Instructions to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with Transformers:

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

pipe = pipeline("text-generation", model="wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot")
model = AutoModelForCausalLM.from_pretrained("wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot", 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 wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot

SGLang

How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot 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 "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot" \
    --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": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot",
		"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 "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot" \
        --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": "wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot with Docker Model Runner:
```
docker model run hf.co/wjkim2022/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-wild_lethal_ocelot
```

wjkim2022 commited on Apr 5, 2025

Commit

0529955

verified ·

1 Parent(s): 0a20b95

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 +117 -117

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.010085236077429727,
-    "train_runtime": 1144.6607,
     "train_samples": 160,
-    "train_samples_per_second": 0.28,
     "train_steps_per_second": 0.017
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.09601817332440987,
+    "train_runtime": 1148.53,
     "train_samples": 160,
+    "train_samples_per_second": 0.279,
     "train_steps_per_second": 0.017
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9ae4ef8463f92bcbac6736cae5510774ab8de28f078d1c1d8d0e374ce23a9a
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:fbaccebd7ca92c0edd25e1f6aabc6a7ed11b9564f5f878416dfc6fb5134c05ea
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.010085236077429727,
-    "train_runtime": 1144.6607,
     "train_samples": 160,
-    "train_samples_per_second": 0.28,
     "train_steps_per_second": 0.017
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.09601817332440987,
+    "train_runtime": 1148.53,
     "train_samples": 160,
+    "train_samples_per_second": 0.279,
     "train_steps_per_second": 0.017
 }

