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 22, 2025

Commit

bf00015

verified ·

1 Parent(s): 6b214f1

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 +89 -89

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.05696702897548676,
-    "train_runtime": 894.3741,
-    "train_samples": 26,
-    "train_samples_per_second": 0.045,
-    "train_steps_per_second": 0.011
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.002082011103630066,
+    "train_runtime": 1069.2271,
+    "train_samples": 21,
+    "train_samples_per_second": 0.037,
+    "train_steps_per_second": 0.009
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d609e6f58f8740cc496b9ba3fc7be78957dafa63297089227faddea785c7afde
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:e98640fd0fb62748d083f5fbf62cb3bf0d69e65aae5bf4458b30ec20523a526d
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.05696702897548676,
-    "train_runtime": 894.3741,
-    "train_samples": 26,
-    "train_samples_per_second": 0.045,
-    "train_steps_per_second": 0.011
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.002082011103630066,
+    "train_runtime": 1069.2271,
+    "train_samples": 21,
+    "train_samples_per_second": 0.037,
+    "train_steps_per_second": 0.009
 }

trainer_state.json CHANGED Viewed

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7692307692307693,
   "eval_steps": 500,
   "global_step": 10,
   "is_hyper_param_search": false,
@@ -16,21 +16,21 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 64.5,
-      "completions/max_terminated_length": 64.5,
-      "completions/mean_length": 38.25,
-      "completions/mean_terminated_length": 38.25,
-      "completions/min_length": 6.0,
-      "completions/min_terminated_length": 6.0,
-      "epoch": 0.15384615384615385,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 24.975540161132812,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.1495,
-      "num_tokens": 1330.0,
-      "reward": 0.02695654146373272,
-      "reward_std": 0.004698488744907081,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -39,8 +39,8 @@
       "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": 0.02695654146373272,
-      "rewards/question_recreation_reward_func/std": 0.009667334612458944,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
@@ -56,31 +56,31 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 152.5,
-      "completions/max_terminated_length": 152.5,
-      "completions/mean_length": 65.5,
-      "completions/mean_terminated_length": 65.5,
-      "completions/min_length": 4.0,
-      "completions/min_terminated_length": 4.0,
-      "epoch": 0.3076923076923077,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 13.696731567382812,
-      "kl": 0.002270349781611003,
       "learning_rate": 4.415111107797445e-07,
-      "loss": -0.0013,
-      "num_tokens": 2878.0,
-      "reward": 2.546881502494216,
-      "reward_std": 3.55640537571162,
-      "rewards/concensus_correctness_reward_func/mean": 2.5,
-      "rewards/concensus_correctness_reward_func/std": 5.0,
       "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": 0.0468815416097641,
-      "rewards/question_recreation_reward_func/std": 0.031144380569458008,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
@@ -96,31 +96,31 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 162.5,
-      "completions/max_terminated_length": 162.5,
-      "completions/mean_length": 107.875,
-      "completions/mean_terminated_length": 107.875,
-      "completions/min_length": 52.5,
-      "completions/min_terminated_length": 52.5,
-      "epoch": 0.46153846153846156,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 12.553956031799316,
-      "kl": 0.011294666648609564,
       "learning_rate": 2.934120444167326e-07,
-      "loss": 0.0173,
-      "num_tokens": 4765.0,
-      "reward": 0.03608411527238786,
-      "reward_std": 0.00972485588863492,
-      "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": 0.036084115505218506,
-      "rewards/question_recreation_reward_func/std": 0.012303954223170877,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
@@ -136,21 +136,21 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 131.0,
-      "completions/max_terminated_length": 131.0,
-      "completions/mean_length": 58.0,
-      "completions/mean_terminated_length": 58.0,
-      "completions/min_length": 9.5,
-      "completions/min_terminated_length": 9.5,
-      "epoch": 0.6153846153846154,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 36.519691467285156,
-      "kl": 0.029099395032972097,
       "learning_rate": 1.2500000000000005e-07,
-      "loss": 0.0025,
-      "num_tokens": 6253.0,
-      "reward": 0.03265724144876003,
-      "reward_std": 0.00910294521600008,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -159,8 +159,8 @@
       "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": 0.03265724144876003,
-      "rewards/question_recreation_reward_func/std": 0.01016752002760768,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
@@ -176,21 +176,21 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 179.0,
-      "completions/max_terminated_length": 179.0,
-      "completions/mean_length": 109.5,
-      "completions/mean_terminated_length": 109.5,
-      "completions/min_length": 35.5,
-      "completions/min_terminated_length": 35.5,
-      "epoch": 0.7692307692307693,
       "frac_reward_zero_std": 0.0,
-      "grad_norm": 18.44257926940918,
-      "kl": 0.010602469090372324,
       "learning_rate": 1.507684480352292e-08,
-      "loss": 0.1169,
-      "num_tokens": 8153.0,
-      "reward": 0.03864075988531113,
