Instructions to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara")
model = AutoModelForCausalLM.from_pretrained("aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara

SGLang

How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara 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 "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara" \
    --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": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"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 "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara" \
        --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": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with Docker Model Runner:
```
docker model run hf.co/aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara
```

aayasmin880 commited on Apr 14, 2025

Commit

4194b7f

verified ·

1 Parent(s): e89cd38

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 +117 -117

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 49901.23018899171,
-    "train_runtime": 262.9719,
     "train_samples": 28,
-    "train_samples_per_second": 1.217,
-    "train_steps_per_second": 0.076
 }

 {
     "total_flos": 0.0,
+    "train_loss": 12557.179350649192,
+    "train_runtime": 313.5081,
     "train_samples": 28,
+    "train_samples_per_second": 1.021,
+    "train_steps_per_second": 0.064
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fde2934312d5d04871cc66a7a15ed4ebeb562fa11a25026d831c32ff6cf6e2a
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:71e25c2e14d5e63f3c46a728cc660dde808fac00dc195b10adf5c6e984bba1c9
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 49901.23018899171,
-    "train_runtime": 262.9719,
     "train_samples": 28,
-    "train_samples_per_second": 1.217,
-    "train_steps_per_second": 0.076
 }

 {
     "total_flos": 0.0,
+    "train_loss": 12557.179350649192,
+    "train_runtime": 313.5081,
     "train_samples": 28,
+    "train_samples_per_second": 1.021,
+    "train_steps_per_second": 0.064
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 239.71875,
       "epoch": 0.5714285714285714,
-      "grad_norm": 95.6217269897461,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 3.411907421424985,
-      "reward_std": 1.0213662280293647,
-      "rewards/concensus_correctness_reward_func": 0.722499992698431,
       "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.6654074005782604,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.140625,
-      "rewards/xmlcount_reward_func": 0.8833750006742775,
       "step": 2
     },
     {
-      "completion_length": 191.45833333333334,
       "epoch": 1.0,
-      "grad_norm": 90.70590209960938,
-      "kl": 11.105051194084808,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0083,
-      "reward": 5.0871754586696625,
-      "reward_std": 0.8933408875018358,
-      "rewards/concensus_correctness_reward_func": 1.6633333216110866,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.16666666666666666,
-      "rewards/question_recreation_reward_func": 0.8636337878803412,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 0.97687499721845,
       "step": 4
     },
     {
-      "completion_length": 144.8125,
       "epoch": 1.5714285714285714,
-      "grad_norm": 12763.9677734375,
-      "kl": 371160992.2142713,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 371161.0,
-      "reward": 5.649522170424461,
-      "reward_std": 0.4812943177530542,
-      "rewards/concensus_correctness_reward_func": 1.7268749810755253,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8271158672869205,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.1580312475562096,
       "step": 6
     },
     {
-      "completion_length": 158.25,
       "epoch": 2.0,
-      "grad_norm": 470.1229248046875,
-      "kl": 33.2004448591421,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0249,
-      "reward": 5.9468167424201965,
-      "reward_std": 0.557059312860171,
-      "rewards/concensus_correctness_reward_func": 1.6239999930063884,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.4166666666666667,
-      "rewards/question_recreation_reward_func": 0.8116916169722875,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.1986250032981236,
       "step": 8
     },
     {
-      "completion_length": 158.875,
       "epoch": 2.571428571428571,
-      "grad_norm": 1373.3016357421875,
-      "kl": 90.10051518678665,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0901,
-      "reward": 5.205721497535706,
-      "reward_std": 0.9359988046780927,
-      "rewards/concensus_correctness_reward_func": 1.5136249922215939,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.806252661626786,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.234375,
-      "rewards/xmlcount_reward_func": 1.0889687538146973,
       "step": 10
     },
     {
-      "completion_length": 152.33333333333334,
       "epoch": 3.0,
-      "grad_norm": 17.614341735839844,
-      "kl": 1.049506738781929,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0008,
-      "reward": 5.7788688739140825,
-      "reward_std": 0.46703821086945635,
-      "rewards/concensus_correctness_reward_func": 1.5952499856551488,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9873272279898325,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.2171249985694885,
       "step": 12
     },
     {
-      "completion_length": 160.125,
       "epoch": 3.571428571428571,
-      "grad_norm": 18237585408.0,
-      "kl": 127851017.32849634,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 127851.0234,
-      "reward": 5.240972131490707,
-      "reward_std": 0.8679977187712211,
-      "rewards/concensus_correctness_reward_func": 1.4918124862015247,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.8974408358335495,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.265625,
-      "rewards/xmlcount_reward_func": 1.086093746125698,
       "step": 14
     },
     {
-      "completion_length": 184.45833333333334,
       "epoch": 4.0,
-      "grad_norm": 31.62788963317871,
-      "kl": 5.1200584676116705,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0038,
-      "reward": 5.502565364042918,
-      "reward_std": 1.0750461738110364,
-      "rewards/concensus_correctness_reward_func": 1.5802499850591023,
-      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.8181487048665682,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.2916666666666667,
-      "rewards/xmlcount_reward_func": 1.1458333333333333,
       "step": 16
     },
     {
-      "completion_length": 193.46875,
       "epoch": 4.571428571428571,
-      "grad_norm": 41.31015396118164,
-      "kl": 56.5603180474136,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0566,
-      "reward": 5.485173583030701,
-      "reward_std": 1.1279915878549218,
