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 15, 2025

Commit

18ce37d

verified ·

1 Parent(s): 7397c17

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 +117 -117

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.07264543487108313,
-    "train_runtime": 136.4407,
     "train_samples": 28,
-    "train_samples_per_second": 2.345,
-    "train_steps_per_second": 0.147
 }

 {
     "total_flos": 0.0,
+    "train_loss": 7414045297408.011,
+    "train_runtime": 138.0454,
     "train_samples": 28,
+    "train_samples_per_second": 2.318,
+    "train_steps_per_second": 0.145
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de3538acf2b32e41b954ecfe3d985f7cbaaef68c9e4b7951a6f40b0d67705a3
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:4086f4aade2b60e7dd20a1f4e228e875875f8c8a99508a2109229f82264a0498
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.07264543487108313,
-    "train_runtime": 136.4407,
     "train_samples": 28,
-    "train_samples_per_second": 2.345,
-    "train_steps_per_second": 0.147
 }

 {
     "total_flos": 0.0,
+    "train_loss": 7414045297408.011,
+    "train_runtime": 138.0454,
     "train_samples": 28,
+    "train_samples_per_second": 2.318,
+    "train_steps_per_second": 0.145
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 237.6875,
       "epoch": 0.5714285714285714,
-      "grad_norm": 181.59732055664062,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": -0.0,
-      "reward": 2.5774178989231586,
-      "reward_std": 1.2357047752884682,
-      "rewards/concensus_correctness_reward_func": 0.6088124960660934,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.6205741320736706,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.125,
-      "rewards/xmlcount_reward_func": 0.47303125634789467,
       "step": 2
     },
     {
-      "completion_length": 124.79166666666667,
       "epoch": 1.0,
-      "grad_norm": 96.6654052734375,
-      "kl": 0.9972796945755059,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0007,
-      "reward": 4.230183084805806,
-      "reward_std": 1.9244762441764276,
-      "rewards/concensus_correctness_reward_func": 1.1103333234786987,
-      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3333333333333333,
-      "rewards/question_recreation_reward_func": 0.6771413628011942,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 0.9427083333333334,
       "step": 4
     },
     {
-      "completion_length": 133.40625,
       "epoch": 1.5714285714285714,
-      "grad_norm": 37.24774932861328,
-      "kl": 5.742610273417085,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0057,
-      "reward": 5.29827593266964,
-      "reward_std": 1.1600022818893194,
-      "rewards/concensus_correctness_reward_func": 1.5391874946653843,
       "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.8020571381784976,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.09765625,
       "step": 6
     },
     {
-      "completion_length": 125.625,
       "epoch": 2.0,
-      "grad_norm": 5167.6875,
-      "kl": 761.0514728690808,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.5708,
-      "reward": 3.813926508029302,
-      "reward_std": 1.3750482468458358,
-      "rewards/concensus_correctness_reward_func": 0.9399999976158142,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6603849031962454,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 0.9635416666666666,
       "step": 8
     },
     {
-      "completion_length": 124.53125,
       "epoch": 2.571428571428571,
-      "grad_norm": 65.18873596191406,
-      "kl": 13.80536068067886,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0138,
-      "reward": 4.39049181714654,
-      "reward_std": 0.9386822572123492,
-      "rewards/concensus_correctness_reward_func": 1.1541249938309193,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7074293025070801,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.28125,
-      "rewards/xmlcount_reward_func": 0.997687503695488,
       "step": 10
     },
     {
-      "completion_length": 125.0,
       "epoch": 3.0,
-      "grad_norm": 19.021623611450195,
-      "kl": 30.206965184692915,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0227,
-      "reward": 5.097049216429393,
-      "reward_std": 1.5233796233854566,
-      "rewards/concensus_correctness_reward_func": 1.372166657820344,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.5,
-      "rewards/question_recreation_reward_func": 0.7648824911254147,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 0.980833334227403,
       "step": 12
     },
     {
-      "completion_length": 127.71875,
       "epoch": 3.571428571428571,
-      "grad_norm": 56.89619445800781,
-      "kl": 11.910120419692248,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0119,
-      "reward": 4.755805924534798,
-      "reward_std": 0.866679758488317,
-      "rewards/concensus_correctness_reward_func": 1.363562498241663,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.6814933620626107,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.265625,
-      "rewards/xmlcount_reward_func": 1.0076249949634075,
       "step": 14
     },
     {
-      "completion_length": 122.08333333333333,
       "epoch": 4.0,
-      "grad_norm": 301.321533203125,
-      "kl": 88.25671694303553,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0662,
-      "reward": 3.93316487967968,
-      "reward_std": 0.7382187309655516,
-      "rewards/concensus_correctness_reward_func": 1.0914166569709778,
-      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.6660815561190248,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.22916666666666666,
-      "rewards/xmlcount_reward_func": 0.9464999934037527,
       "step": 16
     },
     {
-      "completion_length": 136.78125,
       "epoch": 4.571428571428571,
-      "grad_norm": 140.7506866455078,
-      "kl": 13.990060538053513,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.014,
-      "reward": 4.935266211628914,
-      "reward_std": 1.5161829814314842,
-      "rewards/concensus_correctness_reward_func": 1.3161874935030937,
-      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.8143599089235067,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.0547187477350235,
       "step": 18
     },
     {
-      "completion_length": 122.41666666666667,
       "epoch": 5.0,
-      "grad_norm": 13.33469009399414,
