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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/albiandb/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-skittish_eager_squirrel

SGLang

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

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

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

albiandb

End of training

6ab4479 verified about 1 year ago

Raw

History Blame Contribute Delete

4.5 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 3.4,
	"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": 60.875,
	"epoch": 0.8,
	"grad_norm": 11.54460620880127,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": -0.0,
	"reward": 1.057928904891014,
	"reward_std": 0.4130301158875227,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.75,
	"rewards/question_recreation_reward_func": 0.22980391420423985,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.078125,
	"step": 2
	},
	{
	"completion_length": 46.0,
	"epoch": 1.4,
	"grad_norm": 20.20862579345703,
	"kl": 0.0006413682131096721,
	"learning_rate": 4.415111107797445e-07,
	"loss": 0.0,
	"reward": 2.403201421101888,
	"reward_std": 0.11947024613618851,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 2.0,
	"rewards/question_recreation_reward_func": 0.2782013813654582,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.125,
	"step": 4
	},
	{
	"completion_length": 65.33333333333333,
	"epoch": 2.0,
	"grad_norm": 7.1093010902404785,
	"kl": 0.003498752814872811,
	"learning_rate": 2.934120444167326e-07,
	"loss": 0.0,
	"reward": 0.9607302248477936,
	"reward_std": 0.028399634330223005,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.6666666666666666,
	"rewards/question_recreation_reward_func": 0.16906354576349258,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.125,
	"step": 6
	},
	{
	"completion_length": 53.625,
	"epoch": 2.8,
	"grad_norm": 18.270339965820312,
	"kl": 0.014321320282761008,
	"learning_rate": 1.2500000000000005e-07,
	"loss": 0.0,
	"reward": 1.302920363843441,
	"reward_std": 0.06874886981677264,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 1.0,
	"rewards/question_recreation_reward_func": 0.2091703936457634,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.09375,
	"step": 8
	},
	{
	"completion_length": 57.0,
	"epoch": 3.4,
	"grad_norm": 11.339275360107422,
	"kl": 0.014808982765922943,
	"learning_rate": 1.507684480352292e-08,
	"loss": 0.0,
	"reward": 1.7219081123669941,
	"reward_std": 0.02633840839068095,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 1.3333333333333333,
	"rewards/question_recreation_reward_func": 0.263574759165446,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.125,
	"step": 10
	},
	{
	"epoch": 3.4,
	"step": 10,
	"total_flos": 0.0,
	"train_loss": 5.096610766486265e-06,
	"train_runtime": 1640.2429,
	"train_samples_per_second": 0.024,
	"train_steps_per_second": 0.006
	}
	],
	"logging_steps": 2,
	"max_steps": 10,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 5,
	"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
	}