-      "rewards/concensus_correctness_reward_func": 1.4998124986886978,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.8965173326432705,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.0888437516987324,
       "step": 18
     },
     {
-      "completion_length": 150.33333333333334,
       "epoch": 5.0,
-      "grad_norm": 26.81821060180664,
-      "kl": 125.25199296387534,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0939,
-      "reward": 5.590295096238454,
-      "reward_std": 0.47100249683717266,
-      "rewards/concensus_correctness_reward_func": 1.695166637500127,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.9042950918277105,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 1.157499998807907,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 49901.23018899171,
-      "train_runtime": 262.9719,
-      "train_samples_per_second": 1.217,
-      "train_steps_per_second": 0.076
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 193.03125,
       "epoch": 0.5714285714285714,
+      "grad_norm": 58.96494674682617,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 3.9653831757605076,
+      "reward_std": 1.6660508274399035,
+      "rewards/concensus_correctness_reward_func": 1.3522499948740005,
       "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.6935394024476409,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.09375,
+      "rewards/xmlcount_reward_func": 0.8258437626063824,
       "step": 2
     },
     {
+      "completion_length": 158.45833333333334,
       "epoch": 1.0,
+      "grad_norm": 11952.29296875,
+      "kl": 184.58293704595417,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.1384,
+      "reward": 4.575585693120956,
+      "reward_std": 1.3194325535247724,
+      "rewards/concensus_correctness_reward_func": 1.4599166363477707,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6824189899489284,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.14583333333333334,
+      "rewards/xmlcount_reward_func": 0.8707499926288923,
       "step": 4
     },
     {
+      "completion_length": 167.125,
       "epoch": 1.5714285714285714,
+      "grad_norm": 13332.767578125,
+      "kl": 3023.1682174415328,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 3.0232,
+      "reward": 5.874457582831383,
+      "reward_std": 0.6478101983811939,
+      "rewards/concensus_correctness_reward_func": 1.811624988913536,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.9079888015985489,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.296875,
+      "rewards/xmlcount_reward_func": 1.1079687476158142,
       "step": 6
     },
     {
+      "completion_length": 152.04166666666666,
       "epoch": 2.0,
+      "grad_norm": 79987.484375,
+      "kl": 90168.79363891482,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 67.6266,
+      "reward": 5.187588373819987,
+      "reward_std": 1.0589998407910268,
+      "rewards/concensus_correctness_reward_func": 1.417999967932701,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.8533799548943838,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.20833333333333334,
+      "rewards/xmlcount_reward_func": 1.1245416700839996,
       "step": 8
     },
     {
+      "completion_length": 157.53125,
       "epoch": 2.571428571428571,
+      "grad_norm": 3333359360.0,
+      "kl": 125493555.85986722,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 125493.5625,
+      "reward": 5.848238706588745,
+      "reward_std": 0.6607750835828483,
+      "rewards/concensus_correctness_reward_func": 1.6875624880194664,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.9156449176371098,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.265625,
+      "rewards/xmlcount_reward_func": 1.1669062599539757,
       "step": 10
     },
     {
+      "completion_length": 195.79166666666666,
       "epoch": 3.0,
+      "grad_norm": 271.3752136230469,
+      "kl": 273.68281539777917,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.2053,
+      "reward": 4.707200989127159,
+      "reward_std": 1.0174018343289692,
+      "rewards/concensus_correctness_reward_func": 1.2951666414737701,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.88674263159434,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.20833333333333334,
+      "rewards/xmlcount_reward_func": 0.9836249972383181,
       "step": 12
     },
     {
+      "completion_length": 166.96875,
       "epoch": 3.571428571428571,
+      "grad_norm": 110.81871032714844,
+      "kl": 381.98320501018316,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.382,
+      "reward": 5.036348949186504,
+      "reward_std": 0.7069780651872861,
+      "rewards/concensus_correctness_reward_func": 1.4621874764561653,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.8386613675393164,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.15625,
+      "rewards/xmlcount_reward_func": 1.016749992966652,
       "step": 14
     },
     {
+      "completion_length": 156.625,
       "epoch": 4.0,
+      "grad_norm": 134596.234375,
+      "kl": 2400.9205045119547,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 1.8007,
+      "reward": 6.160478989283244,
+      "reward_std": 0.551658857613802,
+      "rewards/concensus_correctness_reward_func": 1.9151666462421417,
+      "rewards/consensus_reward_func": 1.8333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.936062236626943,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.2916666666666667,
+      "rewards/xmlcount_reward_func": 1.1009166712562244,
       "step": 16
     },
     {
+      "completion_length": 164.0,
       "epoch": 4.571428571428571,
+      "grad_norm": 263.9651184082031,
+      "kl": 4597.32190877432,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 4.5973,
+      "reward": 5.041443020105362,
+      "reward_std": 1.1247155531891622,
+      "rewards/concensus_correctness_reward_func": 1.4394999742507935,
+      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8013805472292006,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.296875,
+      "rewards/xmlcount_reward_func": 1.066187497228384,
       "step": 18
     },
     {
+      "completion_length": 171.20833333333334,
       "epoch": 5.0,
+      "grad_norm": 50.64336395263672,
+      "kl": 610.0436264934639,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.4575,
+      "reward": 5.777886807918549,
+      "reward_std": 0.557022233454821,
+      "rewards/concensus_correctness_reward_func": 1.7898333221673965,
+      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.9035117427508036,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.2708333333333333,
+      "rewards/xmlcount_reward_func": 1.1470416635274887,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 12557.179350649192,
+      "train_runtime": 313.5081,
+      "train_samples_per_second": 1.021,
+      "train_steps_per_second": 0.064
     }
   ],
   "logging_steps": 2,