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 24, 2025

Commit

9b46217

verified ·

1 Parent(s): fbbdc9e

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 +153 -66

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.03367206752300263,
-    "train_runtime": 356.6659,
-    "train_samples": 3,
-    "train_samples_per_second": 0.112,
-    "train_steps_per_second": 0.028
 }

 {
     "total_flos": 0.0,
+    "train_loss": -0.029699506424367427,
+    "train_runtime": 807.7132,
+    "train_samples": 26,
+    "train_samples_per_second": 0.05,
+    "train_steps_per_second": 0.012
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a9148038dd36cc63726ee17f793406147884f33a1c6c3c1b48d770c647dd07
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:dab5e2e8ae5faf6708d6b585e293f02e37d096a066fd77b2957db238389842a8
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.03367206752300263,
-    "train_runtime": 356.6659,
-    "train_samples": 3,
-    "train_samples_per_second": 0.112,
-    "train_steps_per_second": 0.028
 }

 {
     "total_flos": 0.0,
+    "train_loss": -0.029699506424367427,
+    "train_runtime": 807.7132,
+    "train_samples": 26,
+    "train_samples_per_second": 0.05,
+    "train_steps_per_second": 0.012
 }

trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "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,
@@ -16,37 +16,37 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 81.0,
-      "completions/max_terminated_length": 81.0,
-      "completions/mean_length": 57.0,
-      "completions/mean_terminated_length": 57.0,
-      "completions/min_length": 28.0,
-      "completions/min_terminated_length": 28.0,
-      "epoch": 1.6666666666666665,
-      "frac_reward_zero_std": 0.25,
-      "grad_norm": 14.307222366333008,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": 0.0864,
-      "num_tokens": 1480.0,
-      "reward": 1.1501935720443726,
-      "reward_std": 0.047099690929826465,
       "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": 1.0,
-      "rewards/final_correctness_reward_func/std": 1.154700517654419,
-      "rewards/question_recreation_reward_func/mean": 0.03494352102279663,
-      "rewards/question_recreation_reward_func/std": 0.016959080006927252,
       "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": 0.11525000631809235,
-      "rewards/xmlcount_reward_func/std": 0.10984272509813309,
       "step": 2
     },
     {
@@ -56,37 +56,37 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 83.5,
-      "completions/max_terminated_length": 83.5,
-      "completions/mean_length": 64.5,
-      "completions/mean_terminated_length": 64.5,
-      "completions/min_length": 29.5,
-      "completions/min_terminated_length": 29.5,
-      "epoch": 3.6666666666666665,
-      "frac_reward_zero_std": 0.25,
-      "grad_norm": 15.269614219665527,
-      "kl": 0.012955578858964145,
       "learning_rate": 4.415111107797445e-07,
-      "loss": -0.0011,
-      "num_tokens": 3020.0,
-      "reward": 1.1475419402122498,
-      "reward_std": 0.05424876143115398,
       "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": 1.0,
-      "rewards/final_correctness_reward_func/std": 1.154700517654419,
-      "rewards/question_recreation_reward_func/mean": 0.03229191992431879,
-      "rewards/question_recreation_reward_func/std": 0.017355359625071287,
       "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": 0.11525000631809235,
-      "rewards/xmlcount_reward_func/std": 0.10984272509813309,
       "step": 4
     },
     {
@@ -96,18 +96,61 @@
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
-      "completions/max_length": 118.0,
-      "completions/max_terminated_length": 118.0,
-      "completions/mean_length": 80.0,
-      "completions/mean_terminated_length": 80.0,
-      "completions/min_length": 44.0,
-      "completions/min_terminated_length": 44.0,
-      "epoch": 4.666666666666667,
-      "frac_reward_zero_std": 0.5,
-      "kl": 0.0020351801649667323,
-      "num_tokens": 3852.0,
-      "reward": 0.0799480453133583,
-      "reward_std": 0.0018708972493186593,
       "rewards/concensus_correctness_reward_func/mean": 0.0,
       "rewards/concensus_correctness_reward_func/std": 0.0,
       "rewards/consensus_reward_func/mean": 0.0,
@@ -116,26 +159,70 @@
       "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": 0.03694804385304451,
-      "rewards/question_recreation_reward_func/std": 0.013481352478265762,
       "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": 0.0430000014603138,
-      "rewards/xmlcount_reward_func/std": 0.04965212568640709,
-      "step": 5,
       "total_flos": 0.0,
-      "train_loss": 0.03367206752300263,
-      "train_runtime": 356.6659,
-      "train_samples_per_second": 0.112,
-      "train_steps_per_second": 0.028
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
-  "num_input_tokens_seen": 3852,
-  "num_train_epochs": 5,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -143,8 +230,8 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": false,
-        "should_training_stop": false
       },
       "attributes": {}
     }

