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 29, 2025

Commit

a44ac1b

verified ·

1 Parent(s): da8e356

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 +116 -116

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.015239826700417325,
-    "train_runtime": 118.3693,
     "train_samples": 28,
-    "train_samples_per_second": 2.703,
-    "train_steps_per_second": 0.169
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.007935073497719713,
+    "train_runtime": 113.8169,
     "train_samples": 28,
+    "train_samples_per_second": 2.812,
+    "train_steps_per_second": 0.176
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16cfa443886b780b898c8387b2a1cf0989c44b50986a85eb6afdfd6d191e4a6e
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:f98dcb5cbd6a82cffa80ffdfd9381d4d969960b2c9b74d820e5f7cf696a2977d
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.015239826700417325,
-    "train_runtime": 118.3693,
     "train_samples": 28,
-    "train_samples_per_second": 2.703,
-    "train_steps_per_second": 0.169
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.007935073497719713,
+    "train_runtime": 113.8169,
     "train_samples": 28,
+    "train_samples_per_second": 2.812,
+    "train_steps_per_second": 0.176
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 256.84375,
       "epoch": 0.5714285714285714,
-      "grad_norm": 13.20946216583252,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
-      "reward": 3.5172531362622976,
-      "reward_std": 1.6824106731219217,
-      "rewards/concensus_correctness_reward_func": 1.1026875022798777,
-      "rewards/consensus_reward_func": 0.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.78572190948762,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.15625,
-      "rewards/xmlcount_reward_func": 0.7225937498733401,
       "step": 2
     },
     {
-      "completion_length": 127.875,
       "epoch": 1.0,
-      "grad_norm": 17.741985321044922,
-      "kl": 0.0648303555790335,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 5.2357520659764605,
-      "reward_std": 0.7724269255219648,
-      "rewards/concensus_correctness_reward_func": 1.2560833344856899,
-      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9067520834505558,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.2395833333333333,
       "step": 4
     },
     {
-      "completion_length": 179.0,
       "epoch": 1.5714285714285714,
-      "grad_norm": 20.493099212646484,
-      "kl": 2.482064534968231,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0025,
-      "reward": 5.278004735708237,
-      "reward_std": 0.642303595377598,
-      "rewards/concensus_correctness_reward_func": 1.2840625047683716,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.837692235596478,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.203125,
       "step": 6
     },
     {
-      "completion_length": 149.66666666666666,
       "epoch": 2.0,
-      "grad_norm": 1263.5687255859375,
-      "kl": 150.79599456271777,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.1131,
-      "reward": 5.402757366498311,
-      "reward_std": 0.5394644890911877,
-      "rewards/concensus_correctness_reward_func": 1.2094166576862335,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.943340669075648,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.2083333333333333,
       "step": 8
     },
     {
-      "completion_length": 160.875,
       "epoch": 2.571428571428571,
-      "grad_norm": 78.72379302978516,
-      "kl": 8.204042462282814,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0082,
-      "reward": 5.274870753288269,
-      "reward_std": 0.8696553824120201,
-      "rewards/concensus_correctness_reward_func": 1.2636250033974648,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7846833458170295,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.2109375,
       "step": 10
     },
     {
-      "completion_length": 183.5,
       "epoch": 3.0,
-      "grad_norm": 8.092999458312988,
-      "kl": 24.662458303578507,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0185,
-      "reward": 5.748429457346599,
-      "reward_std": 0.587055459463348,
-      "rewards/concensus_correctness_reward_func": 1.476666659116745,
-      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.9488461514314016,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.1770833333333333,
       "step": 12
     },
     {
-      "completion_length": 156.65625,
       "epoch": 3.571428571428571,
-      "grad_norm": 17.131343841552734,
-      "kl": 5.732951158774085,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0057,
-      "reward": 5.7203836143016815,
-      "reward_std": 0.44315753914997913,
-      "rewards/concensus_correctness_reward_func": 1.3100624904036522,
-      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9337586387991905,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.2265625,
       "step": 14
     },
     {
-      "completion_length": 153.29166666666666,
       "epoch": 4.0,
-      "grad_norm": 9.420696258544922,
-      "kl": 0.6137937561919292,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0005,
-      "reward": 5.5632253885269165,
-      "reward_std": 0.8672101106494665,
-      "rewards/concensus_correctness_reward_func": 1.4070000052452087,
       "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.874225395421187,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.1986666669448216,
       "step": 16
     },
     {
-      "completion_length": 144.71875,
       "epoch": 4.571428571428571,
-      "grad_norm": 16.628013610839844,
-      "kl": 2.9537172889104113,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.003,
-      "reward": 5.453140243887901,
-      "reward_std": 0.9786578630446456,
-      "rewards/concensus_correctness_reward_func": 1.4116249978542328,
-      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.8579214736819267,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.24609375,
       "step": 18
     },
     {
-      "completion_length": 139.91666666666666,
       "epoch": 5.0,
-      "grad_norm": 19.892173767089844,
-      "kl": 1.238232851959765,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0009,
