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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda

SGLang

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

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

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

Biondovi

End of training

ccdc588 verified over 1 year ago

Raw History Blame Contribute Delete

9.65 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.43478260869565216,
	"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": 58.5,
	"completions/max_terminated_length": 58.5,
	"completions/mean_length": 36.625,
	"completions/mean_terminated_length": 36.625,
	"completions/min_length": 20.5,
	"completions/min_terminated_length": 20.5,
	"epoch": 0.08695652173913043,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 42.607154846191406,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": 0.104,
	"num_tokens": 1317.0,
	"reward": 0.2697029113769531,
	"reward_std": 0.06398913823068142,
	"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": 0.009077915921807289,
	"rewards/question_recreation_reward_func/std": 0.009524198016151786,
	"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": 0.2606250084936619,
	"rewards/xmlcount_reward_func/std": 0.10797951556742191,
	"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": 97.0,
	"completions/max_terminated_length": 97.0,
	"completions/mean_length": 46.625,
	"completions/mean_terminated_length": 46.625,
	"completions/min_length": 23.0,
	"completions/min_terminated_length": 23.0,
	"epoch": 0.17391304347826086,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 72.13888549804688,
	"kl": 0.016350419347872958,
	"learning_rate": 4.415111107797445e-07,
	"loss": 0.0001,
	"num_tokens": 2714.0,
	"reward": 0.3842458426952362,
	"reward_std": 0.1307172253727913,
	"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": 0.08724584802985191,
	"rewards/question_recreation_reward_func/std": 0.02099667303264141,
	"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": 0.296999990940094,
	"rewards/xmlcount_reward_func/std": 0.12750041857361794,
	"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": 0.0,
	"completions/max_length": 34.5,
	"completions/max_terminated_length": 34.5,
	"completions/mean_length": 26.875,
	"completions/mean_terminated_length": 26.875,
	"completions/min_length": 20.0,
	"completions/min_terminated_length": 20.0,
	"epoch": 0.2608695652173913,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 40.991939544677734,
	"kl": 0.05134714557789266,
	"learning_rate": 2.934120444167326e-07,
	"loss": 0.0068,
	"num_tokens": 3953.0,
	"reward": 0.39916859567165375,
	"reward_std": 0.056330110877752304,
	"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": 0.004543595423456281,
	"rewards/question_recreation_reward_func/std": 0.009087190846912563,
	"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": 0.3946250081062317,
	"rewards/xmlcount_reward_func/std": 0.055458297953009605,
	"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": 117.5,
	"completions/max_terminated_length": 117.5,
	"completions/mean_length": 47.5,
	"completions/mean_terminated_length": 47.5,
	"completions/min_length": 18.5,
	"completions/min_terminated_length": 18.5,
	"epoch": 0.34782608695652173,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 39.77725601196289,
	"kl": 0.0206502788932994,
	"learning_rate": 1.2500000000000005e-07,
	"loss": 0.2759,
	"num_tokens": 5357.0,
	"reward": 0.5431624054908752,
	"reward_std": 0.4544815495610237,
	"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": 0.25,
	"rewards/final_correctness_reward_func/std": 0.5,
	"rewards/question_recreation_reward_func/mean": 0.024537368677556515,
	"rewards/question_recreation_reward_func/std": 0.018834506161510944,
	"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": 0.26862500607967377,
	"rewards/xmlcount_reward_func/std": 0.13356759771704674,
	"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": 47.5,
	"completions/max_terminated_length": 47.5,
	"completions/mean_length": 27.875,
	"completions/mean_terminated_length": 27.875,
	"completions/min_length": 20.0,
	"completions/min_terminated_length": 20.0,
	"epoch": 0.43478260869565216,
	"frac_reward_zero_std": 0.0,
	"grad_norm": 69.54534149169922,
	"kl": 0.023991694557480514,
	"learning_rate": 1.507684480352292e-08,
	"loss": 0.0467,
	"num_tokens": 6604.0,
	"reward": 1.1605660021305084,
	"reward_std": 0.4542441703379154,
	"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": 0.75,
	"rewards/final_correctness_reward_func/std": 1.0773502588272095,
	"rewards/question_recreation_reward_func/mean": 0.06994102522730827,
	"rewards/question_recreation_reward_func/std": 0.02063577761873603,
	"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": 0.34062498807907104,
	"rewards/xmlcount_reward_func/std": 0.11164618656039238,
	"step": 10
	},
	{
	"epoch": 0.43478260869565216,
	"step": 10,
	"total_flos": 0.0,
	"train_loss": 0.08669190295040607,
	"train_runtime": 717.6828,
	"train_samples_per_second": 0.056,
	"train_steps_per_second": 0.014
	}
	],
	"logging_steps": 2,
	"max_steps": 10,
	"num_input_tokens_seen": 6604,
	"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
	}