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)

# pip install -U transformers accelerate
# 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=256)
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 10, 2025

Commit

1139c35

verified ·

1 Parent(s): 81ab53f

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 +119 -119

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.00792201853514598,
-    "train_runtime": 396.9219,
     "train_samples": 160,
-    "train_samples_per_second": 0.806,
-    "train_steps_per_second": 0.05
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.002275521305273287,
+    "train_runtime": 243.325,
     "train_samples": 160,
+    "train_samples_per_second": 1.315,
+    "train_steps_per_second": 0.082
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a03cedc1516f2a0175b35cfcb5b6b62420efc3a8a14c7354499b3edc564e6b
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:11a9ea1314afb7bb302c07f5b744a49b23c6aa13d18883a521fb22420e338c72
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.00792201853514598,
-    "train_runtime": 396.9219,
     "train_samples": 160,
-    "train_samples_per_second": 0.806,
-    "train_steps_per_second": 0.05
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.002275521305273287,
+    "train_runtime": 243.325,
     "train_samples": 160,
+    "train_samples_per_second": 1.315,
+    "train_steps_per_second": 0.082
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 247.90625,
       "epoch": 0.1,
-      "grad_norm": 10.021683692932129,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": -0.0,
-      "reward": 2.4450593369547278,
-      "reward_std": 1.1119756028056145,
-      "rewards/concensus_correctness_reward_func": 0.6449374966323376,
-      "rewards/consensus_reward_func": 0.5625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.46149685559794307,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.109375,
-      "rewards/xmlcount_reward_func": 0.47924999706447124,
       "step": 2
     },
     {
-      "completion_length": 190.46875,
       "epoch": 0.2,
-      "grad_norm": 8.89192008972168,
-      "kl": 0.005316529219271615,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0,
-      "reward": 4.150590166449547,
-      "reward_std": 1.336550968058873,
-      "rewards/concensus_correctness_reward_func": 0.8426875062286854,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7316839005798101,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.2012187540531158,
       "step": 4
     },
     {
-      "completion_length": 257.09375,
       "epoch": 0.3,
-      "grad_norm": 9.808917045593262,
-      "kl": 0.8788318820152199,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0009,
-      "reward": 5.5001067370176315,
-      "reward_std": 2.3428714748006314,
-      "rewards/concensus_correctness_reward_func": 1.8922499883919954,
-      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.6502629593014717,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.1450937502086163,
       "step": 6
     },
     {
-      "completion_length": 197.78125,
       "epoch": 0.4,
-      "grad_norm": 13.780550956726074,
-      "kl": 0.06198396524996497,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0001,
-      "reward": 4.6093490421772,
-      "reward_std": 1.8008742583915591,
-      "rewards/concensus_correctness_reward_func": 1.0125624909996986,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.7031928412616253,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 1.2060937508940697,
       "step": 8
     },
     {
-      "completion_length": 176.71875,
       "epoch": 0.5,
-      "grad_norm": 10.058258056640625,
-      "kl": 0.4827866753330454,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0005,
-      "reward": 5.229237146675587,
-      "reward_std": 1.1708262786269188,
-      "rewards/concensus_correctness_reward_func": 1.386999985203147,
       "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.7719246558845043,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.2109375,
       "step": 10
     },
     {
-      "completion_length": 177.28125,
       "epoch": 0.6,
-      "grad_norm": 17.550567626953125,
-      "kl": 0.3366106414468959,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0003,
-      "reward": 4.7117330729961395,
-      "reward_std": 1.115633858833462,
-      "rewards/concensus_correctness_reward_func": 1.1793749928474426,
-      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.6730456687510014,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.328125,
-      "rewards/xmlcount_reward_func": 1.1561875008046627,
       "step": 12
     },
     {
-      "completion_length": 227.6875,
       "epoch": 0.7,
-      "grad_norm": 16.5429744720459,
-      "kl": 1.5206072250730358,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0015,
-      "reward": 4.640110909938812,
-      "reward_std": 1.7832957496866584,
-      "rewards/concensus_correctness_reward_func": 1.1444999910891056,
-      "rewards/consensus_reward_func": 1.3125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.665735860588029,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.328125,
-      "rewards/xmlcount_reward_func": 1.126749999821186,
       "step": 14
     },
     {
-      "completion_length": 178.0,
       "epoch": 0.8,
-      "grad_norm": 371.01739501953125,
-      "kl": 53.80844628554769,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0538,
-      "reward": 5.07245098054409,
-      "reward_std": 1.5081751813995652,
-      "rewards/concensus_correctness_reward_func": 1.2416250053793192,
-      "rewards/consensus_reward_func": 1.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.5625,
-      "rewards/question_recreation_reward_func": 0.612044810783118,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.265625,
-      "rewards/xmlcount_reward_func": 1.2031562477350235,
       "step": 16
     },
     {
-      "completion_length": 165.1875,
       "epoch": 0.9,
-      "grad_norm": 14.873185157775879,
-      "kl": 1.2991704902378842,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0013,
-      "reward": 5.263396844267845,
-      "reward_std": 1.1040999177785125,
-      "rewards/concensus_correctness_reward_func": 1.37393750064075,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.6318342788144946,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.265625,