-      "reward": 5.744285662968953,
-      "reward_std": 0.30870523195092875,
-      "rewards/concensus_correctness_reward_func": 1.3590000023444493,
-      "rewards/consensus_reward_func": 1.9166666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9009107251962026,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3541666666666667,
-      "rewards/xmlcount_reward_func": 1.2135416666666667,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.015239826700417325,
-      "train_runtime": 118.3693,
-      "train_samples_per_second": 2.703,
-      "train_steps_per_second": 0.169
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 249.09375,
       "epoch": 0.5714285714285714,
+      "grad_norm": 15.826354026794434,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
+      "reward": 3.1409673830494285,
+      "reward_std": 0.5669145663268864,
+      "rewards/concensus_correctness_reward_func": 0.677437499165535,
+      "rewards/consensus_reward_func": 0.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6192173752933741,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.203125,
+      "rewards/xmlcount_reward_func": 0.8130624974146485,
       "step": 2
     },
     {
+      "completion_length": 141.29166666666666,
       "epoch": 1.0,
+      "grad_norm": 19.891996383666992,
+      "kl": 0.051878421756555326,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 6.275930285453796,
+      "reward_std": 0.43359654447219026,
+      "rewards/concensus_correctness_reward_func": 1.8171666612227757,
+      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9587636291980743,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4375,
+      "rewards/xmlcount_reward_func": 1.2291666666666667,
       "step": 4
     },
     {
+      "completion_length": 145.46875,
       "epoch": 1.5714285714285714,
+      "grad_norm": 35.34943771362305,
+      "kl": 4.545525601715781,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0046,
+      "reward": 5.105868987739086,
+      "reward_std": 1.0059626991860569,
+      "rewards/concensus_correctness_reward_func": 1.3870624974370003,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.815806420519948,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.1686250008642673,
       "step": 6
     },
     {
+      "completion_length": 149.16666666666666,
       "epoch": 2.0,
+      "grad_norm": 17.956090927124023,
+      "kl": 16.69708132984427,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0125,
+      "reward": 5.243768513202667,
+      "reward_std": 0.9967770762741566,
+      "rewards/concensus_correctness_reward_func": 1.380166659752528,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.8973517914613088,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3333333333333333,
+      "rewards/xmlcount_reward_func": 1.1329166665673256,
       "step": 8
     },
     {
+      "completion_length": 145.84375,
       "epoch": 2.571428571428571,
+      "grad_norm": 204.36766052246094,
+      "kl": 6.182277198997326,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0062,
+      "reward": 5.2804940938949585,
+      "reward_std": 0.7280786414630711,
+      "rewards/concensus_correctness_reward_func": 1.3514374941587448,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8353065783157945,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.21875,
       "step": 10
     },
     {
+      "completion_length": 130.20833333333334,
       "epoch": 3.0,
+      "grad_norm": 13.758617401123047,
+      "kl": 2.5372236209611096,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0019,
+      "reward": 5.9271767139434814,
+      "reward_std": 1.0066710526007228,
+      "rewards/concensus_correctness_reward_func": 1.7358333269755046,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.8788432826598486,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.1666666666666667,
       "step": 12
     },
     {
+      "completion_length": 153.09375,
       "epoch": 3.571428571428571,
+      "grad_norm": 17.412891387939453,
+      "kl": 14.441048187669367,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0144,
+      "reward": 5.792197838425636,
+      "reward_std": 0.6557959095516708,
+      "rewards/concensus_correctness_reward_func": 1.541562493890524,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.965479101985693,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.390625,
+      "rewards/xmlcount_reward_func": 1.20703125,
       "step": 14
     },
     {
+      "completion_length": 158.16666666666666,
       "epoch": 4.0,
+      "grad_norm": 36.88016891479492,
+      "kl": 49.86970095926275,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0374,
+      "reward": 5.60576315720876,
+      "reward_std": 0.6289195278271412,
+      "rewards/concensus_correctness_reward_func": 1.4773333271344502,
       "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8367630946449935,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.2291666666666667,
       "step": 16
     },
     {
+      "completion_length": 152.1875,
       "epoch": 4.571428571428571,
+      "grad_norm": 23.444311141967773,
+      "kl": 2.181370427366346,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0022,
+      "reward": 5.7395588383078575,
+      "reward_std": 0.6194086364121176,
+      "rewards/concensus_correctness_reward_func": 1.522999994456768,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8806212916970253,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.421875,
+      "rewards/xmlcount_reward_func": 1.2265625,
       "step": 18
     },
     {
+      "completion_length": 137.66666666666666,
       "epoch": 5.0,
+      "grad_norm": 5.253830909729004,
+      "kl": 0.16584620422994098,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0001,
+      "reward": 5.688922603925069,
+      "reward_std": 0.20631138902778426,
+      "rewards/concensus_correctness_reward_func": 1.5138333241144817,
+      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8782142276565233,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.007935073497719713,
+      "train_runtime": 113.8169,
+      "train_samples_per_second": 2.812,
+      "train_steps_per_second": 0.176
     }
   ],
   "logging_steps": 2,