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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Oberhaus/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-rabid_prowling_jay

SGLang

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

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

Oberhaus commited on Jun 21, 2025

Commit

0c9f61f

verified ·

1 Parent(s): 29a492a

End of training

Browse files

Files changed (4) hide show

all_results.json +5 -5
model.safetensors +1 -1
train_results.json +5 -5
trainer_state.json +64 -151

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.018859711289405823,
-    "train_runtime": 821.595,
-    "train_samples": 2,
-    "train_samples_per_second": 0.049,
-    "train_steps_per_second": 0.012
 }

 {
     "total_flos": 0.0,
+    "train_loss": -0.05952250063419342,
+    "train_runtime": 596.557,
+    "train_samples": 3,
+    "train_samples_per_second": 0.067,
+    "train_steps_per_second": 0.017
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:397b0e43a008185cb6c2b9bb95d456bd57a042ec68b91ff1fd01187192ba385e
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:dcaff2c27c99675727d3f3f7ca52f52806145f8eab4a1a220efa48d86318aab2
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.018859711289405823,
-    "train_runtime": 821.595,
-    "train_samples": 2,
-    "train_samples_per_second": 0.049,
-    "train_steps_per_second": 0.012
 }

 {
     "total_flos": 0.0,
+    "train_loss": -0.05952250063419342,
+    "train_runtime": 596.557,
+    "train_samples": 3,
+    "train_samples_per_second": 0.067,
+    "train_steps_per_second": 0.017
 }

trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.0,
   "eval_steps": 500,
-  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,21 +16,21 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 78.5,
-      "completions/max_terminated_length": 78.5,
-      "completions/mean_length": 71.0,
-      "completions/mean_terminated_length": 71.0,
-      "completions/min_length": 66.0,
-      "completions/min_terminated_length": 66.0,
-      "epoch": 2.0,
-      "frac_reward_zero_std": 0.5,
-      "grad_norm": 7.5716962814331055,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": -0.0038,
-      "num_tokens": 1592.0,
-      "reward": 0.595897763967514,
-      "reward_std": 0.007195939775556326,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -39,14 +39,14 @@
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.23139773309230804,
-      "rewards/question_recreation_reward_func/std": 0.23004795610904694,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.3645000010728836,
-      "rewards/xmlcount_reward_func/std": 0.1402961164712906,
       "step": 2
     },
     {
@@ -55,38 +55,38 @@
       "clip_ratio/low_mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.125,
-      "completions/max_length": 162.5,
-      "completions/max_terminated_length": 74.5,
-      "completions/mean_length": 92.5,
-      "completions/mean_terminated_length": 69.41666793823242,
-      "completions/min_length": 67.0,
-      "completions/min_terminated_length": 67.0,
-      "epoch": 4.0,
-      "frac_reward_zero_std": 0.25,
-      "grad_norm": 15.5301513671875,
-      "kl": 0.005864029284566641,
       "learning_rate": 4.415111107797445e-07,
-      "loss": 0.0884,
-      "num_tokens": 3356.0,
-      "reward": 0.6439805626869202,
-      "reward_std": 0.08714117787894793,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/consensus_reward_func/std": 0.0,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
-      "rewards/final_correctness_reward_func/mean": 0.0,
-      "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.21773060411214828,
-      "rewards/question_recreation_reward_func/std": 0.22334621846675873,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.42624998092651367,
-      "rewards/xmlcount_reward_func/std": 0.12349999696016312,
       "step": 4
     },
     {
@@ -96,101 +96,18 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 79.5,
-      "completions/max_terminated_length": 79.5,
-      "completions/mean_length": 70.5,
-      "completions/mean_terminated_length": 70.5,
-      "completions/min_length": 66.5,
-      "completions/min_terminated_length": 66.5,
-      "epoch": 6.0,
-      "frac_reward_zero_std": 0.5,
-      "grad_norm": 5.464433670043945,
-      "kl": 0.06922211730852723,
-      "learning_rate": 2.934120444167326e-07,
-      "loss": 0.0101,
-      "num_tokens": 4944.0,
-      "reward": 0.6734130382537842,
-      "reward_std": 0.09387753391638398,
-      "rewards/concensus_correctness_reward_func/mean": 0.0,
-      "rewards/concensus_correctness_reward_func/std": 0.0,
-      "rewards/consensus_reward_func/mean": 0.0,
-      "rewards/consensus_reward_func/std": 0.0,
-      "rewards/cumulative_reward_2/mean": 0.0,
-      "rewards/cumulative_reward_2/std": 0.0,
-      "rewards/final_correctness_reward_func/mean": 0.0,
-      "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.24316304177045822,
-      "rewards/question_recreation_reward_func/std": 0.23954910784959793,
-      "rewards/soft_format_reward_func/mean": 0.0,
-      "rewards/soft_format_reward_func/std": 0.0,
-      "rewards/strict_format_reward_func/mean": 0.0,
-      "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.43024998903274536,
-      "rewards/xmlcount_reward_func/std": 0.12218121439218521,
-      "step": 6
-    },
-    {
-      "clip_ratio/high_max": 0.0,
-      "clip_ratio/high_mean": 0.0,
-      "clip_ratio/low_mean": 0.0,
-      "clip_ratio/low_min": 0.0,
-      "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.0,
-      "completions/max_length": 70.0,
-      "completions/max_terminated_length": 70.0,
-      "completions/mean_length": 67.875,
-      "completions/mean_terminated_length": 67.875,
-      "completions/min_length": 66.0,
-      "completions/min_terminated_length": 66.0,
-      "epoch": 8.0,
-      "frac_reward_zero_std": 0.5,
-      "grad_norm": 6.253076076507568,
-      "kl": 0.10633310675621033,
-      "learning_rate": 1.2500000000000005e-07,
-      "loss": -0.0005,
-      "num_tokens": 6511.0,
-      "reward": 0.7169579863548279,
-      "reward_std": 0.0016185232670977712,
-      "rewards/concensus_correctness_reward_func/mean": 0.0,
-      "rewards/concensus_correctness_reward_func/std": 0.0,
-      "rewards/consensus_reward_func/mean": 0.0,
-      "rewards/consensus_reward_func/std": 0.0,
-      "rewards/cumulative_reward_2/mean": 0.0,
-      "rewards/cumulative_reward_2/std": 0.0,
-      "rewards/final_correctness_reward_func/mean": 0.0,
-      "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.2229580283164978,
-      "rewards/question_recreation_reward_func/std": 0.22353137284517288,
-      "rewards/soft_format_reward_func/mean": 0.0,
-      "rewards/soft_format_reward_func/std": 0.0,
-      "rewards/strict_format_reward_func/mean": 0.0,
-      "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.49399998784065247,
-      "rewards/xmlcount_reward_func/std": 0.0,
-      "step": 8
-    },
-    {
-      "clip_ratio/high_max": 0.0,
-      "clip_ratio/high_mean": 0.0,
-      "clip_ratio/low_mean": 0.0,
-      "clip_ratio/low_min": 0.0,
-      "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.0,
-      "completions/max_length": 70.5,
-      "completions/max_terminated_length": 70.5,
-      "completions/mean_length": 67.625,
-      "completions/mean_terminated_length": 67.625,
-      "completions/min_length": 64.5,
-      "completions/min_terminated_length": 64.5,
-      "epoch": 10.0,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 6.309518337249756,
-      "kl": 0.1051179226487875,
-      "learning_rate": 1.507684480352292e-08,
-      "loss": 0.0001,
-      "num_tokens": 8076.0,
-      "reward": 0.7306996285915375,
-      "reward_std": 0.016598860966041684,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -199,30 +116,26 @@
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
-      "rewards/question_recreation_reward_func/mean": 0.23669961094856262,
-      "rewards/question_recreation_reward_func/std": 0.2363170012831688,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
-      "rewards/xmlcount_reward_func/mean": 0.49399998784065247,
-      "rewards/xmlcount_reward_func/std": 0.0,
-      "step": 10
-    },
-    {
-      "epoch": 10.0,
-      "step": 10,
       "total_flos": 0.0,
-      "train_loss": 0.018859711289405823,
-      "train_runtime": 821.595,
-      "train_samples_per_second": 0.049,
-      "train_steps_per_second": 0.012
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
-  "num_input_tokens_seen": 8076,
-  "num_train_epochs": 10,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -230,8 +143,8 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
       },
       "attributes": {}
     }

