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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("benfielding/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feathered_stalking_ladybug")
model = AutoModelForMultimodalLM.from_pretrained("benfielding/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feathered_stalking_ladybug")
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 benfielding/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feathered_stalking_ladybug with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/benfielding/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-feathered_stalking_ladybug

SGLang

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

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

benfielding commited on Apr 14, 2025

Commit

3409fc3

verified ·

1 Parent(s): c4a6197

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 +114 -114

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.18189025411120383,
-    "train_runtime": 97.0582,
     "train_samples": 28,
-    "train_samples_per_second": 3.297,
-    "train_steps_per_second": 0.206
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.003102183849841822,
+    "train_runtime": 99.7531,
     "train_samples": 28,
+    "train_samples_per_second": 3.208,
+    "train_steps_per_second": 0.2
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63cf13b6f914951ed69ac8813f9e6d51cef1576af8c6c84a2ef83eac87a1c056
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:a30df9e4891a4e527df9555e64d3b0d0afc6dee2068c748ceaf96e10364fa618
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.18189025411120383,
-    "train_runtime": 97.0582,
     "train_samples": 28,
-    "train_samples_per_second": 3.297,
-    "train_steps_per_second": 0.206
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.003102183849841822,
+    "train_runtime": 99.7531,
     "train_samples": 28,
+    "train_samples_per_second": 3.208,
+    "train_steps_per_second": 0.2
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 218.84375,
       "epoch": 0.5714285714285714,
-      "grad_norm": 16.413349151611328,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": -0.0,
-      "reward": 3.463685939088464,
-      "reward_std": 0.7034649187116884,
-      "rewards/concensus_correctness_reward_func": 0.7219999879598618,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7888422352261841,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.15625,
-      "rewards/xmlcount_reward_func": 0.7340937531553209,
       "step": 2
     },
     {
-      "completion_length": 136.70833333333334,
       "epoch": 1.0,
-      "grad_norm": 16.801883697509766,
-      "kl": 0.11107732852300008,
       "learning_rate": 4.698684378016222e-07,
-      "loss": 0.0001,
-      "reward": 5.620846748352051,
-      "reward_std": 0.8283557544151942,
-      "rewards/concensus_correctness_reward_func": 1.700999992589156,
-      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.9094300220410029,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.2916666666666667,
-      "rewards/xmlcount_reward_func": 1.1354166666666667,
       "step": 4
     },
     {
-      "completion_length": 137.625,
       "epoch": 1.5714285714285714,
-      "grad_norm": 1251.4542236328125,
-      "kl": 29.201528461358976,
       "learning_rate": 4.193203929064353e-07,
-      "loss": 0.0292,
-      "reward": 6.083442434668541,
-      "reward_std": 0.6032323502004147,
-      "rewards/concensus_correctness_reward_func": 1.8181874863803387,
-      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9065674878656864,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.375,
-      "rewards/xmlcount_reward_func": 1.1711875014007092,
       "step": 6
     },
     {
-      "completion_length": 141.95833333333334,
       "epoch": 2.0,
-      "grad_norm": 80.33175659179688,
-      "kl": 2238.1095382701606,
       "learning_rate": 3.5042385616324236e-07,
-      "loss": 1.6786,
-      "reward": 5.476725300153096,
-      "reward_std": 0.5055693089962006,
-      "rewards/concensus_correctness_reward_func": 1.338249978919824,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.9041003783543905,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3541666666666667,
-      "rewards/xmlcount_reward_func": 1.2135416666666667,
       "step": 8
     },
     {
-      "completion_length": 140.0625,
       "epoch": 2.571428571428571,
-      "grad_norm": 5685.56640625,
-      "kl": 73.77052622684278,
       "learning_rate": 2.706448363680831e-07,
-      "loss": 0.0738,
-      "reward": 6.193239971995354,
-      "reward_std": 1.6658249166794121,
