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

Libraries

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

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay")
model = AutoModelForCausalLM.from_pretrained("Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay

SGLang

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

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

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

Oberhaus

End of training

cb33b25 verified over 1 year ago

Raw History Blame

9.51 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 0.7407407407407407,
	"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": 50.0,
	"completions/max_terminated_length": 50.0,
	"completions/mean_length": 21.125,
	"completions/mean_terminated_length": 21.125,
	"completions/min_length": 4.0,
	"completions/min_terminated_length": 4.0,
	"epoch": 0.14814814814814814,
	"frac_reward_zero_std": 0.5,
	"grad_norm": 12.743616104125977,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": 0.0992,
	"num_tokens": 1193.0,
	"reward": 0.09130313247442245,
	"reward_std": 0.01168987131677568,
	"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": 0.09130313247442245,
	"rewards/question_recreation_reward_func/std": 0.013678928487934172,
	"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": 22.0,
	"completions/max_terminated_length": 22.0,
	"completions/mean_length": 12.375,
	"completions/mean_terminated_length": 12.375,
	"completions/min_length": 7.0,
	"completions/min_terminated_length": 7.0,
	"epoch": 0.2962962962962963,
	"frac_reward_zero_std": 0.5,
	"grad_norm": 43.35768508911133,
	"kl": 0.017325570806860924,
	"learning_rate": 4.415111107797445e-07,
	"loss": -0.1484,
	"num_tokens": 2316.0,
	"reward": 0.1280631353147328,
	"reward_std": 0.018915515393018723,
	"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": 0.1280631353147328,
	"rewards/question_recreation_reward_func/std": 0.018273787572979927,
	"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": 0.0,
	"completions/max_length": 19.5,
	"completions/max_terminated_length": 19.5,
	"completions/mean_length": 13.375,
	"completions/mean_terminated_length": 13.375,
	"completions/min_length": 6.5,
	"completions/min_terminated_length": 6.5,
	"epoch": 0.4444444444444444,
	"frac_reward_zero_std": 0.5,
	"grad_norm": 0.018915563821792603,
	"kl": 0.03074789233505726,
	"learning_rate": 2.934120444167326e-07,
	"loss": 0.0001,
	"num_tokens": 3447.0,
	"reward": 0.09580376278609037,
	"reward_std": 0.002759912982583046,
	"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": 0.09580376371741295,
	"rewards/question_recreation_reward_func/std": 0.002817572792991996,
	"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": 61.5,
	"completions/max_terminated_length": 61.5,
	"completions/mean_length": 29.375,
	"completions/mean_terminated_length": 29.375,
	"completions/min_length": 3.0,
	"completions/min_terminated_length": 3.0,
	"epoch": 0.5925925925925926,
	"frac_reward_zero_std": 0.25,
	"grad_norm": 36.02655792236328,
	"kl": 0.03904347028583288,
	"learning_rate": 1.2500000000000005e-07,
	"loss": 0.0023,
	"num_tokens": 4706.0,
	"reward": 0.01581350341439247,
	"reward_std": 0.008347119903191924,
	"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": 0.01581350341439247,
	"rewards/question_recreation_reward_func/std": 0.012281739618629217,
	"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": 18.0,
	"completions/max_terminated_length": 18.0,
	"completions/mean_length": 11.75,
	"completions/mean_terminated_length": 11.75,
	"completions/min_length": 4.5,
	"completions/min_terminated_length": 4.5,
	"epoch": 0.7407407407407407,
	"frac_reward_zero_std": 0.25,
	"grad_norm": 89.89861297607422,
	"kl": 0.04395892460888717,
	"learning_rate": 1.507684480352292e-08,
	"loss": 0.0962,
	"num_tokens": 5824.0,
	"reward": 0.5346636138856411,
	"reward_std": 0.6897922963835299,
	"rewards/concensus_correctness_reward_func/mean": 0.2395000010728836,
	"rewards/concensus_correctness_reward_func/std": 0.4790000319480896,
	"rewards/consensus_reward_func/mean": 0.25,
	"rewards/consensus_reward_func/std": 0.5,
	"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": 0.045163657516241074,
	"rewards/question_recreation_reward_func/std": 0.028757712803781033,
	"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": 0.7407407407407407,
	"step": 10,
	"total_flos": 0.0,
	"train_loss": 0.009888447250705212,
	"train_runtime": 625.0756,
	"train_samples_per_second": 0.064,
	"train_steps_per_second": 0.016
	}
	],
	"logging_steps": 2,
	"max_steps": 10,
	"num_input_tokens_seen": 5824,
	"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
	}