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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/jimons/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fanged_arctic_prawn

SGLang

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

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

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

jimons

End of training

4eb0c65 verified over 1 year ago

Raw

History Blame Contribute Delete

8.08 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 1.0,
	"eval_steps": 500,
	"global_step": 20,
	"is_hyper_param_search": false,
	"is_local_process_zero": true,
	"is_world_process_zero": true,
	"log_history": [
	{
	"completion_length": 158.59375,
	"epoch": 0.1,
	"grad_norm": 10.994775772094727,
	"kl": 0.0,
	"learning_rate": 4.965903258506806e-07,
	"loss": 0.0,
	"reward": 0.15987260814290494,
	"reward_std": 0.1004382234714285,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.09737260674592108,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.0,
	"step": 2
	},
	{
	"completion_length": 155.71875,
	"epoch": 0.2,
	"grad_norm": 15.824545860290527,
	"kl": 0.0005915943892205178,
	"learning_rate": 4.698684378016222e-07,
	"loss": 0.0,
	"reward": 0.197197389556095,
	"reward_std": 0.20802540019030857,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.0656348958145827,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.006562499795109034,
	"step": 4
	},
	{
	"completion_length": 89.34375,
	"epoch": 0.3,
	"grad_norm": 9.462965965270996,
	"kl": 0.002917701404385298,
	"learning_rate": 4.193203929064353e-07,
	"loss": 0.0,
	"reward": 0.11539923714008182,
	"reward_std": 0.037611501840729034,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.10883673781063408,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.006562499795109034,
	"step": 6
	},
	{
	"completion_length": 206.03125,
	"epoch": 0.4,
	"grad_norm": 5.41404390335083,
	"kl": 0.0024468189403705765,
	"learning_rate": 3.5042385616324236e-07,
	"loss": 0.0,
	"reward": 0.17654531029984355,
	"reward_std": 0.1492071510583628,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.1062328047119081,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.0078125,
	"step": 8
	},
	{
	"completion_length": 145.40625,
	"epoch": 0.5,
	"grad_norm": 10.185800552368164,
	"kl": 0.0034970568067365093,
	"learning_rate": 2.706448363680831e-07,
	"loss": 0.0,
	"reward": 0.10095155995804816,
	"reward_std": 0.02929924816635321,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.10095155995804816,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.0,
	"step": 10
	},
	{
	"completion_length": 109.09375,
	"epoch": 0.6,
	"grad_norm": 23.074642181396484,
	"kl": 0.032730046284996206,
	"learning_rate": 1.886286282148002e-07,
	"loss": 0.0,
	"reward": 0.13027076213620603,
	"reward_std": 0.04056345629214775,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.13027076213620603,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.0,
	"step": 12
	},
	{
	"completion_length": 191.46875,
	"epoch": 0.7,
	"grad_norm": 5.876796245574951,
	"kl": 0.005669093662618252,
	"learning_rate": 1.1326296046939333e-07,
	"loss": 0.0,
	"reward": 0.0862976847711252,
	"reward_std": 0.047334227681858465,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.10236018449359108,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.016062499955296516,
	"step": 14
	},
	{
	"completion_length": 80.75,
	"epoch": 0.8,
	"grad_norm": 13.765327453613281,
	"kl": 0.016974578695226228,
	"learning_rate": 5.271487265090163e-08,
	"loss": 0.0,
	"reward": 0.210471858328674,
	"reward_std": 0.1216582864508382,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.1446906128549017,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.003281249897554517,
	"step": 16
	},
	{
	"completion_length": 92.375,
	"epoch": 0.9,
	"grad_norm": 14.822056770324707,
	"kl": 0.010443305796798086,
	"learning_rate": 1.3545689574841341e-08,
	"loss": 0.0,
	"reward": 0.22659404878504574,
	"reward_std": 0.18330318277003244,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.1940940455533564,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.029999999329447746,
	"step": 18
	},
	{
	"completion_length": 163.0625,
	"epoch": 1.0,
	"grad_norm": 27.081457138061523,
	"kl": 0.012444959231743269,
	"learning_rate": 0.0,
	"loss": 0.0,
	"reward": 0.0902460323413834,
	"reward_std": 0.05573141352215316,
	"rewards/concensus_correctness_reward_func": 0.0,
	"rewards/consensus_reward_func": 0.0,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.0902460323413834,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.0,
	"step": 20
	},
	{
	"epoch": 1.0,
	"step": 20,
	"total_flos": 0.0,
	"train_loss": 8.742677027839819e-06,
	"train_runtime": 7708.1016,
	"train_samples_per_second": 0.042,
	"train_steps_per_second": 0.003
	}
	],
	"logging_steps": 2,
	"max_steps": 20,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 1,
	"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
	}