-      "kl": 27.524718740023673,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0206,
-      "reward": 4.406380941470464,
-      "reward_std": 0.1256474384960408,
-      "rewards/concensus_correctness_reward_func": 1.162333329518636,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7336308974772692,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.03125,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.07264543487108313,
-      "train_runtime": 136.4407,
-      "train_samples_per_second": 2.345,
-      "train_steps_per_second": 0.147
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 220.40625,
       "epoch": 0.5714285714285714,
+      "grad_norm": 370.6959228515625,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0,
+      "reward": 3.158231223002076,
+      "reward_std": 2.3540359642356634,
+      "rewards/concensus_correctness_reward_func": 0.7574374969117343,
+      "rewards/consensus_reward_func": 0.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.5939812306314707,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.125,
+      "rewards/xmlcount_reward_func": 0.7443124949932098,
       "step": 2
     },
     {
+      "completion_length": 133.33333333333334,
       "epoch": 1.0,
+      "grad_norm": 38.79075241088867,
+      "kl": 5.331876152127127,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.004,
+      "reward": 5.233374044299126,
+      "reward_std": 0.8660089472929636,
+      "rewards/concensus_correctness_reward_func": 1.5560000042120616,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.7919573835097253,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.09375,
       "step": 4
     },
     {
+      "completion_length": 126.09375,
       "epoch": 1.5714285714285714,
+      "grad_norm": 122.4796371459961,
+      "kl": 4.008211376552936,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.004,
+      "reward": 5.296303015202284,
+      "reward_std": 0.6576162387646036,
+      "rewards/concensus_correctness_reward_func": 1.5581875033676624,
       "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8373342980630696,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.0726562459021807,
       "step": 6
     },
     {
+      "completion_length": 135.16666666666666,
       "epoch": 2.0,
+      "grad_norm": 116.60319519042969,
+      "kl": 72.46203918956842,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0543,
+      "reward": 4.962096472581227,
+      "reward_std": 1.3264382254953186,
+      "rewards/concensus_correctness_reward_func": 1.2855833172798157,
+      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.8027631565928459,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3333333333333333,
+      "rewards/xmlcount_reward_func": 1.0404166678587596,
       "step": 8
     },
     {
+      "completion_length": 124.125,
       "epoch": 2.571428571428571,
+      "grad_norm": 3.246325260877824e+16,
+      "kl": 4467538332384663.5,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 4467538788352.0,
+      "reward": 4.5928835310041904,
+      "reward_std": 0.8666829236244666,
+      "rewards/concensus_correctness_reward_func": 1.259687501937151,
+      "rewards/consensus_reward_func": 1.1875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.794633528450504,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.038562498986721,
       "step": 10
     },
     {
+      "completion_length": 136.20833333333334,
       "epoch": 3.0,
+      "grad_norm": 27328237273088.0,
+      "kl": 9.273817938508731e+16,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 69553639915520.0,
+      "reward": 5.450516646107038,
+      "reward_std": 1.0470037174236495,
+      "rewards/concensus_correctness_reward_func": 1.5939166539659102,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3333333333333333,
+      "rewards/question_recreation_reward_func": 0.7107667277256647,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3333333333333333,
+      "rewards/xmlcount_reward_func": 1.0625,
       "step": 12
     },
     {
+      "completion_length": 136.0,
       "epoch": 3.571428571428571,
+      "grad_norm": 662111554371584.0,
+      "kl": 114505841377290.19,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 114505850880.0,
+      "reward": 5.673261195421219,
+      "reward_std": 0.344359127106145,
+      "rewards/concensus_correctness_reward_func": 1.7128124977461994,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7814487130381167,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.1477500051259995,
       "step": 14
     },
     {
+      "completion_length": 122.0,
       "epoch": 4.0,
+      "grad_norm": 116.89218139648438,
+      "kl": 51.65798989799805,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0387,
+      "reward": 4.060450504223506,
+      "reward_std": 0.8071012394114708,
+      "rewards/concensus_correctness_reward_func": 1.0406666646401088,
+      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7489505461417139,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.2708333333333333,
+      "rewards/xmlcount_reward_func": 1.0,
       "step": 16
     },
     {
+      "completion_length": 154.71875,
       "epoch": 4.571428571428571,
+      "grad_norm": 150.25718688964844,
+      "kl": 18.977649124339223,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.019,
+      "reward": 5.8731399923563,
+      "reward_std": 0.9883110183291137,
+      "rewards/concensus_correctness_reward_func": 1.6851874883286655,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.9194212518632412,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.174781247973442,
       "step": 18
     },
     {
+      "completion_length": 141.95833333333334,
       "epoch": 5.0,
+      "grad_norm": 16.426393508911133,
+      "kl": 6357892377798.195,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 4768419328.0,
+      "reward": 4.353968332211177,
+      "reward_std": 0.8190002473032413,
+      "rewards/concensus_correctness_reward_func": 1.137750009695689,
+      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8203849969431758,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.0833333333333333,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 7414045297408.011,
+      "train_runtime": 138.0454,
+      "train_samples_per_second": 2.318,
+      "train_steps_per_second": 0.145
     }
   ],
   "logging_steps": 2,