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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf")
model = AutoModelForCausalLM.from_pretrained("Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Dassem/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-endangered_gregarious_wolf

SGLang

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

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

Dassem commited on Apr 29, 2025

Commit

8c20c82

verified ·

1 Parent(s): 9790cc3

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 +93 -93
training_args.bin +1 -1

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 4.807692021131515e-05,
-    "train_runtime": 223.5988,
     "train_samples": 28,
-    "train_samples_per_second": 1.431,
-    "train_steps_per_second": 0.089
 }

 {
     "total_flos": 0.0,
+    "train_loss": 2.0853490582339874e-06,
+    "train_runtime": 204.0881,
     "train_samples": 28,
+    "train_samples_per_second": 1.568,
+    "train_steps_per_second": 0.098
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1aeff634efeea61be258fad59789239599dc7824d2bd4964a394afd2c4c14a
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:2f5d728429d554ea6eaf4d2918e296b68ec0bf9c3ad131de9e0093c0e41221a5
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 4.807692021131515e-05,
-    "train_runtime": 223.5988,
     "train_samples": 28,
-    "train_samples_per_second": 1.431,
-    "train_steps_per_second": 0.089
 }

 {
     "total_flos": 0.0,
+    "train_loss": 2.0853490582339874e-06,
+    "train_runtime": 204.0881,
     "train_samples": 28,
+    "train_samples_per_second": 1.568,
+    "train_steps_per_second": 0.098
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 331.84375,
       "epoch": 0.5714285714285714,
-      "grad_norm": 12.900187492370605,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
-      "reward": 0.34199932194314897,
-      "reward_std": 0.4895538101554848,
-      "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": 0.2938743317499757,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.04812499601393938,
       "step": 2
     },
     {
-      "completion_length": 479.875,
       "epoch": 1.0,
-      "grad_norm": 2.7152481079101562,
-      "kl": 0.001086632667769057,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 0.6767907881488403,
-      "reward_std": 0.5845600264146924,
       "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": 0.4829991268149267,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.19379166513681412,
       "step": 4
     },
     {
-      "completion_length": 338.90625,
       "epoch": 1.5714285714285714,
-      "grad_norm": 9.47800350189209,
-      "kl": 0.0016836673603393137,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 0.7841773272957653,
-      "reward_std": 0.462471331236884,
-      "rewards/concensus_correctness_reward_func": 0.04050000011920929,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.4120211040135473,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.20665625017136335,
       "step": 6
     },
     {
-      "completion_length": 405.25,
       "epoch": 2.0,
-      "grad_norm": 11.009736061096191,
-      "kl": 0.003919503399326156,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
-      "reward": 0.2670134180225432,
-      "reward_std": 0.7524235047555218,
-      "rewards/concensus_correctness_reward_func": 0.029083333909511566,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.4279300711738567,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.18999999637405077,
       "step": 8
     },
     {
-      "completion_length": 448.53125,
       "epoch": 2.571428571428571,
-      "grad_norm": 5.630650997161865,
-      "kl": 0.0027485769605846144,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
-      "reward": 0.7138850018382072,
-      "reward_std": 0.6001558369025588,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.4186662440188229,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.17021874990314245,
       "step": 10
     },
     {
-      "completion_length": 377.8333333333333,
       "epoch": 3.0,
-      "grad_norm": 5.156170845031738,
-      "kl": 0.0025291694328188896,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
-      "reward": 0.5306394845247269,
-      "reward_std": 0.5479348444690307,
-      "rewards/concensus_correctness_reward_func": 0.06633333365122478,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.47072283178567886,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.006416679670413335,
       "step": 12
     },
     {
-      "completion_length": 446.375,
       "epoch": 3.571428571428571,
-      "grad_norm": 4.689492225646973,
-      "kl": 0.0022219597703951877,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
-      "reward": 0.6020145197398961,
-      "reward_std": 0.3495015730150044,
       "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": 0.2982957558706403,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3037187489680946,
       "step": 14
     },
     {
-      "completion_length": 401.7083333333333,
       "epoch": 4.0,
-      "grad_norm": 6.32925271987915,
-      "kl": 0.0035769061311536157,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
-      "reward": 0.43863170221447945,
-      "reward_std": 0.6057547355691592,
       "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": 0.258715037877361,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.17991666806240877,
       "step": 16
     },
     {
-      "completion_length": 441.8125,
       "epoch": 4.571428571428571,
-      "grad_norm": 5.893700122833252,
-      "kl": 0.00262964062676474,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
-      "reward": 0.38816174550447613,
-      "reward_std": 0.48828089070593705,
-      "rewards/concensus_correctness_reward_func": 0.020625000819563866,
-      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.35328673908952624,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.04825000371783972,
       "step": 18
     },
     {
-      "completion_length": 409.5,
       "epoch": 5.0,
