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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_hulking_shrew

SGLang

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

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

xaobai commited on Apr 11, 2025

Commit

94c480e

verified ·

1 Parent(s): 0d51352

End of training

Browse files

Files changed (4) hide show

all_results.json +4 -4
model.safetensors +1 -1
train_results.json +4 -4
trainer_state.json +91 -91

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.8831884264945986e-06,
-    "train_runtime": 321.1862,
     "train_samples": 28,
-    "train_samples_per_second": 0.996,
-    "train_steps_per_second": 0.062
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.235096275806427e-06,
+    "train_runtime": 305.2825,
     "train_samples": 28,
+    "train_samples_per_second": 1.048,
+    "train_steps_per_second": 0.066
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e183340ed8ed52e81ea049a32530dfcd6b600859ed2ca8faa4857d8006fbc118
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:d622b9ccdf411ac22ac8cc7c3f917b9b19a792c6c4a2f6a85eb8f8d51aaa2515
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 2.8831884264945986e-06,
-    "train_runtime": 321.1862,
     "train_samples": 28,
-    "train_samples_per_second": 0.996,
-    "train_steps_per_second": 0.062
 }

 {
     "total_flos": 0.0,
+    "train_loss": 4.235096275806427e-06,
+    "train_runtime": 305.2825,
     "train_samples": 28,
+    "train_samples_per_second": 1.048,
+    "train_steps_per_second": 0.066
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 460.25,
       "epoch": 0.5714285714285714,
-      "grad_norm": 8.145787239074707,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.0,
-      "reward": 0.5769589798292145,
-      "reward_std": 0.5029744083003607,
       "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": 0.3631777291884646,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2137812494765967,
       "step": 2
     },
     {
-      "completion_length": 465.6666666666667,
       "epoch": 1.0,
-      "grad_norm": 5.695125102996826,
-      "kl": 0.00203544043082123,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 0.7484609962751468,
-      "reward_std": 0.8892306635777155,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.16666666666666666,
-      "rewards/question_recreation_reward_func": 0.3487526588141918,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.23304166520635286,
       "step": 4
     },
     {
-      "completion_length": 435.0625,
       "epoch": 1.5714285714285714,
-      "grad_norm": 128.2107696533203,
-      "kl": 0.0025215414807462366,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 0.09904030775942374,
-      "reward_std": 0.748617625591578,
-      "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": 0.24341530133096967,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.2224999968893826,
       "step": 6
     },
     {
-      "completion_length": 547.4166666666666,
       "epoch": 2.0,
-      "grad_norm": 3.181215524673462,
-      "kl": 0.001443970463393877,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
-      "reward": 0.5557474804421266,
-      "reward_std": 0.9948170799762011,
-      "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.377622480407202,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.09479165822267532,
       "step": 8
     },
     {
-      "completion_length": 411.25,
       "epoch": 2.571428571428571,
-      "grad_norm": 34.44321060180664,
-      "kl": 0.002047349447821034,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
-      "reward": 0.30374075239524245,
-      "reward_std": 0.3811396125238389,
       "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": 0.13608450882020406,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.16765625029802322,
       "step": 10
     },
     {
-      "completion_length": 396.3333333333333,
       "epoch": 3.0,
-      "grad_norm": 4.588991165161133,
-      "kl": 0.0028088390439127884,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
-      "reward": 0.6483861189335585,
-      "reward_std": 0.5188679856558641,
-      "rewards/concensus_correctness_reward_func": 0.041666666666666664,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.36321946295599145,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.16016666063417992,
       "step": 12
     },
     {
-      "completion_length": 417.34375,
       "epoch": 3.571428571428571,
-      "grad_norm": 5.519042491912842,
-      "kl": 0.005811016399093205,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
-      "reward": 0.625898445956409,
-      "reward_std": 1.1080984161235392,
-      "rewards/concensus_correctness_reward_func": 0.03412500023841858,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.46202343376353383,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.0733750038780272,
       "step": 14
     },
     {
-      "completion_length": 414.5416666666667,
       "epoch": 4.0,
-      "grad_norm": 8.085697174072266,
-      "kl": 0.0025997629078725972,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
-      "reward": 0.6545891736944517,
-      "reward_std": 0.7784566836586843,
-      "rewards/concensus_correctness_reward_func": 0.024333332975705464,
-      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.23488083481788635,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2287083345775803,
       "step": 16
     },
     {
-      "completion_length": 367.15625,
       "epoch": 4.571428571428571,
-      "grad_norm": 5.562610149383545,
-      "kl": 0.0063671202879049815,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
-      "reward": 0.6448051813058555,
-      "reward_std": 0.4576542386203073,
-      "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": 0.36211768235079944,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2826874984893948,
       "step": 18
     },
     {
-      "completion_length": 368.1666666666667,
       "epoch": 5.0,
-      "grad_norm": 50.179561614990234,
-      "kl": 0.006806447321044591,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
-      "reward": 0.28496329362193745,
-      "reward_std": 0.4717485976095001,
       "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": 0.4522966348255674,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.167333343376716,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 2.8831884264945986e-06,
-      "train_runtime": 321.1862,
-      "train_samples_per_second": 0.996,
-      "train_steps_per_second": 0.062
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 333.71875,
       "epoch": 0.5714285714285714,
+      "grad_norm": 8.716035842895508,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": -0.0,
+      "reward": 0.6000244622118771,
+      "reward_std": 0.5127546100484324,
       "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": 0.4123369613662362,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18768750131130219,
       "step": 2
     },
     {
+      "completion_length": 389.75,
       "epoch": 1.0,
+      "grad_norm": 3.642230987548828,
+      "kl": 0.0010912369568056117,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 0.28384447245237726,
+      "reward_std": 0.49865033632765215,
       "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": 0.23167781718075275,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.052166664972901344,
       "step": 4
     },
     {
+      "completion_length": 417.5,
       "epoch": 1.5714285714285714,
+      "grad_norm": 7.316373825073242,
+      "kl": 0.0022729315041942755,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 0.3090596494730562,
+      "reward_std": 0.7388703430769965,
+      "rewards/concensus_correctness_reward_func": 0.025750000029802322,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.40930966450832784,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.18850000482052565,
       "step": 6
     },
     {
+      "completion_length": 365.2083333333333,
       "epoch": 2.0,
+      "grad_norm": 5.989852428436279,
+      "kl": 0.002178182010538876,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 0.6400048338497678,
+      "reward_std": 0.5366769605316222,
+      "rewards/concensus_correctness_reward_func": 0.026249999801317852,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.35033816068122786,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18008332575360933,
       "step": 8
     },
     {
+      "completion_length": 367.71875,
       "epoch": 2.571428571428571,
+      "grad_norm": 5.3512773513793945,
+      "kl": 0.002255434766993858,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 0.5805878184037283,
+      "reward_std": 0.6734246980631724,
       "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": 0.37505657062865794,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.1742812478914857,
       "step": 10
     },
     {
+      "completion_length": 386.7083333333333,
       "epoch": 3.0,
+      "grad_norm": 5.522129535675049,
+      "kl": 0.0037184827281938246,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
+      "reward": 0.1442863984654347,
+      "reward_std": 0.43704667780548334,
+      "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": 0.2309113945811987,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.0866249967366457,
       "step": 12
     },
     {
+      "completion_length": 381.84375,
       "epoch": 3.571428571428571,
+      "grad_norm": 47.56230926513672,
+      "kl": 0.015617469740391243,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": 1.336521113757044,
+      "reward_std": 1.4042669633490732,
+      "rewards/concensus_correctness_reward_func": 0.625,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.31658362364396453,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.26993750035762787,
       "step": 14
     },
     {
+      "completion_length": 536.625,
       "epoch": 4.0,
+      "grad_norm": 2.141207456588745,
+      "kl": 0.0030050037554853284,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 0.321597548512121,
+      "reward_std": 0.9716614107601345,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.34909753625591594,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.11083333070079486,
       "step": 16
     },
     {
+      "completion_length": 378.65625,
       "epoch": 4.571428571428571,
+      "grad_norm": 3.662749767303467,
+      "kl": 0.008682570693054004,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
+      "reward": 0.6588729335926473,
+      "reward_std": 0.4257765415823087,
+      "rewards/concensus_correctness_reward_func": 0.019687499850988388,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.42031042685266584,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 0.20325000025331974,
       "step": 18
     },
     {
+      "completion_length": 428.9583333333333,
       "epoch": 5.0,
+      "grad_norm": 2.5166842937469482,
+      "kl": 0.003367605541522304,
       "learning_rate": 3.4096741493194193e-09,
       "loss": 0.0,
+      "reward": 0.6689658281393349,
+      "reward_std": 0.48696194697792333,
       "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": 0.49421582091599703,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.17475001141428947,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 4.235096275806427e-06,
+      "train_runtime": 305.2825,
+      "train_samples_per_second": 1.048,
+      "train_steps_per_second": 0.066
     }
   ],
   "logging_steps": 2,