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 May 1, 2025

Commit

6c9cac6

verified ·

1 Parent(s): 1be2e30

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": 0.01456121146620717,
-    "train_runtime": 104.7942,
     "train_samples": 28,
-    "train_samples_per_second": 3.054,
-    "train_steps_per_second": 0.191
 }

 {
     "total_flos": 0.0,
+    "train_loss": 5571.733635760998,
+    "train_runtime": 105.8429,
     "train_samples": 28,
+    "train_samples_per_second": 3.023,
+    "train_steps_per_second": 0.189
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db8215b668d68ae02d894da3b18e90e52d68cb06ee4936437a396a8ca4a14c3a
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:5ae6da2fefec234081b1a007ce1a15c7e237ea9e596d9ce10140d079e660e4d0
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.01456121146620717,
-    "train_runtime": 104.7942,
     "train_samples": 28,
-    "train_samples_per_second": 3.054,
-    "train_steps_per_second": 0.191
 }

 {
     "total_flos": 0.0,
+    "train_loss": 5571.733635760998,
+    "train_runtime": 105.8429,
     "train_samples": 28,
+    "train_samples_per_second": 3.023,
+    "train_steps_per_second": 0.189
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 258.75,
       "epoch": 0.5714285714285714,
-      "grad_norm": 24.276386260986328,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.0,
-      "reward": 2.473452533595264,
-      "reward_std": 0.863301204983145,
-      "rewards/concensus_correctness_reward_func": 0.4078124985098839,
-      "rewards/consensus_reward_func": 0.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.6493587854201905,
-      "rewards/soft_format_reward_func": 0.015625,
-      "rewards/strict_format_reward_func": 0.1875,
-      "rewards/xmlcount_reward_func": 0.7131562496069819,
       "step": 2
     },
     {
-      "completion_length": 152.75,
       "epoch": 1.0,
-      "grad_norm": 15.70272445678711,
-      "kl": 0.0913985538451622,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0001,
-      "reward": 4.695222715536754,
-      "reward_std": 0.9066670658066869,
-      "rewards/concensus_correctness_reward_func": 1.04008333136638,
-      "rewards/consensus_reward_func": 1.0833333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9520144065221151,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.203125,
       "step": 4
     },
     {
-      "completion_length": 153.0625,
       "epoch": 1.5714285714285714,
-      "grad_norm": 282.7716369628906,
-      "kl": 21.259941923432052,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0213,
-      "reward": 3.8154746890068054,
-      "reward_std": 1.185201896354556,
-      "rewards/concensus_correctness_reward_func": 0.6304375007748604,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8139434717595577,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.23046875,
       "step": 6
     },
     {
-      "completion_length": 158.16666666666666,
       "epoch": 2.0,
-      "grad_norm": 14.254634857177734,
-      "kl": 123.83601214177907,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0929,
-      "reward": 4.6126260956128435,
-      "reward_std": 1.0945286303758621,
-      "rewards/concensus_correctness_reward_func": 0.9207499970992407,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8845844517151514,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.2447916666666667,
       "step": 8
     },
     {
-      "completion_length": 158.0,
       "epoch": 2.571428571428571,
-      "grad_norm": 44.15595626831055,
-      "kl": 23.192988209077157,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0232,
-      "reward": 4.534977212548256,
-      "reward_std": 0.9283770591719076,
-      "rewards/concensus_correctness_reward_func": 0.9546249955892563,
-      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8850397262722254,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.2265625,
       "step": 10
     },
     {
-      "completion_length": 144.5,
       "epoch": 3.0,
-      "grad_norm": 28.398914337158203,
-      "kl": 2.826799030726155,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0021,
-      "reward": 4.855075677235921,
-      "reward_std": 0.7589315362177634,
-      "rewards/concensus_correctness_reward_func": 1.0696666687726974,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9057840059200922,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.2337916791439056,
       "step": 12
     },
     {
-      "completion_length": 147.375,
       "epoch": 3.571428571428571,
-      "grad_norm": 36.5538444519043,
-      "kl": 0.723049987340346,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0006,
-      "reward": 4.739177033305168,
-      "reward_std": 0.8477327320531458,
-      "rewards/concensus_correctness_reward_func": 0.9858125001192093,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9058333383873105,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.2381562516093254,
       "step": 14
     },
     {
-      "completion_length": 180.54166666666666,
       "epoch": 4.0,
-      "grad_norm": 19.689754486083984,
-      "kl": 4.507961235009134,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0034,
-      "reward": 4.5156717002391815,
-      "reward_std": 1.0695796869695187,
-      "rewards/concensus_correctness_reward_func": 0.962583323319753,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8447550491740307,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3541666666666667,
-      "rewards/xmlcount_reward_func": 1.1875,
       "step": 16
     },
     {
-      "completion_length": 145.3125,
       "epoch": 4.571428571428571,
-      "grad_norm": 35.39835739135742,
-      "kl": 1.8185896119102836,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0018,
-      "reward": 4.79159389436245,
-      "reward_std": 0.9671289685647935,
-      "rewards/concensus_correctness_reward_func": 1.037812501192093,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8650939203798771,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.421875,
-      "rewards/xmlcount_reward_func": 1.2168124988675117,
       "step": 18
     },
     {
-      "completion_length": 166.375,
       "epoch": 5.0,
-      "grad_norm": 16.493608474731445,
