Instructions to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with Transformers:

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

pipe = pipeline("text-generation", model="0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee")
model = AutoModelForCausalLM.from_pretrained("0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee", 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 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee

SGLang

How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee 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 "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee" \
    --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": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"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 "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee" \
        --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": "0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee with Docker Model Runner:
```
docker model run hf.co/0xOzii/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-large_padded_chimpanzee
```

0xOzii commited on Apr 11, 2025

Commit

a793e1d

verified ·

1 Parent(s): dc86d88

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 +118 -118

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.115379324562673,
-    "train_runtime": 259.4546,
     "train_samples": 160,
-    "train_samples_per_second": 1.233,
-    "train_steps_per_second": 0.077
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.004387809181207558,
+    "train_runtime": 428.4371,
     "train_samples": 160,
+    "train_samples_per_second": 0.747,
+    "train_steps_per_second": 0.047
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a21b5d9e047c37cdab249081bf74ceac6bce314cc9fb75d212305c1c3ff9ed
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:8404e647722253eaa2165b9a636568c407f0f005cd3baca14089d8fd75c1cb20
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.115379324562673,
-    "train_runtime": 259.4546,
     "train_samples": 160,
-    "train_samples_per_second": 1.233,
-    "train_steps_per_second": 0.077
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.004387809181207558,
+    "train_runtime": 428.4371,
     "train_samples": 160,
+    "train_samples_per_second": 0.747,
+    "train_steps_per_second": 0.047
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 218.3125,
       "epoch": 0.1,
-      "grad_norm": 26.296350479125977,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 3.6801370374159887,
-      "reward_std": 0.9767160329502076,
-      "rewards/concensus_correctness_reward_func": 1.0209375005215406,
-      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.5786370331188664,
       "rewards/soft_format_reward_func": 0.015625,
-      "rewards/strict_format_reward_func": 0.21875,
-      "rewards/xmlcount_reward_func": 0.7836875002831221,
       "step": 2
     },
     {
-      "completion_length": 213.84375,
       "epoch": 0.2,
-      "grad_norm": 18.412763595581055,
-      "kl": 0.03608834894839674,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0,
-      "reward": 5.093468546867371,
-      "reward_std": 0.7862121085636318,
-      "rewards/concensus_correctness_reward_func": 1.377750001847744,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7636561114341021,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.234375,
-      "rewards/xmlcount_reward_func": 1.092687502503395,
       "step": 4
     },
     {
-      "completion_length": 178.65625,
       "epoch": 0.3,
-      "grad_norm": 33.60361099243164,
-      "kl": 1.8460544827394187,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0018,
-      "reward": 5.909685879945755,
-      "reward_std": 0.537973428494297,
-      "rewards/concensus_correctness_reward_func": 1.7259999811649323,
-      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.6087171288672835,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.1999687552452087,
       "step": 6
     },
     {
-      "completion_length": 223.9375,
       "epoch": 0.4,
-      "grad_norm": 21.402921676635742,
-      "kl": 0.2481348062865436,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0002,
-      "reward": 5.865360073745251,
-      "reward_std": 0.5864021766465157,
-      "rewards/concensus_correctness_reward_func": 1.6750624952837825,
-      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.8017975240945816,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.0916250050067902,
       "step": 8
     },
     {
-      "completion_length": 141.03125,
       "epoch": 0.5,
-      "grad_norm": 374.7390441894531,
-      "kl": 9.812545548425987,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0098,
-      "reward": 6.339390397071838,
-      "reward_std": 0.7099191725574201,
-      "rewards/concensus_correctness_reward_func": 1.9031875021755695,
-      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.7487654462456703,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.1718125082552433,
       "step": 10
     },
     {
-      "completion_length": 172.5625,
       "epoch": 0.6,
-      "grad_norm": 21.252607345581055,
-      "kl": 1.4022152130492032,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0014,
-      "reward": 5.558282479643822,
-      "reward_std": 1.3155544230939995,
-      "rewards/concensus_correctness_reward_func": 1.5314374901354313,
       "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.6867825677618384,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.328125,
-      "rewards/xmlcount_reward_func": 1.1369374990463257,
       "step": 12
     },
     {
-      "completion_length": 180.21875,
       "epoch": 0.7,
-      "grad_norm": 23.611936569213867,
-      "kl": 0.9560910745058209,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.001,
-      "reward": 5.223624475300312,
-      "reward_std": 1.299547572270967,
-      "rewards/concensus_correctness_reward_func": 1.4121874868869781,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7627807483077049,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.1267812550067902,
       "step": 14
     },
     {
-      "completion_length": 180.9375,
       "epoch": 0.8,
-      "grad_norm": 24.841073989868164,
-      "kl": 3.4200790476752445,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0034,
-      "reward": 7.234135746955872,
-      "reward_std": 1.0761003146908479,
-      "rewards/concensus_correctness_reward_func": 2.73300002142787,
-      "rewards/consensus_reward_func": 1.9375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.4375,
-      "rewards/question_recreation_reward_func": 0.7248231656849384,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.28125,
-      "rewards/xmlcount_reward_func": 1.1200625263154507,
       "step": 16
     },
     {
