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

Libraries

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

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

pipe = pipeline("text-generation", model="Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda")
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("Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda")
model = AutoModelForCausalLM.from_pretrained("Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda", 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 Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Biondovi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-huge_fluffy_barracuda

SGLang

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

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

Biondovi commited on Jun 26, 2025

Commit

c3c0a6f

verified ·

1 Parent(s): 388da4c

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": -0.02006573975086212,
-    "train_runtime": 384.0277,
-    "train_samples": 3,
-    "train_samples_per_second": 0.104,
-    "train_steps_per_second": 0.026
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.056733327358961104,
+    "train_runtime": 778.6822,
+    "train_samples": 49,
+    "train_samples_per_second": 0.051,
+    "train_steps_per_second": 0.013
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00eff6443fb43b7eb75b96dd4a0bdc703ae8b2db6ac266fe37803cdcf9df747
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:fedc5f020be8194eb5cea3c7ebfea8065867f92bd11479c4f6aa5a2cc53947e5
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": -0.02006573975086212,
-    "train_runtime": 384.0277,
-    "train_samples": 3,
-    "train_samples_per_second": 0.104,
-    "train_steps_per_second": 0.026
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.056733327358961104,
+    "train_runtime": 778.6822,
+    "train_samples": 49,
+    "train_samples_per_second": 0.051,
+    "train_steps_per_second": 0.013
 }

