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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/haedahae/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-deadly_deadly_dingo

SGLang

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

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

haedahae commited on Apr 5, 2025

Commit

97ed018

verified ·

1 Parent(s): 2e6d6d8

End of training

Browse files

Files changed (4) hide show

all_results.json +3 -3
model.safetensors +1 -1
train_results.json +3 -3
trainer_state.json +114 -114

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.059670508140698075,
-    "train_runtime": 1089.8785,
     "train_samples": 160,
-    "train_samples_per_second": 0.294,
     "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.006785672821570188,
+    "train_runtime": 1090.6448,
     "train_samples": 160,
+    "train_samples_per_second": 0.293,
     "train_steps_per_second": 0.018
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c80b09520fe21cc83534f55e1af667c07bdf5bc5e0928f4753903cdbccd921
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:6fea78f3d19b71acb10ff8f19c04aacdf50a209dcb50757f1152dff24ce22709
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.059670508140698075,
-    "train_runtime": 1089.8785,
     "train_samples": 160,
-    "train_samples_per_second": 0.294,
     "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.006785672821570188,
+    "train_runtime": 1090.6448,
     "train_samples": 160,
+    "train_samples_per_second": 0.293,
     "train_steps_per_second": 0.018
 }

trainer_state.json CHANGED Viewed

@@ -10,202 +10,202 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 224.15625,
       "epoch": 0.1,
-      "grad_norm": 40.93347930908203,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": 0.0,
-      "reward": 4.551249801297672,
-      "reward_std": 1.7841942000377458,
-      "rewards/concensus_correctness_reward_func": 1.7093749940395355,
-      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6374998039100319,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.1875,
-      "rewards/xmlcount_reward_func": 0.7668749894946814,
       "step": 2
     },
     {
-      "completion_length": 171.34375,
       "epoch": 0.2,
-      "grad_norm": 2569.2705078125,
-      "kl": 21.397925002267584,
       "learning_rate": 4.698684378016222e-07,
-      "loss": 0.0214,
-      "reward": 5.90058733522892,
-      "reward_std": 0.9084100943437079,
-      "rewards/concensus_correctness_reward_func": 1.768999982625246,
       "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.811649932526052,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.0699374992400408,
       "step": 4
     },
     {
-      "completion_length": 138.9375,
       "epoch": 0.3,
-      "grad_norm": 38.15834045410156,
-      "kl": 1.8975782822817564,
       "learning_rate": 4.193203929064353e-07,
-      "loss": 0.0019,
-      "reward": 5.859929412603378,
-      "reward_std": 0.5549354225513525,
-      "rewards/concensus_correctness_reward_func": 1.621874986216426,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8495544221950695,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.2010000012814999,
       "step": 6
     },
     {
-      "completion_length": 156.125,
       "epoch": 0.4,
-      "grad_norm": 175.18612670898438,
-      "kl": 9.684959430247545,
       "learning_rate": 3.5042385616324236e-07,
-      "loss": 0.0097,
-      "reward": 6.071536347270012,
-      "reward_std": 1.2400518646172713,
