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

d44aa2c

verified ·

1 Parent(s): 220d22e

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 +120 -120

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.016072430691565387,
-    "train_runtime": 106.3461,
     "train_samples": 28,
-    "train_samples_per_second": 3.009,
-    "train_steps_per_second": 0.188
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.9079696650529513,
+    "train_runtime": 101.7963,
     "train_samples": 28,
+    "train_samples_per_second": 3.144,
+    "train_steps_per_second": 0.196
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e025946034c737bee3b90ae59133bd623fb54916bf0dd540709af2bdd2a7bc3c
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:0f43cc549cf1f166bd38caa4c80ee010e5ec2ade2440a33167e682c22c2036a5
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.016072430691565387,
-    "train_runtime": 106.3461,
     "train_samples": 28,
-    "train_samples_per_second": 3.009,
-    "train_steps_per_second": 0.188
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.9079696650529513,
+    "train_runtime": 101.7963,
     "train_samples": 28,
+    "train_samples_per_second": 3.144,
+    "train_steps_per_second": 0.196
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 213.84375,
       "epoch": 0.5714285714285714,
-      "grad_norm": 26.995677947998047,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 3.3823529183864594,
-      "reward_std": 1.9062391401967034,
-      "rewards/concensus_correctness_reward_func": 0.9595625009387732,
-      "rewards/consensus_reward_func": 0.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.7466653931187466,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.203125,
-      "rewards/xmlcount_reward_func": 0.8479999979317654,
       "step": 2
     },
     {
-      "completion_length": 174.75,
       "epoch": 1.0,
-      "grad_norm": 23.579675674438477,
-      "kl": 0.24154430193205675,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0002,
-      "reward": 5.121496677398682,
-      "reward_std": 1.0787618570029736,
-      "rewards/concensus_correctness_reward_func": 1.4500833277901013,
-      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3333333333333333,
-      "rewards/question_recreation_reward_func": 0.8255801151196162,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.179166664679845,
       "step": 4
     },
     {
-      "completion_length": 153.84375,
       "epoch": 1.5714285714285714,
-      "grad_norm": 1652.6961669921875,
-      "kl": 103.78090217337012,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.1038,
-      "reward": 6.300249941647053,
-      "reward_std": 2.861866514198482,
-      "rewards/concensus_correctness_reward_func": 2.6995000205934048,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.8819998677354306,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.25,
       "step": 6
     },
     {
-      "completion_length": 177.33333333333334,
       "epoch": 2.0,
-      "grad_norm": 17.923799514770508,
-      "kl": 2.6989941227560243,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.002,
-      "reward": 4.556825300057729,
-      "reward_std": 0.5802585556327055,
-      "rewards/concensus_correctness_reward_func": 0.9116666615009308,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9247837464014689,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 1.2203750014305115,
       "step": 8
     },
     {
-      "completion_length": 181.28125,
       "epoch": 2.571428571428571,
-      "grad_norm": 35.15663146972656,
-      "kl": 34.417795192217454,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0344,
-      "reward": 5.128825068473816,
-      "reward_std": 1.7129042008891702,
-      "rewards/concensus_correctness_reward_func": 1.4795000199228525,
-      "rewards/consensus_reward_func": 0.875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.8573875725269318,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.1981875002384186,
       "step": 10
     },
     {
-      "completion_length": 142.25,
       "epoch": 3.0,
-      "grad_norm": 284.0204162597656,
-      "kl": 14.50094847443203,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0109,
-      "reward": 5.041350205739339,
-      "reward_std": 1.0671165152064834,
-      "rewards/concensus_correctness_reward_func": 1.109333336353302,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.9684753070274988,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.234375,
       "step": 12
     },
     {
-      "completion_length": 163.59375,
       "epoch": 3.571428571428571,
-      "grad_norm": 29.660606384277344,
-      "kl": 1.016617722576484,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.001,
-      "reward": 4.721134498715401,
-      "reward_std": 0.9181320399511606,
-      "rewards/concensus_correctness_reward_func": 1.060437509790063,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.8529157675802708,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.1984062492847443,
       "step": 14
     },
     {
-      "completion_length": 142.79166666666666,
       "epoch": 4.0,
-      "grad_norm": 19.0907039642334,
-      "kl": 1.0319154507791002,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0008,
-      "reward": 4.3834298849105835,
-      "reward_std": 1.1806894193092983,
-      "rewards/concensus_correctness_reward_func": 0.816166656712691,
-      "rewards/consensus_reward_func": 0.8333333333333334,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.16666666666666666,
-      "rewards/question_recreation_reward_func": 0.8589299271504084,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4583333333333333,
-      "rewards/xmlcount_reward_func": 1.25,
       "step": 16
     },
     {
-      "completion_length": 153.25,
       "epoch": 4.571428571428571,
-      "grad_norm": 40.38112258911133,
-      "kl": 2.6004606764763594,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0026,
-      "reward": 4.720821499824524,
-      "reward_std": 0.9005987560376525,
-      "rewards/concensus_correctness_reward_func": 1.0456249993294477,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.7951965483371168,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.40625,
-      "rewards/xmlcount_reward_func": 1.2237499989569187,
       "step": 18
     },
     {
-      "completion_length": 155.45833333333334,
       "epoch": 5.0,