-      "kl": 0.38880792989706,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0003,
-      "reward": 4.670658906300862,
-      "reward_std": 0.576637151495864,
-      "rewards/concensus_correctness_reward_func": 0.9631666590770086,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9717422922452291,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3541666666666667,
-      "rewards/xmlcount_reward_func": 1.2149166663487752,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.01456121146620717,
-      "train_runtime": 104.7942,
-      "train_samples_per_second": 3.054,
-      "train_steps_per_second": 0.191
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 223.71875,
       "epoch": 0.5714285714285714,
+      "grad_norm": 31.614778518676758,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": -0.0,
+      "reward": 2.9653216637670994,
+      "reward_std": 1.4805789864331018,
+      "rewards/concensus_correctness_reward_func": 0.4098124969750643,
+      "rewards/consensus_reward_func": 0.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.7164467088878155,
+      "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.203125,
+      "rewards/xmlcount_reward_func": 0.9484374951571226,
       "step": 2
     },
     {
+      "completion_length": 151.20833333333334,
       "epoch": 1.0,
+      "grad_norm": 19.80303192138672,
+      "kl": 0.10296421435972054,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0001,
+      "reward": 5.499126513799031,
+      "reward_std": 0.53629773731033,
+      "rewards/concensus_correctness_reward_func": 1.334166665871938,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8379182033240795,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.181208332379659,
       "step": 4
     },
     {
+      "completion_length": 143.59375,
       "epoch": 1.5714285714285714,
+      "grad_norm": 34.6270751953125,
+      "kl": 2.8533220877870917,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0029,
+      "reward": 5.050898350775242,
+      "reward_std": 1.3527698878897354,
+      "rewards/concensus_correctness_reward_func": 1.2711875047534704,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7718983719823882,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.421875,
+      "rewards/xmlcount_reward_func": 1.2109375,
       "step": 6
     },
     {
+      "completion_length": 160.66666666666666,
       "epoch": 2.0,
+      "grad_norm": 15.381648063659668,
+      "kl": 11.692268824204803,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0088,
+      "reward": 4.899051864941915,
+      "reward_std": 0.8737152467171351,
+      "rewards/concensus_correctness_reward_func": 0.8280833214521408,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8834685583909353,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4375,
+      "rewards/xmlcount_reward_func": 1.25,
       "step": 8
     },
     {
+      "completion_length": 171.3125,
       "epoch": 2.571428571428571,
+      "grad_norm": 1969201920.0,
+      "kl": 55716476.06210626,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 55716.4805,
+      "reward": 4.228640131652355,
+      "reward_std": 0.9665384208783507,
+      "rewards/concensus_correctness_reward_func": 0.6550625003874302,
+      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.886077631264925,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.25,
       "step": 10
     },
     {
+      "completion_length": 160.875,
       "epoch": 3.0,
+      "grad_norm": 15.754578590393066,
+      "kl": 34.520431245987616,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0259,
+      "reward": 4.905407538016637,
+      "reward_std": 0.4380470165245545,
+      "rewards/concensus_correctness_reward_func": 1.046166663368543,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.859240879615148,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.2083333333333333,
       "step": 12
     },
     {
+      "completion_length": 173.03125,
       "epoch": 3.571428571428571,
+      "grad_norm": 43.54138946533203,
+      "kl": 788.5391242853366,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.7885,
+      "reward": 4.416811063885689,
+      "reward_std": 1.3936654469143832,
+      "rewards/concensus_correctness_reward_func": 0.8432500008493662,
+      "rewards/consensus_reward_func": 1.1875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8274673502892256,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.21484375,
       "step": 14
     },
     {
+      "completion_length": 165.16666666666666,
       "epoch": 4.0,
+      "grad_norm": 25.31414031982422,
+      "kl": 6.561875412861506,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0049,
+      "reward": 4.753732244173686,
+      "reward_std": 1.579458454468598,
+      "rewards/concensus_correctness_reward_func": 1.0581666653354962,
+      "rewards/consensus_reward_func": 1.0833333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.9195239692926407,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 16
     },
     {
+      "completion_length": 158.78125,
       "epoch": 4.571428571428571,
+      "grad_norm": 25.638328552246094,
+      "kl": 15.994928859174252,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.016,
+      "reward": 4.85489359498024,
+      "reward_std": 1.2258785646408796,
+      "rewards/concensus_correctness_reward_func": 1.0678125005215406,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8339561484754086,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.390625,
+      "rewards/xmlcount_reward_func": 1.1875,
       "step": 18
     },
     {
+      "completion_length": 162.125,
       "epoch": 5.0,
+      "grad_norm": 18.205522537231445,
+      "kl": 11.792570936183134,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0088,
+      "reward": 4.547471563021342,
+      "reward_std": 0.43150439858436584,
+      "rewards/concensus_correctness_reward_func": 0.9048333416382471,
+      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.9553049008051554,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.2290000021457672,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 5571.733635760998,
+      "train_runtime": 105.8429,
+      "train_samples_per_second": 3.023,
+      "train_steps_per_second": 0.189
     }
   ],
   "logging_steps": 2,