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

5ca5adc

verified ·

1 Parent(s): e9dd9f1

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": 0.0013754309693467803,
-    "train_runtime": 484.3785,
     "train_samples": 160,
-    "train_samples_per_second": 0.661,
-    "train_steps_per_second": 0.041
 }

 {
     "total_flos": 0.0,
+    "train_loss": 251.78188937576107,
+    "train_runtime": 294.9846,
     "train_samples": 160,
+    "train_samples_per_second": 1.085,
+    "train_steps_per_second": 0.068
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f97c2a0ff6f7b1416e4facc086062b10fc9051ff576ccd5eef41de004de7ae
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:0057bae9352aa235822a8b16298eb4fb77d770dc0d933a82d3fe56a604ddf159
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0013754309693467803,
-    "train_runtime": 484.3785,
     "train_samples": 160,
-    "train_samples_per_second": 0.661,
-    "train_steps_per_second": 0.041
 }

 {
     "total_flos": 0.0,
+    "train_loss": 251.78188937576107,
+    "train_runtime": 294.9846,
     "train_samples": 160,
+    "train_samples_per_second": 1.085,
+    "train_steps_per_second": 0.068
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 239.96875,
       "epoch": 0.1,
-      "grad_norm": 14.757119178771973,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
-      "reward": 4.141140762716532,
-      "reward_std": 2.135552801191807,
-      "rewards/concensus_correctness_reward_func": 1.4067499954253435,
-      "rewards/consensus_reward_func": 0.8125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6212345045059919,
       "rewards/soft_format_reward_func": 0.015625,
-      "rewards/strict_format_reward_func": 0.140625,
-      "rewards/xmlcount_reward_func": 0.8944062516093254,
       "step": 2
     },
     {
-      "completion_length": 195.65625,
       "epoch": 0.2,
-      "grad_norm": 13.58037281036377,
-      "kl": 0.011399912415072322,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0,
-      "reward": 5.415508016943932,
-      "reward_std": 2.055123375263065,
-      "rewards/concensus_correctness_reward_func": 1.609812529757619,
-      "rewards/consensus_reward_func": 1.3125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.7978829508647323,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.2265625,
       "step": 4
     },
     {
-      "completion_length": 194.21875,
       "epoch": 0.3,
-      "grad_norm": 12.860827445983887,
-      "kl": 0.021882248751353472,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 4.905243486166,
-      "reward_std": 0.8757127709686756,
-      "rewards/concensus_correctness_reward_func": 1.192249994724989,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.5915559427812696,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.2151875048875809,
       "step": 6
     },
     {
-      "completion_length": 262.5625,
       "epoch": 0.4,
-      "grad_norm": 14.72692584991455,
-      "kl": 0.11686136166099459,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0001,
-      "reward": 5.4161528795957565,
-      "reward_std": 1.402472271467559,
-      "rewards/concensus_correctness_reward_func": 1.487437496893108,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.6943403414916247,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.140625,
       "step": 8
     },
     {
-      "completion_length": 165.21875,
       "epoch": 0.5,
-      "grad_norm": 15.326648712158203,
-      "kl": 0.3416352487402037,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0003,
-      "reward": 5.379797145724297,
-      "reward_std": 1.3166494268225506,
-      "rewards/concensus_correctness_reward_func": 1.4649374894797802,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.7547033838927746,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.22265625,
       "step": 10
     },
     {
-      "completion_length": 144.1875,
       "epoch": 0.6,
-      "grad_norm": 16.668014526367188,
-      "kl": 5.399480640422553,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0054,
-      "reward": 4.270255737006664,
-      "reward_std": 1.8121604117623065,
-      "rewards/concensus_correctness_reward_func": 0.9575624875724316,
-      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.629099409095943,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.16796875,
       "step": 12
     },
     {
-      "completion_length": 185.375,
       "epoch": 0.7,
-      "grad_norm": 12.288613319396973,
-      "kl": 0.6827053101733327,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0007,
-      "reward": 5.141661882400513,
-      "reward_std": 0.7572070101741701,
-      "rewards/concensus_correctness_reward_func": 1.4605000037699938,
       "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.7367555964738131,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.28125,
-      "rewards/xmlcount_reward_func": 1.1006562560796738,
       "step": 14
     },
     {
-      "completion_length": 164.03125,
       "epoch": 0.8,
-      "grad_norm": 15.52062702178955,
-      "kl": 1.212333734758431,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0012,
-      "reward": 6.140733391046524,
-      "reward_std": 1.1298037951346487,
-      "rewards/concensus_correctness_reward_func": 1.7470625024288893,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.4375,
-      "rewards/question_recreation_reward_func": 0.7061708739493042,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.25,
       "step": 16
     },
     {
-      "completion_length": 190.8125,
       "epoch": 0.9,
-      "grad_norm": 16.11543083190918,
-      "kl": 0.662576879694825,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0007,
-      "reward": 5.2932950630784035,
-      "reward_std": 1.04986025391554,
-      "rewards/concensus_correctness_reward_func": 1.4145000018179417,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.741638807579875,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.1371562499552965,
       "step": 18
     },
     {
-      "completion_length": 134.65625,
       "epoch": 1.0,
-      "grad_norm": 17.023681640625,
