Instructions to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with Transformers:

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

pipe = pipeline("text-generation", model="0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee")
model = AutoModelForCausalLM.from_pretrained("0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee

SGLang

How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee 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 "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee" \
    --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": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"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 "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee" \
        --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": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with Docker Model Runner:
```
docker model run hf.co/0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee
```

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

0xOzii

End of training

6c9cac6 verified over 1 year ago

Raw

History Blame Contribute Delete

8.42 kB

	{
	"best_global_step": null,
	"best_metric": null,
	"best_model_checkpoint": null,
	"epoch": 5.0,
	"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": 223.71875,
	"epoch": 0.5714285714285714,
	"grad_norm": 31.614778518676758,
	"kl": 0.0,
	"learning_rate": 5e-07,
	"loss": -0.0,
	"reward": 2.9653216637670994,
	"reward_std": 1.4805789864331018,
	"rewards/concensus_correctness_reward_func": 0.4098124969750643,
	"rewards/consensus_reward_func": 0.625,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.7164467088878155,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.203125,
	"rewards/xmlcount_reward_func": 0.9484374951571226,
	"step": 2
	},
	{
	"completion_length": 151.20833333333334,
	"epoch": 1.0,
	"grad_norm": 19.80303192138672,
	"kl": 0.10296421435972054,
	"learning_rate": 4.864543104251586e-07,
	"loss": 0.0001,
	"reward": 5.499126513799031,
	"reward_std": 0.53629773731033,
	"rewards/concensus_correctness_reward_func": 1.334166665871938,
	"rewards/consensus_reward_func": 1.75,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.8379182033240795,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.3958333333333333,
	"rewards/xmlcount_reward_func": 1.181208332379659,
	"step": 4
	},
	{
	"completion_length": 143.59375,
	"epoch": 1.5714285714285714,
	"grad_norm": 34.6270751953125,
	"kl": 2.8533220877870917,
	"learning_rate": 4.472851273490984e-07,
	"loss": 0.0029,
	"reward": 5.050898350775242,
	"reward_std": 1.3527698878897354,
	"rewards/concensus_correctness_reward_func": 1.2711875047534704,
	"rewards/consensus_reward_func": 1.25,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.7718983719823882,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.421875,
	"rewards/xmlcount_reward_func": 1.2109375,
	"step": 6
	},
	{
	"completion_length": 160.66666666666666,
	"epoch": 2.0,
	"grad_norm": 15.381648063659668,
	"kl": 11.692268824204803,
	"learning_rate": 3.867370395306068e-07,
	"loss": 0.0088,
	"reward": 4.899051864941915,
	"reward_std": 0.8737152467171351,
	"rewards/concensus_correctness_reward_func": 0.8280833214521408,
	"rewards/consensus_reward_func": 1.5,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.8834685583909353,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.4375,
	"rewards/xmlcount_reward_func": 1.25,
	"step": 8
	},
	{
	"completion_length": 171.3125,
	"epoch": 2.571428571428571,
	"grad_norm": 1969201920.0,
	"kl": 55716476.06210626,
	"learning_rate": 3.1137137178519977e-07,
	"loss": 55716.4805,
	"reward": 4.228640131652355,
	"reward_std": 0.9665384208783507,
	"rewards/concensus_correctness_reward_func": 0.6550625003874302,
	"rewards/consensus_reward_func": 0.9375,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.125,
	"rewards/question_recreation_reward_func": 0.886077631264925,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.375,
	"rewards/xmlcount_reward_func": 1.25,
	"step": 10
	},
	{
	"completion_length": 160.875,
	"epoch": 3.0,
	"grad_norm": 15.754578590393066,
	"kl": 34.520431245987616,
	"learning_rate": 2.2935516363191693e-07,
	"loss": 0.0259,
	"reward": 4.905407538016637,
	"reward_std": 0.4380470165245545,
	"rewards/concensus_correctness_reward_func": 1.046166663368543,
	"rewards/consensus_reward_func": 1.4166666666666667,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.859240879615148,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.375,
	"rewards/xmlcount_reward_func": 1.2083333333333333,
	"step": 12
	},
	{
	"completion_length": 173.03125,
	"epoch": 3.571428571428571,
	"grad_norm": 43.54138946533203,
	"kl": 788.5391242853366,
	"learning_rate": 1.4957614383675767e-07,
	"loss": 0.7885,
	"reward": 4.416811063885689,
	"reward_std": 1.3936654469143832,
	"rewards/concensus_correctness_reward_func": 0.8432500008493662,
	"rewards/consensus_reward_func": 1.1875,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.8274673502892256,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.34375,
	"rewards/xmlcount_reward_func": 1.21484375,
	"step": 14
	},
	{
	"completion_length": 165.16666666666666,
	"epoch": 4.0,
	"grad_norm": 25.31414031982422,
	"kl": 6.561875412861506,
	"learning_rate": 8.067960709356478e-08,
	"loss": 0.0049,
	"reward": 4.753732244173686,
	"reward_std": 1.579458454468598,
	"rewards/concensus_correctness_reward_func": 1.0581666653354962,
	"rewards/consensus_reward_func": 1.0833333333333333,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.08333333333333333,
	"rewards/question_recreation_reward_func": 0.9195239692926407,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.375,
	"rewards/xmlcount_reward_func": 1.234375,
	"step": 16
	},
	{
	"completion_length": 158.78125,
	"epoch": 4.571428571428571,
	"grad_norm": 25.638328552246094,
	"kl": 15.994928859174252,
	"learning_rate": 3.013156219837776e-08,
	"loss": 0.016,
	"reward": 4.85489359498024,
	"reward_std": 1.2258785646408796,
	"rewards/concensus_correctness_reward_func": 1.0678125005215406,
	"rewards/consensus_reward_func": 1.375,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.8339561484754086,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.390625,
	"rewards/xmlcount_reward_func": 1.1875,
	"step": 18
	},
	{
	"completion_length": 162.125,
	"epoch": 5.0,
	"grad_norm": 18.205522537231445,
	"kl": 11.792570936183134,
	"learning_rate": 3.4096741493194193e-09,
	"loss": 0.0088,
	"reward": 4.547471563021342,
	"reward_std": 0.43150439858436584,
	"rewards/concensus_correctness_reward_func": 0.9048333416382471,
	"rewards/consensus_reward_func": 0.9166666666666666,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.16666666666666666,
	"rewards/question_recreation_reward_func": 0.9553049008051554,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.375,
	"rewards/xmlcount_reward_func": 1.2290000021457672,
	"step": 20
	},
	{
	"epoch": 5.0,
	"step": 20,
	"total_flos": 0.0,
	"train_loss": 5571.733635760998,
	"train_runtime": 105.8429,
	"train_samples_per_second": 3.023,
	"train_steps_per_second": 0.189
	}
	],
	"logging_steps": 2,
	"max_steps": 20,
	"num_input_tokens_seen": 0,
	"num_train_epochs": 7,
	"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
	}