trainer_state.json CHANGED Viewed

@@ -10,202 +10,202 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 267.84375,
       "epoch": 0.1,
-      "grad_norm": 22.215709686279297,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
-      "loss": 0.0,
-      "reward": 4.318057797849178,
-      "reward_std": 1.5912078737455886,
-      "rewards/concensus_correctness_reward_func": 1.708625003695488,
       "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.6635578233399428,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.21875,
-      "rewards/xmlcount_reward_func": 0.5396250002086163,
       "step": 2
     },
     {
-      "completion_length": 130.71875,
       "epoch": 0.2,
-      "grad_norm": 35.976646423339844,
-      "kl": 0.5047043640443007,
       "learning_rate": 4.698684378016222e-07,
-      "loss": 0.0005,
-      "reward": 6.4149744510650635,
-      "reward_std": 0.9650884206639603,
-      "rewards/concensus_correctness_reward_func": 1.9224999770522118,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.8410994389560074,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.1513750031590462,
       "step": 4
     },
     {
-      "completion_length": 152.0625,
       "epoch": 0.3,
-      "grad_norm": 105.97667694091797,
-      "kl": 9.62625068926718,
       "learning_rate": 4.193203929064353e-07,
-      "loss": 0.0096,
-      "reward": 6.059204041957855,
-      "reward_std": 0.7523557092063129,
-      "rewards/concensus_correctness_reward_func": 1.7304999828338623,
-      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.7850790489464998,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.168624997138977,
       "step": 6
     },
     {
-      "completion_length": 143.875,
       "epoch": 0.4,
-      "grad_norm": 58.275089263916016,
-      "kl": 36.81611431809142,
       "learning_rate": 3.5042385616324236e-07,
-      "loss": 0.0368,
-      "reward": 6.307498164474964,
-      "reward_std": 0.27225188571901526,
-      "rewards/concensus_correctness_reward_func": 1.9297500029206276,
-      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.8251856788992882,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.2088125050067902,
       "step": 8
     },
     {
-      "completion_length": 154.03125,
       "epoch": 0.5,
-      "grad_norm": 35.974021911621094,
-      "kl": 17.69686983374413,
       "learning_rate": 2.706448363680831e-07,
-      "loss": 0.0177,
-      "reward": 6.1004427671432495,
-      "reward_std": 1.3394888696202543,
-      "rewards/concensus_correctness_reward_func": 1.723062489181757,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.8383178114891052,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.421875,
-      "rewards/xmlcount_reward_func": 1.1796875,
       "step": 10
     },
     {
-      "completion_length": 142.09375,
       "epoch": 0.6,
-      "grad_norm": 276.7464294433594,
-      "kl": 10.106085598352365,
       "learning_rate": 1.886286282148002e-07,
-      "loss": 0.0101,
-      "reward": 6.283836856484413,
-      "reward_std": 1.1054969025135506,
-      "rewards/concensus_correctness_reward_func": 1.940999991260469,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.7908368613570929,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.1613750085234642,
       "step": 12
     },
     {
-      "completion_length": 141.875,
       "epoch": 0.7,
-      "grad_norm": 954.4512939453125,
-      "kl": 22.069533768939436,
       "learning_rate": 1.1326296046939333e-07,
-      "loss": 0.0221,
-      "reward": 6.685095690190792,
-      "reward_std": 0.29181225258798804,
-      "rewards/concensus_correctness_reward_func": 2.048875004053116,
-      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.9117832891643047,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.2244375050067902,
       "step": 14
     },
     {
-      "completion_length": 185.75,
       "epoch": 0.8,
-      "grad_norm": 91.3758544921875,
-      "kl": 2.3530825720517896,
       "learning_rate": 5.271487265090163e-08,
-      "loss": 0.0024,
-      "reward": 5.83555194735527,
-      "reward_std": 1.007811893709004,
-      "rewards/concensus_correctness_reward_func": 1.7158749923110008,
       "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.7512082257308066,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.0559687558561563,
       "step": 16
     },
     {
-      "completion_length": 140.625,
       "epoch": 0.9,
-      "grad_norm": 48.41429901123047,
-      "kl": 0.7401317909825593,
       "learning_rate": 1.3545689574841341e-08,
-      "loss": 0.0007,
-      "reward": 6.625904679298401,
-      "reward_std": 0.4565052143007051,
-      "rewards/concensus_correctness_reward_func": 2.078750003129244,
-      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.822029622271657,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.1938750073313713,
       "step": 18
     },
     {
-      "completion_length": 137.0625,
       "epoch": 1.0,
-      "grad_norm": 21.3829288482666,
-      "kl": 0.9205660497245844,
       "learning_rate": 0.0,
-      "loss": 0.0009,
-      "reward": 6.017769768834114,
-      "reward_std": 0.7093295305967331,
-      "rewards/concensus_correctness_reward_func": 1.6843125000596046,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.855113557074219,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.2283437550067902,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.010085236077429727,
-      "train_runtime": 1144.6607,
-      "train_samples_per_second": 0.28,
       "train_steps_per_second": 0.017
     }
   ],