-      "rewards/concensus_correctness_reward_func": 1.9971249867230654,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.9472400806844234,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.359375,
-      "rewards/xmlcount_reward_func": 1.2019999995827675,
       "step": 10
     },
     {
-      "completion_length": 127.08333333333333,
       "epoch": 3.0,
-      "grad_norm": 9.540337562561035,
-      "kl": 3.0621676202863455,
       "learning_rate": 1.886286282148002e-07,
-      "loss": 0.0023,
-      "reward": 5.709832270940145,
-      "reward_std": 0.3538346770995607,
-      "rewards/concensus_correctness_reward_func": 1.5369999806086223,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.988540584842364,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3958333333333333,
-      "rewards/xmlcount_reward_func": 1.2051250040531158,
       "step": 12
     },
     {
-      "completion_length": 132.15625,
       "epoch": 3.571428571428571,
-      "grad_norm": 16.967500686645508,
-      "kl": 11.426087894011289,
       "learning_rate": 1.1326296046939333e-07,
-      "loss": 0.0114,
-      "reward": 5.505586206912994,
-      "reward_std": 0.27794025372713804,
-      "rewards/concensus_correctness_reward_func": 1.4691874869167805,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9235549308359623,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.2065937519073486,
       "step": 14
     },
     {
-      "completion_length": 134.25,
       "epoch": 4.0,
-      "grad_norm": 16.20191192626953,
-      "kl": 2.2744216828917465,
       "learning_rate": 5.271487265090163e-08,
-      "loss": 0.0017,
-      "reward": 6.086844245592753,
-      "reward_std": 0.542460098862648,
-      "rewards/concensus_correctness_reward_func": 1.7269999807079632,
-      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.16666666666666666,
-      "rewards/question_recreation_reward_func": 0.9250942468643188,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.3125,
-      "rewards/xmlcount_reward_func": 1.2055833339691162,
       "step": 16
     },
     {
-      "completion_length": 149.78125,
       "epoch": 4.571428571428571,
-      "grad_norm": 23.975969314575195,
-      "kl": 21.27271423127968,
       "learning_rate": 1.3545689574841341e-08,
-      "loss": 0.0213,
-      "reward": 5.366471603512764,
-      "reward_std": 0.9596925657242537,
-      "rewards/concensus_correctness_reward_func": 1.4007499851286411,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9201591331511736,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.34375,
-      "rewards/xmlcount_reward_func": 1.201812505722046,
       "step": 18
     },
     {
-      "completion_length": 143.20833333333334,
       "epoch": 5.0,
-      "grad_norm": 22.604459762573242,
-      "kl": 0.7605764990051588,
       "learning_rate": 0.0,
-      "loss": 0.0006,
-      "reward": 6.170487980047862,
-      "reward_std": 1.3884001096788172,
-      "rewards/concensus_correctness_reward_func": 2.157916652659575,
-      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.8883628845214844,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3333333333333333,
-      "rewards/xmlcount_reward_func": 1.1242083335916202,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.18189025411120383,
-      "train_runtime": 97.0582,
-      "train_samples_per_second": 3.297,
-      "train_steps_per_second": 0.206
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 231.34375,
       "epoch": 0.5714285714285714,
+      "grad_norm": 16.492544174194336,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": -0.0,
+      "reward": 3.2328345319256186,
+      "reward_std": 0.9783206325955689,
+      "rewards/concensus_correctness_reward_func": 0.8361874893307686,
+      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6478658077539876,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.171875,
+      "rewards/xmlcount_reward_func": 0.6394062614999712,
       "step": 2
     },
     {
+      "completion_length": 143.125,
       "epoch": 1.0,
+      "grad_norm": 17.42470932006836,
+      "kl": 1.0515111999896665,
       "learning_rate": 4.698684378016222e-07,
+      "loss": 0.0008,
+      "reward": 6.118789633115132,
+      "reward_std": 0.5062633926669756,
+      "rewards/concensus_correctness_reward_func": 1.8602499937017758,
+      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.8853313426176707,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.1440416673819225,
       "step": 4
     },
     {
+      "completion_length": 174.75,
       "epoch": 1.5714285714285714,
+      "grad_norm": 33.48395538330078,
+      "kl": 0.9248551621567458,
       "learning_rate": 4.193203929064353e-07,
+      "loss": 0.0009,