-      "rewards/xmlcount_reward_func": 1.1795000061392784,
       "step": 18
     },
     {
-      "completion_length": 166.625,
       "epoch": 1.0,
-      "grad_norm": 11.289081573486328,
-      "kl": 20.827605797094293,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0208,
-      "reward": 5.335067912936211,
-      "reward_std": 1.0122177235316485,
-      "rewards/concensus_correctness_reward_func": 1.4242499899119139,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.7701930534094572,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 1.203125,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.00792201853514598,
-      "train_runtime": 396.9219,
-      "train_samples_per_second": 0.806,
-      "train_steps_per_second": 0.05
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 269.46875,
       "epoch": 0.1,
+      "grad_norm": 16.239093780517578,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0,
+      "reward": 2.880800126120448,
+      "reward_std": 1.4534732950851321,
+      "rewards/concensus_correctness_reward_func": 0.7423749938607216,
+      "rewards/consensus_reward_func": 0.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.6133938133716583,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.125,
+      "rewards/xmlcount_reward_func": 0.5875312527641654,
       "step": 2
     },
     {
+      "completion_length": 239.6875,
       "epoch": 0.2,
+      "grad_norm": 11.873531341552734,
+      "kl": 0.4248676297138445,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0004,
+      "reward": 4.384324841201305,
+      "reward_std": 1.2534358722623438,
+      "rewards/concensus_correctness_reward_func": 1.0317500084638596,
+      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7502623749896884,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 1.0398124977946281,
       "step": 4
     },
     {
+      "completion_length": 189.34375,
       "epoch": 0.3,
+      "grad_norm": 12.294513702392578,
+      "kl": 0.5999842319288291,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0006,
+      "reward": 6.2192337810993195,
+      "reward_std": 2.578816216060659,
+      "rewards/concensus_correctness_reward_func": 2.4570625368505716,
+      "rewards/consensus_reward_func": 1.3125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.6687337625771761,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.2028125002980232,
       "step": 6
     },
     {
+      "completion_length": 237.5,
       "epoch": 0.4,
+      "grad_norm": 17.53519630432129,
+      "kl": 0.30541969055775553,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0003,
+      "reward": 5.638669826090336,
+      "reward_std": 2.0600063524907455,
+      "rewards/concensus_correctness_reward_func": 2.000812502577901,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.6269823843613267,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.21875,
+      "rewards/xmlcount_reward_func": 1.1046249978244305,
       "step": 8
     },
     {
+      "completion_length": 181.53125,
       "epoch": 0.5,
+      "grad_norm": 16.81203269958496,
+      "kl": 6.670397303532809,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0067,
+      "reward": 4.776261255145073,
+      "reward_std": 1.6391612589359283,
+      "rewards/concensus_correctness_reward_func": 1.333374995738268,
       "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6030424917116761,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.234375,
+      "rewards/xmlcount_reward_func": 1.16796875,
       "step": 10
     },
     {
+      "completion_length": 166.25,
       "epoch": 0.6,
+      "grad_norm": 150.65750122070312,
+      "kl": 6.189149694982916,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0062,
+      "reward": 4.521093130111694,
+      "reward_std": 1.3719833476934582,
+      "rewards/concensus_correctness_reward_func": 1.1233749855309725,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6385931784752756,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.1809999980032444,
       "step": 12
     },
     {
+      "completion_length": 207.625,
       "epoch": 0.7,
+      "grad_norm": 10.164613723754883,
+      "kl": 8.024497827515006,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.008,
+      "reward": 4.641659140586853,
+      "reward_std": 1.794553304091096,
+      "rewards/concensus_correctness_reward_func": 1.1958125159144402,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.6910654734820127,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 1.067281249910593,
       "step": 14
     },
     {
+      "completion_length": 172.46875,
       "epoch": 0.8,
+      "grad_norm": 9.830728530883789,
+      "kl": 0.08281770371831954,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0001,
+      "reward": 6.257437109947205,
+      "reward_std": 1.0579542383784428,
+      "rewards/concensus_correctness_reward_func": 1.82268750295043,
+      "rewards/consensus_reward_func": 1.8125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.7196870775078423,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.28125,
+      "rewards/xmlcount_reward_func": 1.2463124990463257,
       "step": 16
     },
     {
+      "completion_length": 212.875,
       "epoch": 0.9,
+      "grad_norm": 10.441980361938477,
+      "kl": 0.14818275324068964,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0002,
+      "reward": 5.439556881785393,
+      "reward_std": 2.0980067034543026,
+      "rewards/concensus_correctness_reward_func": 1.7973749935626984,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7621818715706468,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 1.1924999952316284,
       "step": 18
     },
     {
+      "completion_length": 148.8125,
       "epoch": 1.0,
+      "grad_norm": 15.235068321228027,
+      "kl": 0.30819599982351065,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0003,
+      "reward": 5.189022421836853,
+      "reward_std": 1.3205067773815244,
+      "rewards/concensus_correctness_reward_func": 1.319187493994832,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7493037786334753,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.2299062460660934,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.002275521305273287,
+      "train_runtime": 243.325,
+      "train_samples_per_second": 1.315,
+      "train_steps_per_second": 0.082
     }
   ],
   "logging_steps": 2,