-      "grad_norm": 28.315006256103516,
-      "kl": 6.73517698297898,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0051,
-      "reward": 4.186261216799418,
-      "reward_std": 1.8473886648813884,
-      "rewards/concensus_correctness_reward_func": 0.678999995191892,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.908302957812945,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.203125,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.016072430691565387,
-      "train_runtime": 106.3461,
-      "train_samples_per_second": 3.009,
-      "train_steps_per_second": 0.188
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 234.15625,
       "epoch": 0.5714285714285714,
+      "grad_norm": 27.683847427368164,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 2.5222643236629665,
+      "reward_std": 0.7037200590129942,
+      "rewards/concensus_correctness_reward_func": 0.4209374915808439,
+      "rewards/consensus_reward_func": 0.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.5930143035948277,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.140625,
+      "rewards/xmlcount_reward_func": 0.7426874951343052,
       "step": 2
     },
     {
+      "completion_length": 143.0,
       "epoch": 1.0,
+      "grad_norm": 17.122108459472656,
+      "kl": 0.16011269600130618,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0001,
+      "reward": 4.772655745347341,
+      "reward_std": 1.1716012756029766,
+      "rewards/concensus_correctness_reward_func": 0.9503333320220312,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9473223288853964,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.2291666666666667,
       "step": 4
     },
     {
+      "completion_length": 147.78125,
       "epoch": 1.5714285714285714,
+      "grad_norm": 27.48152732849121,
+      "kl": 7.6550744532141834,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0077,
+      "reward": 4.798253454267979,
+      "reward_std": 0.9606813931604847,
+      "rewards/concensus_correctness_reward_func": 1.0574374869465828,
+      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.904878459405154,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.46875,
+      "rewards/xmlcount_reward_func": 1.2421875,
       "step": 6
     },
     {
+      "completion_length": 158.75,
       "epoch": 2.0,
+      "grad_norm": 22.645151138305664,
+      "kl": 5.480011734490593,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0041,
+      "reward": 3.8781216939290366,
+      "reward_std": 1.187163884441058,
+      "rewards/concensus_correctness_reward_func": 0.5062499915560087,
+      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.866663341720899,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3541666666666667,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 8
     },
     {
+      "completion_length": 153.53125,
       "epoch": 2.571428571428571,
+      "grad_norm": 20.67380714416504,
+      "kl": 0.7204801747575402,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0007,
+      "reward": 4.249390214681625,
+      "reward_std": 1.1478300606831908,
+      "rewards/concensus_correctness_reward_func": 0.7752499897032976,
+      "rewards/consensus_reward_func": 1.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8921089824289083,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.20703125,
       "step": 10
     },
     {
+      "completion_length": 154.29166666666666,
       "epoch": 3.0,
+      "grad_norm": 73.34286499023438,
+      "kl": 4.041042095671098,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.003,
+      "reward": 5.226528386274974,
+      "reward_std": 0.5989202714990824,
+      "rewards/concensus_correctness_reward_func": 1.0834999879201253,
+      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9503200153509775,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.2135416666666667,
       "step": 12
     },
     {
+      "completion_length": 144.875,
       "epoch": 3.571428571428571,
+      "grad_norm": 39.917198181152344,
+      "kl": 2.663881789892912,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0027,
+      "reward": 4.897620126605034,
+      "reward_std": 0.5748005344066769,
+      "rewards/concensus_correctness_reward_func": 1.073999997228384,
+      "rewards/consensus_reward_func": 1.3125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8509638831019402,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.421875,
+      "rewards/xmlcount_reward_func": 1.23828125,
       "step": 14
     },
     {
+      "completion_length": 140.45833333333334,
       "epoch": 4.0,
+      "grad_norm": 31.988113403320312,
+      "kl": 14.644890550523996,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.011,
+      "reward": 3.8852972785631814,
+      "reward_std": 0.5710062601525957,
+      "rewards/concensus_correctness_reward_func": 0.6396666516860327,
+      "rewards/consensus_reward_func": 0.6666666666666666,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9227138857046763,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4166666666666667,
+      "rewards/xmlcount_reward_func": 1.2395833333333333,
       "step": 16
     },
     {
+      "completion_length": 152.03125,
       "epoch": 4.571428571428571,
+      "grad_norm": 34.18471908569336,
+      "kl": 1035.6370647158474,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 1.0356,
+      "reward": 4.561135545372963,
+      "reward_std": 1.0907168765552342,
+      "rewards/concensus_correctness_reward_func": 0.900874987244606,
+      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9539793096482754,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.2219062447547913,
       "step": 18
     },
     {
+      "completion_length": 157.41666666666666,
       "epoch": 5.0,
+      "grad_norm": 1188.0025634765625,
+      "kl": 10686.364451602101,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 8.0148,
+      "reward": 4.090836008389791,
+      "reward_std": 0.9576256484724581,
+      "rewards/concensus_correctness_reward_func": 0.594333328306675,
+      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9912943094968796,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3541666666666667,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.9079696650529513,
+      "train_runtime": 101.7963,
+      "train_samples_per_second": 3.144,
+      "train_steps_per_second": 0.196
     }
   ],
   "logging_steps": 2,