-      "rewards/concensus_correctness_reward_func": 1.8186249919235706,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.8035675827413797,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.1368437483906746,
       "step": 8
     },
     {
-      "completion_length": 142.96875,
       "epoch": 0.5,
-      "grad_norm": 197.0068359375,
-      "kl": 10.860106905922294,
       "learning_rate": 2.706448363680831e-07,
-      "loss": 0.0109,
-      "reward": 6.705548390746117,
-      "reward_std": 1.032524550682865,
-      "rewards/concensus_correctness_reward_func": 2.176624983549118,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.4375,
-      "rewards/question_recreation_reward_func": 0.6847672024741769,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.1566562503576279,
       "step": 10
     },
     {
-      "completion_length": 182.65625,
       "epoch": 0.6,
-      "grad_norm": 31.448713302612305,
-      "kl": 1.455637429608032,
       "learning_rate": 1.886286282148002e-07,
-      "loss": 0.0015,
-      "reward": 6.7447062730789185,
-      "reward_std": 0.33806667962198844,
-      "rewards/concensus_correctness_reward_func": 2.0787499770522118,
-      "rewards/consensus_reward_func": 2.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.8320499854162335,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.421875,
-      "rewards/xmlcount_reward_func": 1.1620312482118607,
       "step": 12
     },
     {
-      "completion_length": 135.59375,
       "epoch": 0.7,
-      "grad_norm": 1884.615478515625,
-      "kl": 354.6374082516413,
       "learning_rate": 1.1326296046939333e-07,
-      "loss": 0.3546,
-      "reward": 7.031403452157974,
-      "reward_std": 0.49297699268208817,
-      "rewards/concensus_correctness_reward_func": 2.173250012099743,
-      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.9675284884870052,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.203125,
       "step": 14
     },
     {
-      "completion_length": 141.15625,
       "epoch": 0.8,
-      "grad_norm": 2758.303466796875,
-      "kl": 128.4870506664738,
       "learning_rate": 5.271487265090163e-08,
-      "loss": 0.1285,
-      "reward": 6.240614026784897,
-      "reward_std": 0.41513029413181357,
-      "rewards/concensus_correctness_reward_func": 1.8091249912977219,
       "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.7695827465504408,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.193156249821186,
       "step": 16
     },
     {
-      "completion_length": 161.75,
       "epoch": 0.9,
-      "grad_norm": 1324.51416015625,
-      "kl": 60.8234548997134,
       "learning_rate": 1.3545689574841341e-08,
-      "loss": 0.0608,
-      "reward": 5.641928143799305,
-      "reward_std": 0.5431558364944067,
-      "rewards/concensus_correctness_reward_func": 1.6804999895393848,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.8078344627283514,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.0598437506705523,
       "step": 18
     },
     {
-      "completion_length": 132.0,
       "epoch": 1.0,
-      "grad_norm": 100.98587799072266,
-      "kl": 7.456962174735963,
       "learning_rate": 0.0,
-      "loss": 0.0075,
-      "reward": 6.75328041613102,
-      "reward_std": 0.6193592441268265,
-      "rewards/concensus_correctness_reward_func": 2.1126249879598618,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.9141554981470108,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.195250004529953,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.059670508140698075,
-      "train_runtime": 1089.8785,
-      "train_samples_per_second": 0.294,
       "train_steps_per_second": 0.018
     }
   ],