-      "grad_norm": 82.05518341064453,
-      "kl": 0.617507851702006,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0005,
-      "reward": 0.29460536015297595,
-      "reward_std": 0.9458088254323229,
-      "rewards/concensus_correctness_reward_func": 0.0,
-      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.3281886938687724,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.11691667434448998,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 4.807692021131515e-05,
-      "train_runtime": 223.5988,
-      "train_samples_per_second": 1.431,
-      "train_steps_per_second": 0.089
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 375.5625,
       "epoch": 0.5714285714285714,
+      "grad_norm": 10.742135047912598,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
+      "reward": 0.6546003548428416,
+      "reward_std": 0.6044875731458887,
+      "rewards/concensus_correctness_reward_func": 0.0013124989345669746,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.3877253632526845,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.07806250406429172,
       "step": 2
     },
     {
+      "completion_length": 232.5,
       "epoch": 1.0,
+      "grad_norm": 3.2642147541046143,
+      "kl": 0.0015699455398134887,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 0.40701879980042577,
+      "reward_std": 0.5096567633251349,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.22247713687829673,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.017874995867411297,
       "step": 4
     },
     {
+      "completion_length": 321.09375,
       "epoch": 1.5714285714285714,
+      "grad_norm": 21.773033142089844,
+      "kl": 0.0015195708147075493,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 0.4619187385542318,
+      "reward_std": 0.5513766110525467,
+      "rewards/concensus_correctness_reward_func": 0.0078125,
       "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.2197312341304496,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.04687500046566129,
       "step": 6
     },
     {
+      "completion_length": 325.7083333333333,
       "epoch": 2.0,
+      "grad_norm": 3.721029758453369,
+      "kl": 0.001866711395753858,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 0.5242425839727124,
+      "reward_std": 0.3492290705131988,
+      "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": 0.3246592610764007,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.19958332367241383,
       "step": 8
     },
     {
+      "completion_length": 343.5625,
       "epoch": 2.571428571428571,
+      "grad_norm": 26.122732162475586,
+      "kl": 0.002480518178344937,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 0.26784040141501464,
+      "reward_std": 0.5901486595976166,
+      "rewards/concensus_correctness_reward_func": -0.021937500685453415,
+      "rewards/consensus_reward_func": 0.0625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.1735591495234985,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.008781250333413482,
       "step": 10
     },
     {
+      "completion_length": 364.5416666666667,
       "epoch": 3.0,
+      "grad_norm": 10.527915000915527,
+      "kl": 0.0015174187331770856,
       "learning_rate": 2.2935516363191693e-07,
       "loss": 0.0,
+      "reward": 0.38991063460707664,
+      "reward_std": 0.6026111692966273,
+      "rewards/concensus_correctness_reward_func": 0.010416666666666666,
+      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.22970231203362346,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.016875003774960835,
       "step": 12
     },
     {
+      "completion_length": 298.6875,
       "epoch": 3.571428571428571,
+      "grad_norm": 13.57264232635498,
+      "kl": 0.005783965454611462,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": -0.03218980669043958,
+      "reward_std": 0.8524897873867303,
       "rewards/concensus_correctness_reward_func": 0.0,
       "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.2236226930981502,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.31831249967217445,
       "step": 14
     },
     {
+      "completion_length": 229.0,
       "epoch": 4.0,
+      "grad_norm": 15.225955963134766,
+      "kl": 0.004969593544956297,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 0.5881440881639719,
+      "reward_std": 0.3967058731747481,
       "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": 0.29397742349343997,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2941666667660077,
       "step": 16
     },
     {
+      "completion_length": 295.3125,
       "epoch": 4.571428571428571,
+      "grad_norm": 5.6039252281188965,
+      "kl": 0.0024270654103020206,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
+      "reward": 1.1645393799990416,
+      "reward_std": 1.3862881572567858,
+      "rewards/concensus_correctness_reward_func": 0.625,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.31653934996575117,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.16050000069662929,
       "step": 18
     },
     {
+      "completion_length": 362.5416666666667,
       "epoch": 5.0,
+      "grad_norm": 36.74289321899414,
+      "kl": 0.001860091744068389,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0,
+      "reward": 0.4840538784240683,
+      "reward_std": 0.5016769632541885,
+      "rewards/concensus_correctness_reward_func": 0.010416666666666666,
+      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.21813720697537065,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.1721666712934772,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 2.0853490582339874e-06,
+      "train_runtime": 204.0881,
+      "train_samples_per_second": 1.568,
+      "train_steps_per_second": 0.098
     }
   ],
   "logging_steps": 2,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78268932364dfe195fcfba8eaf3212b6eedd2ad354c3defdcbbb8bcdd22dd702
 size 5944

 version https://git-lfs.github.com/spec/v1
+oid sha256:04bd33b60bc2c2e4c13bb9f8afb481dc8344053d942adc196453bc75d6ecc286
 size 5944