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,
@@ -15,38 +15,38 @@
       "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": 41.5,
-      "completions/max_terminated_length": 41.5,
-      "completions/mean_length": 28.625,
-      "completions/mean_terminated_length": 28.625,
-      "completions/min_length": 21.0,
-      "completions/min_terminated_length": 21.0,
-      "epoch": 1.6666666666666665,
-      "frac_reward_zero_std": 0.5,
-      "grad_norm": 48.16117858886719,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": -0.0436,
-      "num_tokens": 1253.0,
-      "reward": 1.3778519034385681,
-      "reward_std": 0.02223619797587162,
       "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": 0.11210194230079651,
-      "rewards/question_recreation_reward_func/std": 0.0005584330501733348,
       "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": 0.265749990940094,
-      "rewards/xmlcount_reward_func/std": 0.03149999678134918,
       "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": 48.0,
-      "completions/max_terminated_length": 48.0,
-      "completions/mean_length": 33.125,
-      "completions/mean_terminated_length": 33.125,
-      "completions/min_length": 21.0,
-      "completions/min_terminated_length": 21.0,
-      "epoch": 3.6666666666666665,
       "frac_reward_zero_std": 0.25,
-      "grad_norm": 32.1250114440918,
-      "kl": 0.03968729206826538,
       "learning_rate": 4.415111107797445e-07,
-      "loss": -0.0098,
-      "num_tokens": 2542.0,
-      "reward": 1.393913984298706,
-      "reward_std": 0.044707387627568096,
       "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": 0.11241402477025986,
-      "rewards/question_recreation_reward_func/std": 0.0004275172686902806,
       "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": 0.2814999967813492,
-      "rewards/xmlcount_reward_func/std": 0.036373063921928406,
       "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": 34.0,
-      "completions/max_terminated_length": 34.0,
-      "completions/mean_length": 28.0,
-      "completions/mean_terminated_length": 28.0,
-      "completions/min_length": 21.0,
-      "completions/min_terminated_length": 21.0,
-      "epoch": 4.666666666666667,
-      "frac_reward_zero_std": 0.5,
-      "kl": 0.07297297194600105,
-      "num_tokens": 3166.0,
-      "reward": 0.4249759316444397,
-      "reward_std": 0.000247054296778515,
       "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": 0.11197593808174133,
-      "rewards/question_recreation_reward_func/std": 0.0003493763506412506,
       "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": 0.31299999356269836,
-      "rewards/xmlcount_reward_func/std": 0.07274612784385681,
-      "step": 5,
       "total_flos": 0.0,
-      "train_loss": -0.02006573975086212,
-      "train_runtime": 384.0277,
-      "train_samples_per_second": 0.104,
-      "train_steps_per_second": 0.026
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
-  "num_input_tokens_seen": 3166,
-  "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": 0.40816326530612246,
   "eval_steps": 500,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "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": 172.0,
+      "completions/max_terminated_length": 71.0,
+      "completions/mean_length": 70.25,
+      "completions/mean_terminated_length": 43.66666603088379,
+      "completions/min_length": 29.0,
+      "completions/min_terminated_length": 29.0,
+      "epoch": 0.08163265306122448,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 41.77123260498047,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.1625,
+      "num_tokens": 1586.0,
+      "reward": 0.29884233325719833,
+      "reward_std": 0.06489030597731471,
       "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": 0.020842326804995537,
+      "rewards/question_recreation_reward_func/std": 0.01152020413428545,
       "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": 0.27799999713897705,
+      "rewards/xmlcount_reward_func/std": 0.1191326342523098,
       "step": 2
     },
     {
       "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": 40.75,
+      "completions/mean_terminated_length": 40.75,
+      "completions/min_length": 23.0,
+      "completions/min_terminated_length": 23.0,
+      "epoch": 0.16326530612244897,
       "frac_reward_zero_std": 0.25,
+      "grad_norm": 31.240802764892578,
+      "kl": 0.011891998292412609,
       "learning_rate": 4.415111107797445e-07,
+      "loss": -0.0471,
+      "num_tokens": 2936.0,
+      "reward": 0.8488049805164337,
+      "reward_std": 0.0757781732827425,
       "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": 0.5,
+      "rewards/final_correctness_reward_func/std": 0.5773502588272095,
+      "rewards/question_recreation_reward_func/mean": 0.025055013597011566,
+      "rewards/question_recreation_reward_func/std": 0.02120710676535964,
       "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": 0.32375000417232513,
+      "rewards/xmlcount_reward_func/std": 0.1294357106089592,
       "step": 4
     },
     {
       "clip_ratio/low_min": 0.0,
       "clip_ratio/region_mean": 0.0,
       "completions/clipped_ratio": 0.0,
+      "completions/max_length": 68.5,
+      "completions/max_terminated_length": 68.5,
+      "completions/mean_length": 35.125,
+      "completions/mean_terminated_length": 35.125,
+      "completions/min_length": 22.5,
+      "completions/min_terminated_length": 22.5,
+      "epoch": 0.24489795918367346,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 60.871788024902344,
+      "kl": 0.05835737707093358,
+      "learning_rate": 2.934120444167326e-07,
+      "loss": 0.0565,
+      "num_tokens": 4241.0,
+      "reward": 0.888050839304924,
+      "reward_std": 0.056016623973846436,
+      "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": 0.5,
+      "rewards/final_correctness_reward_func/std": 0.5773502588272095,
+      "rewards/question_recreation_reward_func/mean": 0.024800879880785942,
+      "rewards/question_recreation_reward_func/std": 0.010365220019593835,
+      "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": 0.3632499873638153,
+      "rewards/xmlcount_reward_func/std": 0.07748057693243027,
+      "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": 81.5,
+      "completions/max_terminated_length": 81.5,
+      "completions/mean_length": 39.625,
+      "completions/mean_terminated_length": 39.625,
+      "completions/min_length": 19.0,
+      "completions/min_terminated_length": 19.0,
+      "epoch": 0.32653061224489793,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 45.16495895385742,
+      "kl": 0.07873396738432348,
+      "learning_rate": 1.2500000000000005e-07,
+      "loss": 0.0947,
+      "num_tokens": 5582.0,
+      "reward": 0.4169105738401413,
+      "reward_std": 0.05461369641125202,
       "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": 0.08241057302802801,
+      "rewards/question_recreation_reward_func/std": 0.024038489558734,
       "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": 0.3344999849796295,
+      "rewards/xmlcount_reward_func/std": 0.0637132003903389,
+      "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": 51.5,
+      "completions/max_terminated_length": 51.5,
+      "completions/mean_length": 35.0,
+      "completions/mean_terminated_length": 35.0,
+      "completions/min_length": 22.0,
+      "completions/min_terminated_length": 22.0,
+      "epoch": 0.40816326530612246,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 39.669822692871094,
+      "kl": 0.12252630665898323,
+      "learning_rate": 1.507684480352292e-08,
+      "loss": 0.017,
+      "num_tokens": 6886.0,
+      "reward": 0.5029706656932831,
+      "reward_std": 0.015668265521526337,
+      "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": 0.16784566640853882,
+      "rewards/question_recreation_reward_func/std": 0.038624364882707596,
+      "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": 0.33512498438358307,
+      "rewards/xmlcount_reward_func/std": 0.07968567498028278,
+      "step": 10
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "step": 10,
       "total_flos": 0.0,
+      "train_loss": 0.056733327358961104,
+      "train_runtime": 778.6822,
+      "train_samples_per_second": 0.051,
+      "train_steps_per_second": 0.013
     }
   ],
   "logging_steps": 2,
   "max_steps": 10,
+  "num_input_tokens_seen": 6886,
+  "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": {}
     }