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 193.34375,
       "epoch": 0.1,
+      "grad_norm": 25.437278747558594,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": 0.0,
+      "reward": 3.6266137938946486,
+      "reward_std": 0.8307934795739129,
+      "rewards/concensus_correctness_reward_func": 0.9024999998509884,
+      "rewards/consensus_reward_func": 0.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.6582388319075108,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.234375,
+      "rewards/xmlcount_reward_func": 0.7689999984577298,
       "step": 2
     },
     {
+      "completion_length": 228.46875,
       "epoch": 0.2,
+      "grad_norm": 39.24359130859375,
+      "kl": 1.5343358425889164,
       "learning_rate": 4.698684378016222e-07,
+      "loss": 0.0015,
+      "reward": 6.112734526395798,
+      "reward_std": 1.0056872393470258,
+      "rewards/concensus_correctness_reward_func": 1.8086874820291996,
       "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9244220145046711,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.0515000000596046,
       "step": 4
     },
     {
+      "completion_length": 166.5625,
       "epoch": 0.3,
+      "grad_norm": 138.03665161132812,
+      "kl": 2.744431208819151,
       "learning_rate": 4.193203929064353e-07,
+      "loss": 0.0027,
+      "reward": 5.025258347392082,
+      "reward_std": 0.2811972763593076,
+      "rewards/concensus_correctness_reward_func": 1.3959999848157167,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7735082694562152,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.027624998241663,
       "step": 6
     },
     {
+      "completion_length": 173.75,
       "epoch": 0.4,
+      "grad_norm": 67.41569519042969,
+      "kl": 6.022588826715946,
       "learning_rate": 3.5042385616324236e-07,
+      "loss": 0.006,
+      "reward": 6.697861954569817,
+      "reward_std": 0.6546344570815563,
+      "rewards/concensus_correctness_reward_func": 1.997437495738268,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.913518188521266,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.421875,
+      "rewards/xmlcount_reward_func": 1.1775312554091215,
       "step": 8
     },
     {
+      "completion_length": 136.65625,
       "epoch": 0.5,
+      "grad_norm": 332.54534912109375,
+      "kl": 17.14331202954054,
       "learning_rate": 2.706448363680831e-07,
+      "loss": 0.0171,
+      "reward": 7.414227694272995,
+      "reward_std": 0.496162755342084,
+      "rewards/concensus_correctness_reward_func": 2.4219999983906746,
+      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.625,
+      "rewards/question_recreation_reward_func": 0.7981027774512768,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.4375,
+      "rewards/xmlcount_reward_func": 1.1941250003874302,
       "step": 10
     },
     {
+      "completion_length": 160.6875,
       "epoch": 0.6,
+      "grad_norm": 29.822416305541992,
+      "kl": 28.22160056978464,
       "learning_rate": 1.886286282148002e-07,
+      "loss": 0.0282,
+      "reward": 6.131470635533333,
+      "reward_std": 1.1960517894112854,
+      "rewards/concensus_correctness_reward_func": 1.8389999866485596,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.8451581280678511,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.1348125003278255,
       "step": 12
     },
     {
+      "completion_length": 183.0,
       "epoch": 0.7,
+      "grad_norm": 36.994346618652344,
+      "kl": 8.928391239605844,
       "learning_rate": 1.1326296046939333e-07,
+      "loss": 0.0089,
+      "reward": 6.382866933941841,
+      "reward_std": 0.9713909234851599,
+      "rewards/concensus_correctness_reward_func": 2.0543750189244747,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.8999295085668564,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.0066875014454126,
       "step": 14
     },
     {
+      "completion_length": 148.59375,
       "epoch": 0.8,
+      "grad_norm": 33.646080017089844,
+      "kl": 0.7313799187541008,
       "learning_rate": 5.271487265090163e-08,
+      "loss": 0.0007,
+      "reward": 6.244778722524643,
+      "reward_std": 0.8219166721682996,
+      "rewards/concensus_correctness_reward_func": 1.810937486588955,
       "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8629974937066436,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.1489687487483025,
       "step": 16
     },
     {
+      "completion_length": 125.125,
       "epoch": 0.9,
+      "grad_norm": 263.7424011230469,
+      "kl": 0.666266948916018,
       "learning_rate": 1.3545689574841341e-08,
+      "loss": 0.0007,
+      "reward": 5.990852370858192,
+      "reward_std": 0.24256473960122094,
+      "rewards/concensus_correctness_reward_func": 1.8007499873638153,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7682274281978607,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.46875,
+      "rewards/xmlcount_reward_func": 1.203125,
       "step": 18
     },
     {
+      "completion_length": 130.875,
       "epoch": 1.0,
+      "grad_norm": 75.74906921386719,
+      "kl": 1.873372424626723,
       "learning_rate": 0.0,
+      "loss": 0.0019,
+      "reward": 6.883746221661568,
+      "reward_std": 0.35684540566580836,
+      "rewards/concensus_correctness_reward_func": 2.11268749833107,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.9117461740970612,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.453125,
+      "rewards/xmlcount_reward_func": 1.218687504529953,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.006785672821570188,
+      "train_runtime": 1090.6448,
+      "train_samples_per_second": 0.293,
       "train_steps_per_second": 0.018
     }
   ],