-      "kl": 5.301454717176966,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0053,
-      "reward": 6.571171820163727,
-      "reward_std": 1.634692385821836,
-      "rewards/concensus_correctness_reward_func": 2.174499996006489,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.5,
-      "rewards/question_recreation_reward_func": 0.7169843837618828,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.390625,
-      "rewards/xmlcount_reward_func": 1.2265625,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.0013754309693467803,
-      "train_runtime": 484.3785,
-      "train_samples_per_second": 0.661,
-      "train_steps_per_second": 0.041
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 254.125,
       "epoch": 0.1,
+      "grad_norm": 16.38307762145996,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
+      "reward": 3.2895670142024755,
+      "reward_std": 1.2456239042803645,
+      "rewards/concensus_correctness_reward_func": 0.8370625004172325,
+      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.5819107657298446,
       "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.1875,
+      "rewards/xmlcount_reward_func": 0.6674687508493662,
       "step": 2
     },
     {
+      "completion_length": 183.84375,
       "epoch": 0.2,
+      "grad_norm": 12.496358871459961,
+      "kl": 0.051146795420208946,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0001,
+      "reward": 5.762638598680496,
+      "reward_std": 1.1377782532945275,
+      "rewards/concensus_correctness_reward_func": 1.8422499932348728,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7595135774463415,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.1921250075101852,
       "step": 4
     },
     {
+      "completion_length": 218.09375,
       "epoch": 0.3,
+      "grad_norm": 11.679012298583984,
+      "kl": 0.01872272753098514,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 6.035256557166576,
+      "reward_std": 1.78839290952601,
+      "rewards/concensus_correctness_reward_func": 2.0680624954402447,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.7389754406176507,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.265625,
+      "rewards/xmlcount_reward_func": 1.150093749165535,
       "step": 6
     },
     {
+      "completion_length": 181.03125,
       "epoch": 0.4,
+      "grad_norm": 13.289280891418457,
+      "kl": 0.17071511584799737,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0002,
+      "reward": 5.142755076289177,
+      "reward_std": 1.001112039492,
+      "rewards/concensus_correctness_reward_func": 1.3203749912790954,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.6426925261039287,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.2421875,
       "step": 8
     },
     {
+      "completion_length": 147.78125,
       "epoch": 0.5,
+      "grad_norm": 21.36635971069336,
+      "kl": 0.1995731678325683,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0002,
+      "reward": 5.977291479706764,
+      "reward_std": 1.3045521031599492,
+      "rewards/concensus_correctness_reward_func": 1.794187493622303,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.5981664708815515,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.1474375016987324,
       "step": 10
     },
     {
+      "completion_length": 198.4375,
       "epoch": 0.6,
+      "grad_norm": 3472.832763671875,
+      "kl": 114.03248847631039,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.114,
+      "reward": 6.0456173568964005,
+      "reward_std": 1.7038903646171093,
+      "rewards/concensus_correctness_reward_func": 2.1562499701976776,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7069298811256886,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.34375,
+      "rewards/xmlcount_reward_func": 1.0886874999850988,
       "step": 12
     },
     {
+      "completion_length": 238.09375,
       "epoch": 0.7,
+      "grad_norm": 14.8486909866333,
+      "kl": 0.07892771833576262,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0001,
+      "reward": 5.186425641179085,
+      "reward_std": 1.8659816924482584,
+      "rewards/concensus_correctness_reward_func": 1.3852500077337027,
       "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8363318489864469,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.08984375,
       "step": 14
     },
     {
+      "completion_length": 176.71875,
       "epoch": 0.8,
+      "grad_norm": 14.234199523925781,
+      "kl": 0.13149000180419534,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0001,
+      "reward": 6.3964873701334,
+      "reward_std": 0.8963722591288388,
+      "rewards/concensus_correctness_reward_func": 1.935312494635582,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.7384873954579234,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.2226874977350235,
       "step": 16
     },
     {
+      "completion_length": 211.9375,
       "epoch": 0.9,
+      "grad_norm": 19.819805145263672,
+      "kl": 0.1073005007347092,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0001,
+      "reward": 5.26567505300045,
+      "reward_std": 1.0731214464176446,
+      "rewards/concensus_correctness_reward_func": 1.2814374975860119,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.7554562967270613,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.1662812493741512,
       "step": 18
     },
     {
+      "completion_length": 167.9375,
       "epoch": 1.0,
+      "grad_norm": 15.449546813964844,
+      "kl": 2517704.110972635,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 2517.7041,
+      "reward": 5.996514692902565,
+      "reward_std": 1.6410091544967145,
+      "rewards/concensus_correctness_reward_func": 1.937749994918704,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8407647274434566,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.1711249947547913,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 251.78188937576107,
+      "train_runtime": 294.9846,
+      "train_samples_per_second": 1.085,
+      "train_steps_per_second": 0.068
     }
   ],
   "logging_steps": 2,