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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Cchaos/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-climbing_crested_condor

SGLang

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

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

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

Cchaos

End of training

3bb9cae verified over 1 year ago

Raw

History Blame Contribute Delete

8.28 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": 159.53125,
	"epoch": 0.1,
	"grad_norm": 42.64451599121094,
	"kl": 0.0,
	"learning_rate": 4.965903258506806e-07,
	"loss": 0.0,
	"reward": 0.2750730898696929,
	"reward_std": 0.33796203549718484,
	"rewards/concensus_correctness_reward_func": 0.06018749997019768,
	"rewards/consensus_reward_func": 0.0625,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.12097934319172055,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.031093750149011612,
	"step": 2
	},
	{
	"completion_length": 129.5,
	"epoch": 0.2,
	"grad_norm": 33.4676628112793,
	"kl": 0.0017403407077836164,
	"learning_rate": 4.698684378016222e-07,
	"loss": 0.0,
	"reward": 0.08828154078219086,
	"reward_std": 0.09351343158414238,
	"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": 0.11493779090233147,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.026656249538064003,
	"step": 4
	},
	{
	"completion_length": 156.6875,
	"epoch": 0.3,
	"grad_norm": 23.76153564453125,
	"kl": 0.016077187114206026,
	"learning_rate": 4.193203929064353e-07,
	"loss": 0.0,
	"reward": 0.20646477834088728,
	"reward_std": 0.22474737564334646,
	"rewards/concensus_correctness_reward_func": 0.05999999865889549,
	"rewards/consensus_reward_func": 0.0625,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.0922772788326256,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.008312500081956387,
	"step": 6
	},
	{
	"completion_length": 140.78125,
	"epoch": 0.4,
	"grad_norm": 17.65758514404297,
	"kl": 0.009867031902103918,
	"learning_rate": 3.5042385616324236e-07,
	"loss": 0.0,
	"reward": 0.33196004456840456,
	"reward_std": 0.34907107069011545,
	"rewards/concensus_correctness_reward_func": 0.07918750122189522,
	"rewards/consensus_reward_func": 0.125,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.1137725441949442,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.013999999966472387,
	"step": 8
	},
	{
	"completion_length": 188.21875,
	"epoch": 0.5,
	"grad_norm": 11.617631912231445,
	"kl": 0.00979025863125571,
	"learning_rate": 2.706448363680831e-07,
	"loss": 0.0,
	"reward": 0.30701479013077915,
	"reward_std": 0.3836260371335811,
	"rewards/concensus_correctness_reward_func": 0.051750000566244125,
	"rewards/consensus_reward_func": 0.0625,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0625,
	"rewards/question_recreation_reward_func": 0.1222335389466025,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.008031250443309546,
	"step": 10
	},
	{
	"completion_length": 158.5,
	"epoch": 0.6,
	"grad_norm": 10.506937980651855,
	"kl": 0.015619799527485156,
	"learning_rate": 1.886286282148002e-07,
	"loss": 0.0,
	"reward": 0.3158440781990066,
	"reward_std": 0.09872026408629608,
	"rewards/concensus_correctness_reward_func": 0.11999999731779099,
	"rewards/consensus_reward_func": 0.125,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.10565658047562465,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.03481250139884651,
	"step": 12
	},
	{
	"completion_length": 173.8125,
	"epoch": 0.7,
	"grad_norm": 5.180370330810547,
	"kl": 0.015626165712092188,
	"learning_rate": 1.1326296046939333e-07,
	"loss": 0.0,
	"reward": 0.33155799441738054,
	"reward_std": 0.31527659608400427,
	"rewards/concensus_correctness_reward_func": 0.07293750066310167,
	"rewards/consensus_reward_func": 0.125,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.11968300043372437,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.013937500305473804,
	"step": 14
	},
	{
	"completion_length": 138.34375,
	"epoch": 0.8,
	"grad_norm": 12.473709106445312,
	"kl": 0.029021206886682194,
	"learning_rate": 5.271487265090163e-08,
	"loss": 0.0,
	"reward": 0.6483697192743421,
	"reward_std": 0.21503988321637735,
	"rewards/concensus_correctness_reward_func": 0.3017500005662441,
	"rewards/consensus_reward_func": 0.1875,
	"rewards/cumulative_reward_2": 0.0,
	"rewards/final_correctness_reward_func": 0.0,
	"rewards/question_recreation_reward_func": 0.1563384763430804,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": 0.002781250048428774,
	"step": 16
	},
	{
	"completion_length": 176.5625,
	"epoch": 0.9,
	"grad_norm": 10.102160453796387,
	"kl": 0.007534470460086595,
	"learning_rate": 1.3545689574841341e-08,
	"loss": 0.0,
	"reward": 0.14994344190927222,
	"reward_std": 0.15157496054234798,
	"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": 0.12247469584690407,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.03503125044517219,
	"step": 18
	},
	{
	"completion_length": 173.1875,
	"epoch": 1.0,
	"grad_norm": 7.306704998016357,
	"kl": 0.006795531931857113,
	"learning_rate": 0.0,
	"loss": 0.0,
	"reward": 0.1505529017886147,
	"reward_std": 0.1496142033720389,
	"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": 0.13749039953108877,
	"rewards/soft_format_reward_func": 0.0,
	"rewards/strict_format_reward_func": 0.0,
	"rewards/xmlcount_reward_func": -0.0494375005364418,
	"step": 20
	},
	{
	"epoch": 1.0,
	"step": 20,
	"total_flos": 0.0,
	"train_loss": 1.1270371521732158e-05,
	"train_runtime": 15994.6068,
	"train_samples_per_second": 0.02,
	"train_steps_per_second": 0.001
	}
	],
	"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
	}