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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/angenless/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-quiet_solitary_duck

SGLang

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

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

angenless commited on Jun 15, 2025

Commit

3315121

verified ·

1 Parent(s): 3ec5efe

End of training

Browse files

Files changed (5) hide show

all_results.json +4 -4
model.safetensors +1 -1
train_results.json +4 -4
trainer_state.json +40 -40
training_args.bin +1 -1

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 555.9692,
     "train_samples": 5,
-    "train_samples_per_second": 0.072,
-    "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 6.198883056640625e-07,
+    "train_runtime": 1273.2587,
     "train_samples": 5,
+    "train_samples_per_second": 0.031,
+    "train_steps_per_second": 0.008
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5442f2126f3c0e070b38b223feafe59e4381fbd8765cacb91a928f300b3d2792
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:b17adb89ed44f71d4a01f77b6fd841a58ed9f3e4a0f1dc8880e91944f7b3b71d
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.0,
-    "train_runtime": 555.9692,
     "train_samples": 5,
-    "train_samples_per_second": 0.072,
-    "train_steps_per_second": 0.018
 }

 {
     "total_flos": 0.0,
+    "train_loss": 6.198883056640625e-07,
+    "train_runtime": 1273.2587,
     "train_samples": 5,
+    "train_samples_per_second": 0.031,
+    "train_steps_per_second": 0.008
 }

trainer_state.json CHANGED Viewed

@@ -10,95 +10,95 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 4.0,
       "epoch": 0.8,
-      "grad_norm": 0.0,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 2.415114939212799,
-      "reward_std": 0.0,
-      "rewards/concensus_correctness_reward_func": 2.38400000333786,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.031114899553358555,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 2
     },
     {
-      "completion_length": 4.0,
       "epoch": 1.4,
-      "grad_norm": 0.0,
-      "kl": 0.0,
       "learning_rate": 4.415111107797445e-07,
       "loss": 0.0,
-      "reward": 3.3432147900263467,
-      "reward_std": 0.0,
-      "rewards/concensus_correctness_reward_func": 1.9186666409174602,
-      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.09121479839086533,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 4
     },
     {
-      "completion_length": 4.0,
       "epoch": 2.0,
-      "grad_norm": 0.0,
-      "kl": 0.0,
       "learning_rate": 2.934120444167326e-07,
       "loss": 0.0,
-      "reward": 2.555845538775126,
-      "reward_std": 0.0,
-      "rewards/concensus_correctness_reward_func": 2.540000001589457,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.015845506141583126,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 6
     },
     {
-      "completion_length": 4.0,
       "epoch": 2.8,
-      "grad_norm": 0.0,
-      "kl": 0.0,
       "learning_rate": 1.2500000000000005e-07,
       "loss": 0.0,
-      "reward": 2.9214743077754974,
-      "reward_std": 0.0,
-      "rewards/concensus_correctness_reward_func": 2.384999990463257,
-      "rewards/consensus_reward_func": 0.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.036474294029176235,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 8
     },
     {
-      "completion_length": 4.0,
       "epoch": 3.4,
-      "grad_norm": 0.0,
-      "kl": 0.0,
       "learning_rate": 1.507684480352292e-08,
       "loss": 0.0,
-      "reward": 2.5726755062739053,
-      "reward_std": 0.0,
-      "rewards/concensus_correctness_reward_func": 2.537333329518636,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.035342139502366386,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
@@ -108,10 +108,10 @@
       "epoch": 3.4,
       "step": 10,
       "total_flos": 0.0,
-      "train_loss": 0.0,
-      "train_runtime": 555.9692,
-      "train_samples_per_second": 0.072,
-      "train_steps_per_second": 0.018
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 176.875,
       "epoch": 0.8,
+      "grad_norm": 7.9261298179626465,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 0.06529645575210452,
+      "reward_std": 0.031127130147069693,
+      "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": 0.06529645575210452,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 2
     },
     {
+      "completion_length": 175.83333333333334,
       "epoch": 1.4,
+      "grad_norm": 7.617096424102783,
+      "kl": 0.00035043573977115255,
       "learning_rate": 4.415111107797445e-07,
       "loss": 0.0,
+      "reward": 0.19371196130911508,
+      "reward_std": 0.08724394316474597,
+      "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": 0.19371196130911508,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 4
     },
     {
+      "completion_length": 217.66666666666666,
       "epoch": 2.0,
+      "grad_norm": 5.332751750946045,
+      "kl": 0.000615184020716697,
       "learning_rate": 2.934120444167326e-07,
       "loss": 0.0,
+      "reward": 0.02679351655145486,
+      "reward_std": 0.009128622089823088,
+      "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": 0.02679351655145486,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 6
     },
     {
+      "completion_length": 189.75,
       "epoch": 2.8,
+      "grad_norm": 6.812089920043945,
+      "kl": 0.0007357565191341564,
       "learning_rate": 1.2500000000000005e-07,
       "loss": 0.0,
+      "reward": 0.06324641685932875,
+      "reward_std": 0.013577945763245225,
+      "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": 0.06324641685932875,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "step": 8
     },
     {
+      "completion_length": 148.83333333333334,
       "epoch": 3.4,
+      "grad_norm": 19.7174129486084,
+      "kl": 0.0018994022199573617,
       "learning_rate": 1.507684480352292e-08,
       "loss": 0.0,
+      "reward": 0.0978486401339372,
+      "reward_std": 0.02896895833934347,
+      "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": 0.0978486401339372,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
       "rewards/xmlcount_reward_func": 0.0,
       "epoch": 3.4,
       "step": 10,
       "total_flos": 0.0,
+      "train_loss": 6.198883056640625e-07,
+      "train_runtime": 1273.2587,
+      "train_samples_per_second": 0.031,
+      "train_steps_per_second": 0.008
     }
   ],
   "logging_steps": 2,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfb9eb97347b6555d102b8358e498df70a0655027110fc8906c40568c09446b2
 size 5880

 version https://git-lfs.github.com/spec/v1
+oid sha256:9933732db5666e05988b13b35c6b97a5273a218e9de378d7027bb6d84b6a0650
 size 5880