Instructions to use xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-purring_patterned_prawn 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-purring_patterned_prawn 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-purring_patterned_prawn")
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-purring_patterned_prawn")
model = AutoModelForCausalLM.from_pretrained("xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-purring_patterned_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 xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-purring_patterned_prawn 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-purring_patterned_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": "xaobai/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-purring_patterned_prawn",
		"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-purring_patterned_prawn

SGLang

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

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

xaobai commited on Apr 7, 2025

Commit

56eb7d2

verified ·

1 Parent(s): 6dd2476

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 +110 -110

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 31.67384350030188,
-    "train_runtime": 147.5599,
     "train_samples": 160,
-    "train_samples_per_second": 2.169,
-    "train_steps_per_second": 0.136
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.468176003973349,
+    "train_runtime": 141.5805,
     "train_samples": 160,
+    "train_samples_per_second": 2.26,
+    "train_steps_per_second": 0.141
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69586a64ed901a202bb5b08b6a6a55c0b019535d45d93352c880be51bbe76eb6
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:8bc89d5b0eef6c96f3eeb6f0589367b381fc1f8257b206c43e0fcecb2132fce9
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 31.67384350030188,
-    "train_runtime": 147.5599,
     "train_samples": 160,
-    "train_samples_per_second": 2.169,
-    "train_steps_per_second": 0.136
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.468176003973349,
+    "train_runtime": 141.5805,
     "train_samples": 160,
+    "train_samples_per_second": 2.26,
+    "train_steps_per_second": 0.141
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 293.5,
       "epoch": 0.1,
-      "grad_norm": 21.87837028503418,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
-      "loss": -0.0,
-      "reward": 3.4529242645949125,
-      "reward_std": 0.8168715483043343,
-      "rewards/concensus_correctness_reward_func": 1.0291250012814999,
-      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.6370179792866111,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5992812123149633,
       "step": 2
     },
     {
-      "completion_length": 190.09375,
       "epoch": 0.2,
-      "grad_norm": 18.614229202270508,
-      "kl": 0.0572272595600225,
       "learning_rate": 4.698684378016222e-07,
       "loss": 0.0001,
-      "reward": 5.523550629615784,
-      "reward_std": 0.3650686846813187,
-      "rewards/concensus_correctness_reward_func": 1.491812502965331,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9053631611168385,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 1.1732499599456787,
       "step": 4
     },
     {
-      "completion_length": 183.125,
       "epoch": 0.3,
-      "grad_norm": 17.62615394592285,
-      "kl": 1.6734426808543503,
       "learning_rate": 4.193203929064353e-07,
-      "loss": 0.0017,
-      "reward": 6.672829240560532,
-      "reward_std": 1.334838982205838,
-      "rewards/concensus_correctness_reward_func": 2.5361249819397926,
-      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.9344855435192585,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 1.1240937039256096,
       "step": 6
     },
     {
-      "completion_length": 169.34375,
       "epoch": 0.4,
-      "grad_norm": 22.768394470214844,
-      "kl": 0.16654252854641527,
       "learning_rate": 3.5042385616324236e-07,
-      "loss": 0.0002,
-      "reward": 5.723400875926018,
-      "reward_std": 0.5392706191487378,
-      "rewards/concensus_correctness_reward_func": 1.6863750023767352,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.859369607642293,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 1.2245311960577965,
       "step": 8
     },
     {
-      "completion_length": 150.84375,
       "epoch": 0.5,
-      "grad_norm": 21.333995819091797,
-      "kl": 1.1378401825204492,
       "learning_rate": 2.706448363680831e-07,
-      "loss": 0.0011,
-      "reward": 5.872089892625809,
-      "reward_std": 0.3128124506911263,
-      "rewards/concensus_correctness_reward_func": 1.836374994367361,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9001835249364376,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1980312019586563,
       "step": 10
     },
     {
-      "completion_length": 160.03125,
       "epoch": 0.6,
-      "grad_norm": 15758401.0,
-      "kl": 316713.72098062607,
       "learning_rate": 1.886286282148002e-07,
-      "loss": 316.7137,
-      "reward": 5.619781166315079,
-      "reward_std": 0.27606764990923693,
-      "rewards/concensus_correctness_reward_func": 1.7557499818503857,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8408436197787523,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.2106874510645866,
       "step": 12
     },
     {
-      "completion_length": 157.5625,
       "epoch": 0.7,
-      "grad_norm": 22.5251407623291,
-      "kl": 0.34531001024879515,
       "learning_rate": 1.1326296046939333e-07,
       "loss": 0.0003,
-      "reward": 6.466561004519463,
-      "reward_std": 1.1181316616857657,
-      "rewards/concensus_correctness_reward_func": 2.4810000024735928,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.8361233733594418,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.2119374349713326,
       "step": 14
     },
     {
-      "completion_length": 173.0625,
       "epoch": 0.8,
-      "grad_norm": 20.4410343170166,
-      "kl": 14.952521678758785,
       "learning_rate": 5.271487265090163e-08,
-      "loss": 0.015,
-      "reward": 6.509227424860001,
-      "reward_std": 0.22894962801365182,
-      "rewards/concensus_correctness_reward_func": 2.1026874985545874,
-      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.8933523446321487,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 1.1850624531507492,
       "step": 16
     },
     {
-      "completion_length": 156.40625,
       "epoch": 0.9,
-      "grad_norm": 17.90320587158203,
-      "kl": 3.1803087985608727,
       "learning_rate": 1.3545689574841341e-08,
-      "loss": 0.0032,
-      "reward": 5.28251214325428,
-      "reward_std": 0.4274246614513686,
-      "rewards/concensus_correctness_reward_func": 1.5472500026226044,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9193559512495995,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1909061968326569,
       "step": 18
     },
     {
-      "completion_length": 144.71875,
       "epoch": 1.0,
-      "grad_norm": 137.31451416015625,
-      "kl": 3.2102996171452105,
       "learning_rate": 0.0,
-      "loss": 0.0032,
-      "reward": 6.1640735268592834,
-      "reward_std": 0.44063665649446193,
-      "rewards/concensus_correctness_reward_func": 2.029124990105629,
-      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.919979739934206,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.214968703687191,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 31.67384350030188,
-      "train_runtime": 147.5599,
-      "train_samples_per_second": 2.169,
-      "train_steps_per_second": 0.136
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 238.21875,
       "epoch": 0.1,
+      "grad_norm": 23.061830520629883,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
+      "loss": 0.0,
+      "reward": 4.5968284253031015,
+      "reward_std": 0.616630203621753,
+      "rewards/concensus_correctness_reward_func": 2.199562504887581,
+      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.5915159117430449,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6807499742135406,
       "step": 2
     },
     {
+      "completion_length": 165.375,
       "epoch": 0.2,
+      "grad_norm": 28.605224609375,
+      "kl": 0.1424046578758862,
       "learning_rate": 4.698684378016222e-07,
       "loss": 0.0001,
+      "reward": 5.776076227426529,
+      "reward_std": 0.6955992908915505,
+      "rewards/concensus_correctness_reward_func": 1.6770624928176403,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9044200219213963,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 1.1789687052369118,
       "step": 4
     },
     {
+      "completion_length": 190.0,
       "epoch": 0.3,
+      "grad_norm": 23.82851219177246,
+      "kl": 0.34406266862060875,
       "learning_rate": 4.193203929064353e-07,
+      "loss": 0.0003,
+      "reward": 5.5506651401519775,
+      "reward_std": 0.16025130550133326,
+      "rewards/concensus_correctness_reward_func": 1.6028124950826168,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.9063213616609573,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.1665311940014362,
       "step": 6
     },
     {
+      "completion_length": 172.96875,
       "epoch": 0.4,
+      "grad_norm": 33.95582580566406,
+      "kl": 0.27934576687403023,
       "learning_rate": 3.5042385616324236e-07,
+      "loss": 0.0003,
+      "reward": 6.021767497062683,
+      "reward_std": 0.3667241964285495,
+      "rewards/concensus_correctness_reward_func": 1.857812493108213,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9293612577021122,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 1.1564687080681324,
       "step": 8
     },
     {
+      "completion_length": 153.75,
       "epoch": 0.5,
+      "grad_norm": 18.014972686767578,
+      "kl": 2.704328676336445,
       "learning_rate": 2.706448363680831e-07,
+      "loss": 0.0027,
+      "reward": 6.106728702783585,
+      "reward_std": 0.3038245351635851,
+      "rewards/concensus_correctness_reward_func": 1.9768749848008156,
+      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.9085097648203373,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.1588436998426914,
       "step": 10
     },
     {
+      "completion_length": 162.5,
       "epoch": 0.6,
+      "grad_norm": 97.16446685791016,
+      "kl": 5.110307271126658,
       "learning_rate": 1.886286282148002e-07,
+      "loss": 0.0051,
+      "reward": 5.1675363183021545,
+      "reward_std": 0.8226150240807328,
+      "rewards/concensus_correctness_reward_func": 1.5147499814629555,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7865362111479044,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.1787499599158764,
       "step": 12
     },
     {
+      "completion_length": 153.4375,
       "epoch": 0.7,
+      "grad_norm": 14.0081205368042,
+      "kl": 0.31082624034024775,
       "learning_rate": 1.1326296046939333e-07,
       "loss": 0.0003,
+      "reward": 6.385396376252174,
+      "reward_std": 1.4748346143751405,
+      "rewards/concensus_correctness_reward_func": 2.3415624871850014,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8933338597416878,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.2129999436438084,
       "step": 14
     },
     {
+      "completion_length": 155.375,
       "epoch": 0.8,
+      "grad_norm": 14.671515464782715,
+      "kl": 9.717409254400991,
       "learning_rate": 5.271487265090163e-08,
+      "loss": 0.0097,
+      "reward": 5.68576055765152,
+      "reward_std": 0.6367222345579648,
+      "rewards/concensus_correctness_reward_func": 1.6311874985694885,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8846354763954878,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 1.2168124467134476,
       "step": 16
     },
     {
+      "completion_length": 159.9375,
       "epoch": 0.9,
+      "grad_norm": 134988.875,
+      "kl": 4659.71151078766,
       "learning_rate": 1.3545689574841341e-08,
+      "loss": 4.6597,
+      "reward": 7.275305807590485,
+      "reward_std": 0.2323648716119351,
+      "rewards/concensus_correctness_reward_func": 3.144124999642372,
+      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8945556059479713,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.1741249524056911,
       "step": 18
     },
     {
+      "completion_length": 157.0625,
       "epoch": 1.0,
+      "grad_norm": 35.6768684387207,
+      "kl": 3.506329826777801,
       "learning_rate": 0.0,
+      "loss": 0.0035,
+      "reward": 5.915709361433983,
+      "reward_std": 0.2794380595878465,
+      "rewards/concensus_correctness_reward_func": 1.8087499924004078,
+      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8960218746215105,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.015625,
+      "rewards/xmlcount_reward_func": 1.1328124590218067,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.468176003973349,
+      "train_runtime": 141.5805,
+      "train_samples_per_second": 2.26,
+      "train_steps_per_second": 0.141
     }
   ],
   "logging_steps": 2,