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

Libraries

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

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

pipe = pipeline("text-generation", model="Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel")
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("Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel")
model = AutoModelForCausalLM.from_pretrained("Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Slaughtering/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-fierce_padded_camel

SGLang

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

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

Slaughtering commited on Apr 29, 2025

Commit

28065f8

verified ·

1 Parent(s): aaa7db3

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 +52 -52

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0001302163553191349,
-    "train_runtime": 3756.704,
     "train_samples": 17,
-    "train_samples_per_second": 0.043,
-    "train_steps_per_second": 0.003
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.2571450588438892e-05,
+    "train_runtime": 2664.5232,
     "train_samples": 17,
+    "train_samples_per_second": 0.06,
+    "train_steps_per_second": 0.004
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4b488c87a86c1049b83120ac5aac0c9ba7ac485fe23c7db38d9287f3bdc6b0
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:d54b7bd4c0bce5bac0be4cef36a7b13049947b90b8f832b7a94ac550988f6fd1
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0001302163553191349,
-    "train_runtime": 3756.704,
     "train_samples": 17,
-    "train_samples_per_second": 0.043,
-    "train_steps_per_second": 0.003
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.2571450588438892e-05,
+    "train_runtime": 2664.5232,
     "train_samples": 17,
+    "train_samples_per_second": 0.06,
+    "train_steps_per_second": 0.004
 }

trainer_state.json CHANGED Viewed

@@ -10,108 +10,108 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 195.21875,
       "epoch": 0.9411764705882353,
-      "grad_norm": 7.29820442199707,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 0.3859232247341424,
-      "reward_std": 0.29110795067390427,
-      "rewards/concensus_correctness_reward_func": 0.057874999940395355,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.15576697533833794,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.04728125035762787,
       "step": 2
     },
     {
-      "completion_length": 53.333333333333336,
       "epoch": 1.4705882352941178,
-      "grad_norm": 69.11537170410156,
-      "kl": 0.16177160591663173,
       "learning_rate": 4.415111107797445e-07,
-      "loss": 0.0001,
-      "reward": 1.9489911780175235,
-      "reward_std": 1.5645073917176988,
-      "rewards/concensus_correctness_reward_func": 0.7521111071109772,
-      "rewards/consensus_reward_func": 1.1111111111111112,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.0982133796852496,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.012444444000720978,
       "step": 4
     },
     {
-      "completion_length": 100.66666666666667,
       "epoch": 2.0,
-      "grad_norm": 0.0016701951390132308,
-      "kl": 0.10335994858501686,
       "learning_rate": 2.934120444167326e-07,
-      "loss": 0.0001,
-      "reward": 1.0154777467250824,
-      "reward_std": 0.2517763171474346,
-      "rewards/concensus_correctness_reward_func": 0.36088888843854267,
-      "rewards/consensus_reward_func": 0.5555555555555556,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.09208885813131928,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.006944444444444444,
       "step": 6
     },
     {
-      "completion_length": 52.125,
       "epoch": 2.9411764705882355,
-      "grad_norm": 8.132813453674316,
-      "kl": 0.2391383937210776,
       "learning_rate": 1.2500000000000005e-07,
-      "loss": 0.0002,
-      "reward": 2.033643968985416,
-      "reward_std": 0.24482828610598517,
-      "rewards/concensus_correctness_reward_func": 0.7947499975562096,
-      "rewards/consensus_reward_func": 1.0625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.10820648208027706,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.068187499884516,
       "step": 8
     },
     {
-      "completion_length": 7.0,
       "epoch": 3.4705882352941178,
-      "grad_norm": 22.0374813079834,
-      "kl": 0.4673060178756714,
       "learning_rate": 1.507684480352292e-08,
-      "loss": 0.0003,
-      "reward": 2.54876180489858,
-      "reward_std": 0.7480697764290704,
-      "rewards/concensus_correctness_reward_func": 1.085111101468404,
-      "rewards/consensus_reward_func": 1.4444444444444444,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.019206267988516226,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.0,
       "step": 10
     },
     {
       "epoch": 3.4705882352941178,
       "step": 10,
       "total_flos": 0.0,
-      "train_loss": 0.0001302163553191349,
-      "train_runtime": 3756.704,
-      "train_samples_per_second": 0.043,
-      "train_steps_per_second": 0.003
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 64.09375,
       "epoch": 0.9411764705882353,
+      "grad_norm": 31.377328872680664,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 2.883558839559555,
+      "reward_std": 1.1215332573665364,
+      "rewards/concensus_correctness_reward_func": 1.1368124894797802,
+      "rewards/consensus_reward_func": 1.1875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.237652589159552,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.32159374793991446,
       "step": 2
     },
     {
+      "completion_length": 72.55555555555556,
       "epoch": 1.4705882352941178,
+      "grad_norm": 13.316970825195312,
+      "kl": 0.008080047096074041,
       "learning_rate": 4.415111107797445e-07,
+      "loss": 0.0,
+      "reward": 3.0239129294123916,
+      "reward_std": 0.7411516199095382,
+      "rewards/concensus_correctness_reward_func": 1.2795555525355868,
+      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.2539129143891235,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.15711111492580837,
       "step": 4
     },
     {
+      "completion_length": 85.33333333333333,
       "epoch": 2.0,
+      "grad_norm": 4.109074143343605e-05,
+      "kl": 0.04780876358078482,
       "learning_rate": 2.934120444167326e-07,
+      "loss": 0.0,
+      "reward": 2.12345541599724,
+      "reward_std": 1.6556567519696221,
+      "rewards/concensus_correctness_reward_func": 0.8527777658568488,
+      "rewards/consensus_reward_func": 0.8888888888888888,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.19951097123945752,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18227777712874943,
       "step": 6
     },
     {
+      "completion_length": 57.875,
       "epoch": 2.9411764705882355,
+      "grad_norm": 15.806655883789062,
+      "kl": 0.01811496782465838,
       "learning_rate": 1.2500000000000005e-07,
+      "loss": 0.0,
+      "reward": 3.0472673904150724,
+      "reward_std": 1.1133704138919711,
+      "rewards/concensus_correctness_reward_func": 1.2586249932646751,
+      "rewards/consensus_reward_func": 1.3125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.2538924207619857,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.22225000150501728,
       "step": 8
     },
     {
+      "completion_length": 65.22222222222223,
       "epoch": 3.4705882352941178,
+      "grad_norm": 12.695923805236816,
+      "kl": 0.023818521553443536,
       "learning_rate": 1.507684480352292e-08,
+      "loss": 0.0,
+      "reward": 3.279424058066474,
+      "reward_std": 1.3595769628882408,
+      "rewards/concensus_correctness_reward_func": 1.277111099825965,
+      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.18409076048475173,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.4848888980017768,
       "step": 10
     },
     {
       "epoch": 3.4705882352941178,
       "step": 10,
       "total_flos": 0.0,
+      "train_loss": 1.2571450588438892e-05,
+      "train_runtime": 2664.5232,
+      "train_samples_per_second": 0.06,
+      "train_steps_per_second": 0.004
     }
   ],
   "logging_steps": 2,