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 217.9375,
       "epoch": 0.1,
+      "grad_norm": 26.588115692138672,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
+      "loss": -0.0,
+      "reward": 3.9238121116068214,
+      "reward_std": 0.4984353088802891,
+      "rewards/concensus_correctness_reward_func": 1.1453749984502792,
       "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.6629996267147362,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.203125,
+      "rewards/xmlcount_reward_func": 0.7248125001788139,
       "step": 2
     },
     {
+      "completion_length": 153.125,
       "epoch": 0.2,
+      "grad_norm": 3096.6826171875,
+      "kl": 127.40181041706819,
       "learning_rate": 4.698684378016222e-07,
+      "loss": 0.1274,
+      "reward": 6.899618923664093,
+      "reward_std": 0.24133055911806878,
+      "rewards/concensus_correctness_reward_func": 2.1158749982714653,
+      "rewards/consensus_reward_func": 2.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.8959314632229507,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.200312502682209,
       "step": 4
     },
     {
+      "completion_length": 198.40625,
       "epoch": 0.3,
+      "grad_norm": 1606.969970703125,
+      "kl": 795.1475641654106,
       "learning_rate": 4.193203929064353e-07,
+      "loss": 0.7951,
+      "reward": 5.769073113799095,
+      "reward_std": 0.7471559516125126,
+      "rewards/concensus_correctness_reward_func": 1.5693749859929085,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8377606067806482,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.0806875005364418,
       "step": 6
     },
     {
+      "completion_length": 152.0,
       "epoch": 0.4,
+      "grad_norm": 40.196903228759766,
+      "kl": 13.456765508046374,
       "learning_rate": 3.5042385616324236e-07,
+      "loss": 0.0135,
+      "reward": 6.106819957494736,
+      "reward_std": 0.7433944554068148,
+      "rewards/concensus_correctness_reward_func": 1.8684999831020832,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7426948631182313,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.1831250041723251,
       "step": 8
     },
     {
+      "completion_length": 131.21875,
       "epoch": 0.5,
+      "grad_norm": 295.4882507324219,
+      "kl": 10.536870398558676,
       "learning_rate": 2.706448363680831e-07,
+      "loss": 0.0105,
+      "reward": 6.271051615476608,
+      "reward_std": 0.6707179503282532,
+      "rewards/concensus_correctness_reward_func": 1.9781250059604645,
+      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.7211140692234039,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.40625,
+      "rewards/xmlcount_reward_func": 1.1655625030398369,
       "step": 10
     },
     {
+      "completion_length": 152.90625,
       "epoch": 0.6,
+      "grad_norm": 40.68523025512695,
+      "kl": 1.2147540808655322,
       "learning_rate": 1.886286282148002e-07,
+      "loss": 0.0012,
+      "reward": 6.223801136016846,
+      "reward_std": 0.5582126578883617,
+      "rewards/concensus_correctness_reward_func": 1.8157499795779586,
+      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7773010907694697,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4375,
+      "rewards/xmlcount_reward_func": 1.1932500004768372,
       "step": 12
     },
     {
+      "completion_length": 145.09375,
       "epoch": 0.7,
+      "grad_norm": 45.17070770263672,
+      "kl": 4.149055448011495,
       "learning_rate": 1.1326296046939333e-07,
+      "loss": 0.0041,
+      "reward": 6.308409869670868,
+      "reward_std": 0.6662825503153726,
+      "rewards/concensus_correctness_reward_func": 1.9175625070929527,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.8150973552837968,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.1382500194013119,
       "step": 14
     },
     {
+      "completion_length": 148.96875,
       "epoch": 0.8,
+      "grad_norm": 51.33207321166992,
+      "kl": 1.3372775473326328,
       "learning_rate": 5.271487265090163e-08,
+      "loss": 0.0013,
+      "reward": 6.160888954997063,
+      "reward_std": 0.6417121767881326,
+      "rewards/concensus_correctness_reward_func": 1.8831249922513962,
       "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8388577756704763,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.095156254246831,
       "step": 16
     },
     {
+      "completion_length": 165.5,
       "epoch": 0.9,
+      "grad_norm": 38.135047912597656,
+      "kl": 1.0823733173310757,
       "learning_rate": 1.3545689574841341e-08,
+      "loss": 0.0011,
+      "reward": 6.3814394772052765,
+      "reward_std": 0.5592010340260458,
+      "rewards/concensus_correctness_reward_func": 2.0731874965131283,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.8645332593005151,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.28125,
+      "rewards/xmlcount_reward_func": 1.1624687686562538,
       "step": 18
     },
     {
+      "completion_length": 132.875,
       "epoch": 1.0,
+      "grad_norm": 36.65176773071289,
+      "kl": 5.834113052580506,
       "learning_rate": 0.0,
+      "loss": 0.0058,
+      "reward": 6.213781073689461,
+      "reward_std": 0.47957354108802974,
+      "rewards/concensus_correctness_reward_func": 1.863249994814396,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8057811510516331,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.421875,
+      "rewards/xmlcount_reward_func": 1.1853750050067902,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.09601817332440987,
+      "train_runtime": 1148.53,
+      "train_samples_per_second": 0.279,
       "train_steps_per_second": 0.017
     }
   ],