   "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,
   "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": 108.0,
+      "completions/max_terminated_length": 108.0,
+      "completions/mean_length": 59.25,
+      "completions/mean_terminated_length": 59.25,
+      "completions/min_length": 17.0,
+      "completions/min_terminated_length": 17.0,
+      "epoch": 0.15384615384615385,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 48.085121154785156,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0009,
+      "num_tokens": 1498.0,
+      "reward": 0.13436073064804077,
+      "reward_std": 0.04493647627532482,
       "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": 0.13436073809862137,
+      "rewards/question_recreation_reward_func/std": 0.04219747520983219,
       "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": 2
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 60.0,
+      "completions/max_terminated_length": 60.0,
+      "completions/mean_length": 32.125,
+      "completions/mean_terminated_length": 32.125,
+      "completions/min_length": 5.0,
+      "completions/min_terminated_length": 5.0,
+      "epoch": 0.3076923076923077,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 60.36766052246094,
+      "kl": 0.003583561468985863,
       "learning_rate": 4.415111107797445e-07,
+      "loss": -0.2099,
+      "num_tokens": 2779.0,
+      "reward": 0.025775335729122162,
+      "reward_std": 0.010659229010343552,
       "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": 0.025775334797799587,
+      "rewards/question_recreation_reward_func/std": 0.0112672233954072,
       "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": 4
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 97.0,
+      "completions/max_terminated_length": 97.0,
+      "completions/mean_length": 33.75,
+      "completions/mean_terminated_length": 33.75,
+      "completions/min_length": 3.0,
+      "completions/min_terminated_length": 3.0,
+      "epoch": 0.46153846153846156,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 192.0141143798828,
+      "kl": 0.01052289770450443,
+      "learning_rate": 2.934120444167326e-07,
+      "loss": -0.0346,
+      "num_tokens": 4073.0,
+      "reward": 3.2741336850449443,
+      "reward_std": 2.4791904482990503,
+      "rewards/concensus_correctness_reward_func/mean": 3.0,
+      "rewards/concensus_correctness_reward_func/std": 4.760952472686768,
+      "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": 0.024133848026394844,
+      "rewards/question_recreation_reward_func/std": 0.013698042836040258,
+      "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": 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": 39.5,
+      "completions/max_terminated_length": 39.5,
+      "completions/mean_length": 28.75,
+      "completions/mean_terminated_length": 28.75,
+      "completions/min_length": 15.5,
+      "completions/min_terminated_length": 15.5,
+      "epoch": 0.6153846153846154,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 42.25923156738281,
+      "kl": 0.032926250249147415,
+      "learning_rate": 1.2500000000000005e-07,
+      "loss": 0.1613,
+      "num_tokens": 5327.0,
+      "reward": 0.03418038599193096,
+      "reward_std": 0.013730974402278662,
       "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": 0.03418038599193096,
+      "rewards/question_recreation_reward_func/std": 0.01239373767748475,
       "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": 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": 36.0,
+      "completions/max_terminated_length": 36.0,
+      "completions/mean_length": 21.0,
+      "completions/mean_terminated_length": 21.0,
+      "completions/min_length": 10.5,
+      "completions/min_terminated_length": 10.5,
+      "epoch": 0.7692307692307693,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 48.233489990234375,
+      "kl": 0.009397334884852171,
+      "learning_rate": 1.507684480352292e-08,
+      "loss": -0.0662,
+      "num_tokens": 6519.0,
+      "reward": 0.11028818786144257,
+      "reward_std": 0.03595135407522321,
+      "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": 0.08753819018602371,
+      "rewards/question_recreation_reward_func/std": 0.013110221829265356,
+      "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": 0.022749999538064003,
+      "rewards/xmlcount_reward_func/std": 0.045499999076128006,
+      "step": 10
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "step": 10,
       "total_flos": 0.0,
+      "train_loss": -0.029699506424367427,
+      "train_runtime": 807.7132,
+      "train_samples_per_second": 0.05,
+      "train_steps_per_second": 0.012
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
+  "num_input_tokens_seen": 6519,
+  "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
       },
       "attributes": {}
     }