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 4.666666666666667,
   "eval_steps": 500,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 175.0,
+      "completions/max_terminated_length": 175.0,
+      "completions/mean_length": 117.875,
+      "completions/mean_terminated_length": 117.875,
+      "completions/min_length": 36.0,
+      "completions/min_terminated_length": 36.0,
+      "epoch": 1.6666666666666665,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 14.605681419372559,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": -0.1524,
+      "num_tokens": 1967.0,
+      "reward": 0.20762164145708084,
+      "reward_std": 0.1415688320994377,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.032121654599905014,
+      "rewards/question_recreation_reward_func/std": 0.016860227566212416,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.17549999803304672,
+      "rewards/xmlcount_reward_func/std": 0.13922321051359177,
       "step": 2
     },
     {
       "clip_ratio/low_mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 194.0,
+      "completions/max_terminated_length": 194.0,
+      "completions/mean_length": 138.0,
+      "completions/mean_terminated_length": 138.0,
+      "completions/min_length": 82.5,
+      "completions/min_terminated_length": 82.5,
+      "epoch": 3.6666666666666665,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 18.996776580810547,
+      "kl": 0.006532190498546697,
       "learning_rate": 4.415111107797445e-07,
+      "loss": 0.0037,
+      "num_tokens": 4095.0,
+      "reward": 0.46264173835515976,
+      "reward_std": 0.4753055372275412,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/consensus_reward_func/std": 0.0,
       "rewards/cumulative_reward_2/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
+      "rewards/final_correctness_reward_func/mean": 0.25,
+      "rewards/final_correctness_reward_func/std": 0.5,
+      "rewards/question_recreation_reward_func/mean": 0.0403917171061039,
+      "rewards/question_recreation_reward_func/std": 0.02754821814596653,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.17225000262260437,
+      "rewards/xmlcount_reward_func/std": 0.1409270241856575,
       "step": 4
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 195.0,
+      "completions/max_terminated_length": 195.0,
+      "completions/mean_length": 135.5,
+      "completions/mean_terminated_length": 135.5,
+      "completions/min_length": 64.0,
+      "completions/min_terminated_length": 64.0,
+      "epoch": 4.666666666666667,
       "frac_reward_zero_std": 0.0,
+      "kl": 0.00640501594170928,
+      "num_tokens": 5149.0,
+      "reward": 0.06229368969798088,
+      "reward_std": 0.05007819086313248,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
       "rewards/cumulative_reward_2/std": 0.0,
       "rewards/final_correctness_reward_func/mean": 0.0,
       "rewards/final_correctness_reward_func/std": 0.0,
+      "rewards/question_recreation_reward_func/mean": 0.028543688356876373,
+      "rewards/question_recreation_reward_func/std": 0.008319701068103313,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "rewards/strict_format_reward_func/std": 0.0,
+      "rewards/xmlcount_reward_func/mean": 0.03374999761581421,
+      "rewards/xmlcount_reward_func/std": 0.11535272747278214,
+      "step": 5,
       "total_flos": 0.0,
+      "train_loss": -0.05952250063419342,
+      "train_runtime": 596.557,
+      "train_samples_per_second": 0.067,
+      "train_steps_per_second": 0.017
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
+  "num_input_tokens_seen": 5149,
+  "num_train_epochs": 5,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
       },
       "attributes": {}
     }