-      "completion_length": 167.96875,
       "epoch": 0.9,
-      "grad_norm": 40150.50390625,
-      "kl": 1130.7396090398543,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 1.1307,
-      "reward": 5.12361353635788,
-      "reward_std": 1.119523047003895,
-      "rewards/concensus_correctness_reward_func": 1.425687499344349,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.7232073333580047,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.28125,
-      "rewards/xmlcount_reward_func": 1.0684687495231628,
       "step": 18
     },
     {
-      "completion_length": 169.0625,
       "epoch": 1.0,
-      "grad_norm": 85.5554428100586,
-      "kl": 5.356402600300498,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0054,
-      "reward": 6.061432510614395,
-      "reward_std": 1.0629224462318234,
-      "rewards/concensus_correctness_reward_func": 1.879749994724989,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.7964325090870261,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.28125,
-      "rewards/xmlcount_reward_func": 1.0415000058710575,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.115379324562673,
-      "train_runtime": 259.4546,
-      "train_samples_per_second": 1.233,
-      "train_steps_per_second": 0.077
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 270.96875,
       "epoch": 0.1,
+      "grad_norm": 16.205791473388672,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 3.2229582499712706,
+      "reward_std": 1.0055385334417224,
+      "rewards/concensus_correctness_reward_func": 0.8008749969303608,
+      "rewards/consensus_reward_func": 0.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.5988019495271146,
       "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.171875,
+      "rewards/xmlcount_reward_func": 0.6982812527567148,
       "step": 2
     },
     {
+      "completion_length": 224.6875,
       "epoch": 0.2,
+      "grad_norm": 34.84421920776367,
+      "kl": 0.052124221707344986,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0001,
+      "reward": 5.273870535194874,
+      "reward_std": 0.9794920776039362,
+      "rewards/concensus_correctness_reward_func": 1.3452499955892563,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7844330379739404,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.1285625100135803,
       "step": 4
     },
     {
+      "completion_length": 289.03125,
       "epoch": 0.3,
+      "grad_norm": 20.824169158935547,
+      "kl": 0.22483220288995653,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0002,
+      "reward": 5.732023686170578,
+      "reward_std": 2.016730991192162,
+      "rewards/concensus_correctness_reward_func": 1.8961249869316816,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7713987100869417,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.265625,
+      "rewards/xmlcount_reward_func": 1.0488750003278255,
       "step": 6
     },
     {
+      "completion_length": 183.6875,
       "epoch": 0.4,
+      "grad_norm": 22.67264175415039,
+      "kl": 0.3627709628781304,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0004,
+      "reward": 5.419944912195206,
+      "reward_std": 1.3517259755608393,
+      "rewards/concensus_correctness_reward_func": 1.5902499887160957,
+      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.6896323460387066,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.296875,
+      "rewards/xmlcount_reward_func": 1.1556874960660934,
       "step": 8
     },
     {
+      "completion_length": 193.625,
       "epoch": 0.5,
+      "grad_norm": 19.43205451965332,
+      "kl": 0.8366234111599624,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0008,
+      "reward": 5.874577015638351,
+      "reward_std": 1.1465824714978226,
+      "rewards/concensus_correctness_reward_func": 1.7906249836087227,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.7391394600272179,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.126062497496605,
       "step": 10
     },
     {
+      "completion_length": 159.875,
       "epoch": 0.6,
+      "grad_norm": 24.322616577148438,
+      "kl": 0.8972976715303957,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0009,
+      "reward": 5.864399433135986,
+      "reward_std": 0.4836496456991881,
+      "rewards/concensus_correctness_reward_func": 1.7774374820291996,
       "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7427119584754109,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.1880000159144402,
       "step": 12
     },
     {
+      "completion_length": 219.0,
       "epoch": 0.7,
+      "grad_norm": 1444.1883544921875,
+      "kl": 38.506456029834226,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0385,
+      "reward": 5.395884931087494,
+      "reward_std": 0.9716897597536445,
+      "rewards/concensus_correctness_reward_func": 1.5414999965578318,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.801947420462966,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 1.052437499165535,
       "step": 14
     },
     {
+      "completion_length": 198.96875,
       "epoch": 0.8,
+      "grad_norm": 15.164183616638184,
+      "kl": 1.3254998605698347,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0013,
+      "reward": 5.65350778400898,
+      "reward_std": 1.3196950405836105,
+      "rewards/concensus_correctness_reward_func": 1.5979374945163727,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.8574764824006706,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.28125,
+      "rewards/xmlcount_reward_func": 1.1043437533080578,
       "step": 16
     },
     {
+      "completion_length": 148.0,
       "epoch": 0.9,
+      "grad_norm": 13.233468055725098,
+      "kl": 1.1750296542886645,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0012,
+      "reward": 6.176962792873383,
+      "reward_std": 0.6192302792333066,
+      "rewards/concensus_correctness_reward_func": 1.8604374825954437,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7856503538787365,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.2340000048279762,
       "step": 18
     },
     {
+      "completion_length": 168.34375,
       "epoch": 1.0,
+      "grad_norm": 12.352527618408203,
+      "kl": 0.4884904745267704,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0005,
+      "reward": 5.992502212524414,
+      "reward_std": 0.57326033472782,
+      "rewards/concensus_correctness_reward_func": 1.8762500043958426,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.7554397168569267,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.1733125075697899,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.004387809181207558,
+      "train_runtime": 428.4371,
+      "train_samples_per_second": 0.747,
+      "train_steps_per_second": 0.047
     }
   ],
   "logging_steps": 2,