-      "reward_std": 0.08435654640197754,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -199,29 +199,29 @@
       "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": 0.07639075815677643,
-      "rewards/question_recreation_reward_func/std": 0.036930627189576626,
       "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": -0.0377499982714653,
-      "rewards/xmlcount_reward_func/std": 0.0755000039935112,
       "step": 10
     },
     {
-      "epoch": 0.7692307692307693,
       "step": 10,
       "total_flos": 0.0,
-      "train_loss": 0.05696702897548676,
-      "train_runtime": 894.3741,
-      "train_samples_per_second": 0.045,
-      "train_steps_per_second": 0.011
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
-  "num_input_tokens_seen": 8153,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.9523809523809523,
   "eval_steps": 500,
   "global_step": 10,
   "is_hyper_param_search": false,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 145.0,
+      "completions/max_terminated_length": 145.0,
+      "completions/mean_length": 117.5,
+      "completions/mean_terminated_length": 117.5,
+      "completions/min_length": 97.0,
+      "completions/min_terminated_length": 97.0,
+      "epoch": 0.19047619047619047,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 8.355567932128906,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0713,
+      "num_tokens": 1964.0,
+      "reward": 0.026983825489878654,
+      "reward_std": 0.015820471802726388,
       "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": 0.02698382642120123,
+      "rewards/question_recreation_reward_func/std": 0.021281746681779623,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 198.5,
+      "completions/max_terminated_length": 198.5,
+      "completions/mean_length": 113.0,
+      "completions/mean_terminated_length": 113.0,
+      "completions/min_length": 55.0,
+      "completions/min_terminated_length": 55.0,
+      "epoch": 0.38095238095238093,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 14.761173248291016,
+      "kl": 0.0012884526804555207,
       "learning_rate": 4.415111107797445e-07,
+      "loss": 0.1049,
+      "num_tokens": 3892.0,
+      "reward": 0.08943291194736958,
+      "reward_std": 0.03367678914219141,
+      "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": 0.089432911016047,
+      "rewards/question_recreation_reward_func/std": 0.03494547167792916,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 181.5,
+      "completions/max_terminated_length": 181.5,
+      "completions/mean_length": 108.375,
+      "completions/mean_terminated_length": 108.375,
+      "completions/min_length": 44.5,
+      "completions/min_terminated_length": 44.5,
+      "epoch": 0.5714285714285714,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 19.44080924987793,
+      "kl": 0.002390416557318531,
       "learning_rate": 2.934120444167326e-07,
+      "loss": 0.077,
+      "num_tokens": 5783.0,
+      "reward": 0.5563193969428539,
+      "reward_std": 0.70130077842623,
+      "rewards/concensus_correctness_reward_func/mean": 0.23999999463558197,
+      "rewards/concensus_correctness_reward_func/std": 0.47999998927116394,
+      "rewards/consensus_reward_func/mean": 0.25,
+      "rewards/consensus_reward_func/std": 0.5,
       "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": 0.06631939299404621,
+      "rewards/question_recreation_reward_func/std": 0.01969786360859871,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 99.0,
+      "completions/max_terminated_length": 99.0,
+      "completions/mean_length": 63.375,
+      "completions/mean_terminated_length": 63.375,
+      "completions/min_length": 18.0,
+      "completions/min_terminated_length": 18.0,
+      "epoch": 0.7619047619047619,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 41.01006317138672,
+      "kl": 0.01600448344834149,
       "learning_rate": 1.2500000000000005e-07,
+      "loss": -0.1846,
+      "num_tokens": 7314.0,
+      "reward": 0.05993553204461932,
+      "reward_std": 0.01692041102796793,
       "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": 0.059935531578958035,
+      "rewards/question_recreation_reward_func/std": 0.01765961665660143,
       "rewards/soft_format_reward_func/mean": 0.0,
       "rewards/soft_format_reward_func/std": 0.0,
       "rewards/strict_format_reward_func/mean": 0.0,
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 199.0,
+      "completions/max_terminated_length": 199.0,
+      "completions/mean_length": 156.25,
+      "completions/mean_terminated_length": 156.25,
+      "completions/min_length": 108.0,
+      "completions/min_terminated_length": 108.0,
+      "epoch": 0.9523809523809523,
       "frac_reward_zero_std": 0.0,
+      "grad_norm": 6.120136737823486,
+      "kl": 0.001899369401144213,
       "learning_rate": 1.507684480352292e-08,
+      "loss": -0.0582,
+      "num_tokens": 9588.0,
+      "reward": 0.01779888104647398,
+      "reward_std": 0.005248098401352763,
       "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": 0.01779888104647398,
+      "rewards/question_recreation_reward_func/std": 0.008481711382046342,
       "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": 0.0,
+      "rewards/xmlcount_reward_func/std": 0.0,
       "step": 10
     },
     {
+      "epoch": 0.9523809523809523,
       "step": 10,
       "total_flos": 0.0,
+      "train_loss": 0.002082011103630066,
+      "train_runtime": 1069.2271,
+      "train_samples_per_second": 0.037,
+      "train_steps_per_second": 0.009
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
+  "num_input_tokens_seen": 9588,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {