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

Libraries

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

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

pipe = pipeline("text-generation", model="Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel")
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("Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel")
model = AutoModelForCausalLM.from_pretrained("Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel", 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 Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel

SGLang

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

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

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

Slaughtering

End of training

e5a5d8b verified over 1 year ago

Raw History Blame

4.79 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 3.4705882352941178,
	"eval_steps": 500,
	"global_step": 10,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"completion_length": 255.71875,
	"epoch": 0.9411764705882353,
	"grad_norm": 3.487948179244995,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": 0.0,
	"reward": 5.0162065625190735,
	"reward_std": 1.0330485693411902,
	"rewards/concensus_correctness_reward_func": 1.684250008314848,
	"rewards/consensus_reward_func": 1.6875,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.7768628180492669,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.7425937540829182,
	"step": 2
	},
	{
	"completion_length": 213.16666666666666,
	"epoch": 1.4705882352941178,
	"grad_norm": 7.842313766479492,
	"kl": 0.002754828087442244,
	"learning_rate": 4.415111107797445e-07,
	"loss": 0.0,
	"reward": 4.477089087168376,
	"reward_std": 1.4975592299467988,
	"rewards/concensus_correctness_reward_func": 1.7086666756206088,
	"rewards/consensus_reward_func": 1.7777777777777777,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.6922002554767661,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.2984444366561042,
	"step": 4
	},
	{
	"completion_length": 168.61111111111111,
	"epoch": 2.0,
	"grad_norm": 1.6380842924118042,
	"kl": 0.0041018654462984866,
	"learning_rate": 2.934120444167326e-07,
	"loss": 0.0,
	"reward": 5.742938200632731,
	"reward_std": 0.21626100627084574,
	"rewards/concensus_correctness_reward_func": 2.0337777932484946,
	"rewards/consensus_reward_func": 2.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.2222222222222222,
	"rewards/question_recreation_reward_func": 0.7014382928609848,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.7854999932977889,
	"step": 6
	},
	{
	"completion_length": 150.03125,
	"epoch": 2.9411764705882355,
	"grad_norm": 3.3578732013702393,
	"kl": 0.008432783608441241,
	"learning_rate": 1.2500000000000005e-07,
	"loss": 0.0,
	"reward": 5.191920809447765,
	"reward_std": 0.6329880520643201,
	"rewards/concensus_correctness_reward_func": 1.9247500114142895,
	"rewards/consensus_reward_func": 1.9375,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.6802958373446018,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.5243750028312206,
	"step": 8
	},
	{
	"completion_length": 137.94444444444446,
	"epoch": 3.4705882352941178,
	"grad_norm": 3.12013840675354,
	"kl": 0.010559901181194518,
	"learning_rate": 1.507684480352292e-08,
	"loss": 0.0,
	"reward": 5.422543207804362,
	"reward_std": 0.5203664597744743,
	"rewards/concensus_correctness_reward_func": 2.0377777881092496,
	"rewards/consensus_reward_func": 1.8888888888888888,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.2222222222222222,
	"rewards/question_recreation_reward_func": 0.4938211246497101,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.7798333267370859,
	"step": 10
	},
	{
	"epoch": 3.4705882352941178,
	"step": 10,
	"total_flos": 0.0,
	"train_loss": 3.361709309501748e-06,
	"train_runtime": 12522.5432,
	"train_samples_per_second": 0.013,
	"train_steps_per_second": 0.001
	}
	],
	"logging_steps": 2,
	"max_steps": 10,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 5,
	"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
	}