Instructions to use 0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use 0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish with Transformers:

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

pipe = pipeline("text-generation", model="0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish")
model = AutoModelForCausalLM.from_pretrained("0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish", 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 0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish

SGLang

How to use 0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish 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 "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish" \
    --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": "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish",
		"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 "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish" \
        --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": "0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use 0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish with Docker Model Runner:
```
docker model run hf.co/0xabhay/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quick_tenacious_jellyfish
```

0xabhay commited on Apr 5, 2025

Commit

8b0f7f2

verified ·

1 Parent(s): a33dfdc

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 +101 -101

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 4.599057137966156e-06,
-    "train_runtime": 331.5049,
     "train_samples": 160,
-    "train_samples_per_second": 0.965,
-    "train_steps_per_second": 0.06
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.965649425983429e-06,
+    "train_runtime": 312.2766,
     "train_samples": 160,
+    "train_samples_per_second": 1.025,
+    "train_steps_per_second": 0.064
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:277ec960a786eb2bd76cf0673a0ab78e6ebd5920c865def6f7e3e81e48f31e7b
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:3fbe9e9cfaef92ee489a2ad087e82f34c1703c6c92a219ee132431ccdc759469
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 4.599057137966156e-06,
-    "train_runtime": 331.5049,
     "train_samples": 160,
-    "train_samples_per_second": 0.965,
-    "train_steps_per_second": 0.06
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.965649425983429e-06,
+    "train_runtime": 312.2766,
     "train_samples": 160,
+    "train_samples_per_second": 1.025,
+    "train_steps_per_second": 0.064
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 406.71875,
       "epoch": 0.1,
-      "grad_norm": 97.59458923339844,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": 0.0,
-      "reward": 0.5569465388543904,
-      "reward_std": 0.7908030303369742,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.360384039755445,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.053437501192092896,
       "step": 2
     },
     {
-      "completion_length": 443.0,
       "epoch": 0.2,
-      "grad_norm": 10.776142120361328,
-      "kl": 0.0009524735305603826,
       "learning_rate": 4.698684378016222e-07,
       "loss": 0.0,
-      "reward": 0.8668978805653751,
-      "reward_std": 0.8978493517206516,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.421710389200598,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2576874988153577,
       "step": 4
     },
     {
-      "completion_length": 516.75,
       "epoch": 0.3,
-      "grad_norm": 2.817854404449463,
-      "kl": 0.0014293095127868582,
       "learning_rate": 4.193203929064353e-07,
       "loss": 0.0,
-      "reward": 0.9116544467397034,
-      "reward_std": 0.6559535582782701,
       "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.3917794571025297,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.45737499417737126,
       "step": 6
     },
     {
-      "completion_length": 385.1875,
       "epoch": 0.4,
-      "grad_norm": 6.459072113037109,
-      "kl": 0.0010931758297374472,
       "learning_rate": 3.5042385616324236e-07,
       "loss": 0.0,
-      "reward": 0.1811784120509401,
-      "reward_std": 0.7943573236698285,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.3001159156556241,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.11893750447779894,
       "step": 8
     },
     {
-      "completion_length": 416.28125,
       "epoch": 0.5,
-      "grad_norm": 10.905441284179688,
-      "kl": 0.00129954211297445,
       "learning_rate": 2.706448363680831e-07,
       "loss": 0.0,
-      "reward": 1.7600660370662808,
-      "reward_std": 1.8061272520571947,
-      "rewards/concensus_correctness_reward_func": 0.6928749997168779,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.42084738425910473,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3338437504135072,
       "step": 10
     },
     {
-      "completion_length": 342.5625,
       "epoch": 0.6,
-      "grad_norm": 10.047685623168945,
-      "kl": 0.0013707125399378128,
       "learning_rate": 1.886286282148002e-07,
       "loss": 0.0,
-      "reward": 1.5526420985115692,
-      "reward_std": 1.2724232106702402,
-      "rewards/concensus_correctness_reward_func": 0.7098750006407499,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.4627671140478924,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.2549999924376607,
       "step": 12
     },
     {
-      "completion_length": 438.25,
       "epoch": 0.7,
-      "grad_norm": 5.062710285186768,
-      "kl": 0.002529221248551039,
       "learning_rate": 1.1326296046939333e-07,
       "loss": 0.0,
-      "reward": 0.9059852764476091,
-      "reward_std": 0.9005147942734766,
-      "rewards/concensus_correctness_reward_func": 0.10793749988079071,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.4026103091891855,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.0829374985769391,
       "step": 14
     },
     {
-      "completion_length": 410.65625,
       "epoch": 0.8,
-      "grad_norm": 6.525260925292969,
-      "kl": 0.0014621015652664937,
       "learning_rate": 5.271487265090163e-08,
       "loss": 0.0,
-      "reward": 0.8151912968605757,
-      "reward_std": 0.5487831311766058,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.3653475451283157,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.32484374940395355,
       "step": 16
     },
     {
-      "completion_length": 273.625,
       "epoch": 0.9,
-      "grad_norm": 37.5103645324707,
-      "kl": 0.03249447605048772,
