,
	"loss": 0.0182,
	"num_tokens": 2599.0,
	"reward": 0.04082147125154734,
	"reward_std": 0.016715965699404478,
	"rewards/concensus_correctness_reward_func/mean": 0.0,
	"rewards/concensus_correctness_reward_func/std": 0.0,
	"rewards/consensus_reward_func/mean": 0.0,
	"rewards/consensus_reward_func/std": 0.0,
	"rewards/cumulative_reward_2/mean": 0.0,
	"rewards/cumulative_reward_2/std": 0.0,
	"rewards/final_correctness_reward_func/mean": 0.0,
	"rewards/final_correctness_reward_func/std": 0.0,
	"rewards/question_recreation_reward_func/mean": 0.04082146845757961,
	"rewards/question_recreation_reward_func/std": 0.026838398072868586,
	"rewards/soft_format_reward_func/mean": 0.0,
	"rewards/soft_format_reward_func/std": 0.0,
	"rewards/strict_format_reward_func/mean": 0.0,
	"rewards/strict_format_reward_func/std": 0.0,
	"rewards/xmlcount_reward_func/mean": 0.0,
	"rewards/xmlcount_reward_func/std": 0.0,
	"step": 4
	},
	{
	"clip_ratio/high_max": 0.0,
	"clip_ratio/high_mean": 0.0,
	"clip_ratio/low_mean": 0.0,
	"clip_ratio/low_min": 0.0,
	"clip_ratio/region_mean": 0.0,
	"completions/clipped_ratio": 0.125,
	"completions/max_length": 183.0,
	"completions/max_terminated_length": 148.5,
	"completions/mean_length": 90.25,
	"completions/mean_terminated_length": 70.16666793823242,
	"completions/min_length": 14.0,
	"completions/min_terminated_length": 14.0,
	"epoch": 0.27906976744186046,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 70.61158752441406,
	"kl": 0.014445176813751459,
	"learning_rate": 2.934120444167326e-07,
	"loss": -0.0519,
	"num_tokens": 4345.0,
	"reward": 0.02797679416835308,
	"reward_std": 0.005366061115637422,
	"rewards/concensus_correctness_reward_func/mean": 0.0,
	"rewards/concensus_correctness_reward_func/std": 0.0,
	"rewards/consensus_reward_func/mean": 0.0,
	"rewards/consensus_reward_func/std": 0.0,
	"rewards/cumulative_reward_2/mean": 0.0,
	"rewards/cumulative_reward_2/std": 0.0,
	"rewards/final_correctness_reward_func/mean": 0.0,
	"rewards/final_correctness_reward_func/std": 0.0,
	"rewards/question_recreation_reward_func/mean": 0.02797679416835308,
	"rewards/question_recreation_reward_func/std": 0.016844000667333603,
	"rewards/soft_format_reward_func/mean": 0.0,
	"rewards/soft_format_reward_func/std": 0.0,
	"rewards/strict_format_reward_func/mean": 0.0,
	"rewards/strict_format_reward_func/std": 0.0,
	"rewards/xmlcount_reward_func/mean": 0.0,
	"rewards/xmlcount_reward_func/std": 0.0,
	"step": 6
	},
	{
	"clip_ratio/high_max": 0.0,
	"clip_ratio/high_mean": 0.0,
	"clip_ratio/low_mean": 0.0,
	"clip_ratio/low_min": 0.0,
	"clip_ratio/region_mean": 0.0,
	"completions/clipped_ratio": 0.0,
	"completions/max_length": 35.0,
	"completions/max_terminated_length": 35.0,
	"completions/mean_length": 14.125,
	"completions/mean_terminated_length": 14.125,
	"completions/min_length": 4.0,
	"completions/min_terminated_length": 4.0,
	"epoch": 0.37209302325581395,
	"frac_reward_zero_std": 0.5,
	"grad_norm": 84.35356140136719,
	"kl": 0.05594382411800325,
	"learning_rate": 1.2500000000000005e-07,
	"loss": 0.0779,
	"num_tokens": 5482.0,
	"reward": 1.4956446290016174,
	"reward_std": 0.6916476492770016,
	"rewards/concensus_correctness_reward_func/mean": 0.7199999988079071,
	"rewards/concensus_correctness_reward_func/std": 1.0334109663963318,
	"rewards/consensus_reward_func/mean": 0.75,
	"rewards/consensus_reward_func/std": 1.0773502588272095,
	"rewards/cumulative_reward_2/mean": 0.0,
	"rewards/cumulative_reward_2/std": 0.0,
	"rewards/final_correctness_reward_func/mean": 0.0,
	"rewards/final_correctness_reward_func/std": 0.0,
	"rewards/question_recreation_reward_func/mean": 0.025644690729677677,
	"rewards/question_recreation_reward_func/std": 0.016321994364261627,
	"rewards/soft_format_reward_func/mean": 0.0,
	"rewards/soft_format_reward_func/std": 0.0,
	"rewards/strict_format_reward_func/mean": 0.0,
	"rewards/strict_format_reward_func/std": 0.0,
	"rewards/xmlcount_reward_func/mean": 0.0,
	"rewards/xmlcount_reward_func/std": 0.0,
	"step": 8
	},
	{
	"clip_ratio/high_max": 0.0,
	"clip_ratio/high_mean": 0.0,
	"clip_ratio/low_mean": 0.0,
	"clip_ratio/low_min": 0.0,
	"clip_ratio/region_mean": 0.0,
	"completions/clipped_ratio": 0.0,
	"completions/max_length": 47.0,
	"completions/max_terminated_length": 47.0,
	"completions/mean_length": 22.375,
	"completions/mean_terminated_length": 22.375,
	"completions/min_length": 4.5,
	"completions/min_terminated_length": 4.5,
	"epoch": 0.46511627906976744,
	"frac_reward_zero_std": 0.5,
	"grad_norm": 39.63914489746094,
	"kl": 0.015579930739477277,
	"learning_rate": 1.507684480352292e-08,
	"loss": 0.0031,
	"num_tokens": 6685.0,
	"reward": 0.7941031903028488,
	"reward_std": 0.02715550092398189,
	"rewards/concensus_correctness_reward_func/mean": 0.7120000123977661,
	"rewards/concensus_correctness_reward_func/std": 0.8221468329429626,
	"rewards/consensus_reward_func/mean": 0.0,
	"rewards/consensus_reward_func/std": 0.0,
	"rewards/cumulative_reward_2/mean": 0.0,
	"rewards/cumulative_reward_2/std": 0.0,
	"rewards/final_correctness_reward_func/mean": 0.0,
	"rewards/final_correctness_reward_func/std": 0.0,
	"rewards/question_recreation_reward_func/mean": 0.08210319094359875,
	"rewards/question_recreation_reward_func/std": 0.056017409078776836,
	"rewards/soft_format_reward_func/mean": 0.0,
	"rewards/soft_format_reward_func/std": 0.0,
	"rewards/strict_format_reward_func/mean": 0.0,
	"rewards/strict_format_reward_func/std": 0.0,
	"rewards/xmlcount_reward_func/mean": 0.0,
	"rewards/xmlcount_reward_func/std": 0.0,
	"step": 10
	},
	{
	"epoch": 0.46511627906976744,
	"step": 10,
	"total_flos": 0.0,
	"train_loss": 0.030200545489788056,
	"train_runtime": 708.4645,
	"train_samples_per_second": 0.056,
	"train_steps_per_second": 0.014
	}
	],
	"logging_steps": 2,
	"max_steps": 10,
	"num_input_tokens_seen": 6685,
	"num_train_epochs": 1,
	"save_steps": 10,
	"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
	}