+      "reward": 6.172242045402527,
+      "reward_std": 0.8660736695746891,
+      "rewards/concensus_correctness_reward_func": 1.8191874995827675,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.9246483221650124,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.328125,
+      "rewards/xmlcount_reward_func": 1.1627812534570694,
       "step": 6
     },
     {
+      "completion_length": 142.33333333333334,
       "epoch": 2.0,
+      "grad_norm": 4.0898637771606445,
+      "kl": 13.09252843276287,
       "learning_rate": 3.5042385616324236e-07,
+      "loss": 0.0098,
+      "reward": 5.506042867898941,
+      "reward_std": 0.1585460032025973,
+      "rewards/concensus_correctness_reward_func": 1.36199997117122,
+      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8950429558753967,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3541666666666667,
+      "rewards/xmlcount_reward_func": 1.2281666696071625,
       "step": 8
     },
     {
+      "completion_length": 148.09375,
       "epoch": 2.571428571428571,
+      "grad_norm": 20.544994354248047,
+      "kl": 0.20679084211587906,
       "learning_rate": 2.706448363680831e-07,
+      "loss": 0.0002,
+      "reward": 6.074036613106728,
+      "reward_std": 0.4208658505231142,
+      "rewards/concensus_correctness_reward_func": 1.6786874923855066,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9582866095006466,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.359375,
+      "rewards/xmlcount_reward_func": 1.2026875019073486,
       "step": 10
     },
     {
+      "completion_length": 142.08333333333334,
       "epoch": 3.0,
+      "grad_norm": 12.539798736572266,
+      "kl": 1.9412451159829895,
       "learning_rate": 1.886286282148002e-07,
+      "loss": 0.0015,
+      "reward": 5.9972803592681885,
+      "reward_std": 0.33201182817962643,
+      "rewards/concensus_correctness_reward_func": 1.6988333066304524,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.959905336300532,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3541666666666667,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 12
     },
     {
+      "completion_length": 152.96875,
       "epoch": 3.571428571428571,
+      "grad_norm": 20.224119186401367,
+      "kl": 2.265282135573216,
       "learning_rate": 1.1326296046939333e-07,
+      "loss": 0.0023,
+      "reward": 5.725323170423508,
+      "reward_std": 0.3783342079841532,
+      "rewards/concensus_correctness_reward_func": 1.5473749861121178,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9678856916725636,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 1.2100625038146973,
       "step": 14
     },
     {
+      "completion_length": 149.625,
       "epoch": 4.0,
+      "grad_norm": 8.149849891662598,
+      "kl": 19.414008408008765,
       "learning_rate": 5.271487265090163e-08,
+      "loss": 0.0146,
+      "reward": 6.496492862701416,
+      "reward_std": 0.5013119105133228,
+      "rewards/concensus_correctness_reward_func": 1.8748333180944126,
+      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3333333333333333,
+      "rewards/question_recreation_reward_func": 0.9792429457108179,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3958333333333333,
+      "rewards/xmlcount_reward_func": 1.246583342552185,
       "step": 16
     },
     {
+      "completion_length": 133.59375,
       "epoch": 4.571428571428571,
+      "grad_norm": 20.782503128051758,
+      "kl": 0.5615797373466194,
       "learning_rate": 1.3545689574841341e-08,
+      "loss": 0.0006,
+      "reward": 5.805923208594322,
+      "reward_std": 0.5979153233929537,
+      "rewards/concensus_correctness_reward_func": 1.5301249884068966,
+      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.9401107653975487,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.375,
+      "rewards/xmlcount_reward_func": 1.2106875032186508,
       "step": 18
     },
     {
+      "completion_length": 159.125,
       "epoch": 5.0,
+      "grad_norm": 15.212947845458984,
+      "kl": 0.5920004791890582,
       "learning_rate": 0.0,
+      "loss": 0.0005,
+      "reward": 5.606375018755595,
+      "reward_std": 0.5743791684508324,
+      "rewards/concensus_correctness_reward_func": 1.5080833211541176,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.891125018397967,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.3333333333333333,
+      "rewards/xmlcount_reward_func": 1.2071666618188222,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.003102183849841822,
+      "train_runtime": 99.7531,
+      "train_samples_per_second": 3.208,
+      "train_steps_per_second": 0.2
     }
   ],
   "logging_steps": 2,