       "learning_rate": 1.3545689574841341e-08,
       "loss": 0.0,
-      "reward": 1.3758334373123944,
-      "reward_std": 1.5297130271792412,
-      "rewards/concensus_correctness_reward_func": 0.6331249997019768,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.2841459293849766,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.015625,
-      "rewards/xmlcount_reward_func": 0.13043749704957008,
       "step": 18
     },
     {
-      "completion_length": 409.0,
       "epoch": 1.0,
-      "grad_norm": 7.253600120544434,
-      "kl": 0.003148767544189468,
       "learning_rate": 0.0,
       "loss": 0.0,
-      "reward": 1.1356288827955723,
-      "reward_std": 2.0710439982358366,
-      "rewards/concensus_correctness_reward_func": 0.6501874998211861,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.3790664039552212,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.08112499583512545,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 4.599057137966156e-06,
-      "train_runtime": 331.5049,
-      "train_samples_per_second": 0.965,
-      "train_steps_per_second": 0.06
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 437.53125,
       "epoch": 0.1,
+      "grad_norm": 4.8424882888793945,
       "kl": 0.0,
       "learning_rate": 4.965903258506806e-07,
       "loss": 0.0,
+      "reward": 1.2424767836928368,
+      "reward_std": 1.3980925279902294,
+      "rewards/concensus_correctness_reward_func": 0.19799999985843897,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.4963517915457487,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.17312499787658453,
       "step": 2
     },
     {
+      "completion_length": 343.53125,
       "epoch": 0.2,
+      "grad_norm": 4.962473392486572,
+      "kl": 0.0009593008035153616,
       "learning_rate": 4.698684378016222e-07,
       "loss": 0.0,
+      "reward": 1.5136843903455883,
+      "reward_std": 1.0464290648233145,
+      "rewards/concensus_correctness_reward_func": 0.38618749380111694,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.3337156834313646,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2937812586314976,
       "step": 4
     },
     {
+      "completion_length": 417.5,
       "epoch": 0.3,
+      "grad_norm": 4.399540901184082,
+      "kl": 0.0012396429829095723,
       "learning_rate": 4.193203929064353e-07,
       "loss": 0.0,
+      "reward": 0.9039205983281136,
+      "reward_std": 0.6271124193444848,
       "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.5170456022024155,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.26187500078231096,
       "step": 6
     },
     {
+      "completion_length": 438.84375,
       "epoch": 0.4,
+      "grad_norm": 5.020246505737305,
+      "kl": 0.0013312701448739972,
       "learning_rate": 3.5042385616324236e-07,
       "loss": 0.0,
+      "reward": 0.44116408098489046,
+      "reward_std": 0.9189364665653557,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.3922890628455207,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.07612498779781163,
       "step": 8
     },
     {
+      "completion_length": 331.75,
       "epoch": 0.5,
+      "grad_norm": 7.140576362609863,
+      "kl": 0.0021912034681008663,
       "learning_rate": 2.706448363680831e-07,
       "loss": 0.0,
+      "reward": 2.658341580070555,
+      "reward_std": 2.510888500371948,
+      "rewards/concensus_correctness_reward_func": 1.4297499991953373,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.49171655043028295,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.34625000646337867,
       "step": 10
     },
     {
+      "completion_length": 329.78125,
       "epoch": 0.6,
+      "grad_norm": 3.903331995010376,
+      "kl": 0.0027665450907079503,
       "learning_rate": 1.886286282148002e-07,
       "loss": 0.0,
+      "reward": 1.1588133568875492,
+      "reward_std": 0.6736997785046697,
+      "rewards/concensus_correctness_reward_func": 0.02437499910593033,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.481500833760947,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.34043748676776886,
       "step": 12
     },
     {
+      "completion_length": 400.28125,
       "epoch": 0.7,
+      "grad_norm": 4.698159694671631,
+      "kl": 0.002569452590250876,
       "learning_rate": 1.1326296046939333e-07,
       "loss": 0.0,
+      "reward": 1.884350948035717,
+      "reward_std": 1.5795070074964315,
+      "rewards/concensus_correctness_reward_func": 0.6115624997764826,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.6498196963220835,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.37296874553430825,
       "step": 14
     },
     {
+      "completion_length": 341.34375,
       "epoch": 0.8,
+      "grad_norm": 4.873336315155029,
+      "kl": 0.0027480914432089776,
       "learning_rate": 5.271487265090163e-08,
       "loss": 0.0,
+      "reward": 1.1319349324330688,
+      "reward_std": 0.6429186534369364,
+      "rewards/concensus_correctness_reward_func": 0.028562499210238457,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.5588411949574947,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.41953124897554517,
       "step": 16
     },
     {
+      "completion_length": 490.25,
       "epoch": 0.9,
+      "grad_norm": 3.5482892990112305,
+      "kl": 0.0023091254115570337,
       "learning_rate": 1.3545689574841341e-08,
       "loss": 0.0,
+      "reward": 1.1968865301460028,
+      "reward_std": 2.025821363553405,
+      "rewards/concensus_correctness_reward_func": 0.7219999991357327,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.5161052519106306,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.10371874924749136,
       "step": 18
     },
     {
+      "completion_length": 311.625,
       "epoch": 1.0,
+      "grad_norm": 4.714698314666748,
+      "kl": 0.003313427048851736,
       "learning_rate": 0.0,
       "loss": 0.0,
+      "reward": 2.276610472239554,
+      "reward_std": 1.5040997514151968,
+      "rewards/concensus_correctness_reward_func": 0.7425625007599592,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.375,
+      "rewards/question_recreation_reward_func": 0.578172966837883,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.455875005107373,
       "step": 20
     },
     {
       "epoch": 1.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 1.965649425983429e-06,
+      "train_runtime": 312.2766,
+      "train_samples_per_second": 1.025,
+      "train_steps_per_second": 0.064
     }
   ],
   "logging_steps": 2,