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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/Samyn/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-climbing_hunting_raccoon

SGLang

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

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

Samyn commited on May 1, 2025

Commit

4503624

verified ·

1 Parent(s): 938d13c

End of training

Browse files

Files changed (4) hide show

all_results.json +4 -4
model.safetensors +1 -1
train_results.json +4 -4
trainer_state.json +121 -121

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.017387026955839248,
-    "train_runtime": 118.6454,
     "train_samples": 28,
-    "train_samples_per_second": 2.697,
-    "train_steps_per_second": 0.169
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.0030604461819166316,
+    "train_runtime": 117.2262,
     "train_samples": 28,
+    "train_samples_per_second": 2.73,
+    "train_steps_per_second": 0.171
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4905244cffe7269e11d7f4274187d67f532d4684ebc391dc5310f7b901f666ba
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:d933fc107a943dba72b4e31d2da849f5c351b76b51b866a4817664e43cdfbe01
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.017387026955839248,
-    "train_runtime": 118.6454,
     "train_samples": 28,
-    "train_samples_per_second": 2.697,
-    "train_steps_per_second": 0.169
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.0030604461819166316,
+    "train_runtime": 117.2262,
     "train_samples": 28,
+    "train_samples_per_second": 2.73,
+    "train_steps_per_second": 0.171
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 204.5,
       "epoch": 0.5714285714285714,
-      "grad_norm": 21.317461013793945,
       "kl": 0.0,
       "learning_rate": 5e-07,
-      "loss": -0.0,
-      "reward": 4.721158901229501,
-      "reward_std": 2.3674178675282747,
-      "rewards/concensus_correctness_reward_func": 1.9388749888166785,
-      "rewards/consensus_reward_func": 0.875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.6771589289419353,
-      "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.25,
-      "rewards/xmlcount_reward_func": 0.85512500628829,
       "step": 2
     },
     {
-      "completion_length": 130.0,
       "epoch": 1.0,
-      "grad_norm": 0.897192656993866,
-      "kl": 0.12110849392289917,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.0001,
-      "reward": 6.577021439870198,
-      "reward_std": 0.0755121757586797,
-      "rewards/concensus_correctness_reward_func": 2.099166691303253,
       "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.3333333333333333,
-      "rewards/question_recreation_reward_func": 0.9986881564060847,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.2291666666666667,
       "step": 4
     },
     {
-      "completion_length": 151.125,
       "epoch": 1.5714285714285714,
-      "grad_norm": 22.63121223449707,
-      "kl": 0.4992648454499431,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0005,
-      "reward": 6.839811697602272,
-      "reward_std": 0.42532575655786786,
-      "rewards/concensus_correctness_reward_func": 2.2453750111162663,
       "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.4375,
-      "rewards/question_recreation_reward_func": 0.9772492535412312,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.421875,
-      "rewards/xmlcount_reward_func": 1.1953125,
       "step": 6
     },
     {
-      "completion_length": 133.08333333333334,
       "epoch": 2.0,
-      "grad_norm": 0.5993450284004211,
-      "kl": 9.674524827549854,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0073,
-      "reward": 5.716775357723236,
-      "reward_std": 0.04205002324306406,
-      "rewards/concensus_correctness_reward_func": 1.3745000051955383,
-      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9881086846192678,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.25,
       "step": 8
     },
     {
-      "completion_length": 129.75,
       "epoch": 2.571428571428571,
-      "grad_norm": 10.545403480529785,
-      "kl": 0.6732765130000189,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0007,
-      "reward": 6.794037580490112,
-      "reward_std": 0.2974609099328518,
-      "rewards/concensus_correctness_reward_func": 2.069500010460615,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.5,
-      "rewards/question_recreation_reward_func": 0.9516001231968403,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.46875,
-      "rewards/xmlcount_reward_func": 1.241687498986721,
       "step": 10
     },
     {
-      "completion_length": 119.70833333333333,
       "epoch": 3.0,
-      "grad_norm": 57.550323486328125,
-      "kl": 25.137124353398878,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0189,
-      "reward": 5.880659699440002,
-      "reward_std": 0.20277031386892,
-      "rewards/concensus_correctness_reward_func": 1.6080000090102355,
-      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.9582430322964987,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4375,
-      "rewards/xmlcount_reward_func": 1.2102500001589458,
       "step": 12
     },
     {
-      "completion_length": 131.46875,
       "epoch": 3.571428571428571,
-      "grad_norm": 5390.27734375,
-      "kl": 124.98846409318503,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.125,
-      "reward": 6.1955647468566895,
-      "reward_std": 0.21832684613764286,
-      "rewards/concensus_correctness_reward_func": 1.79493750911206,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.9673460610210896,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.46875,
-      "rewards/xmlcount_reward_func": 1.2145312502980232,
       "step": 14
     },
     {
-      "completion_length": 140.08333333333334,
       "epoch": 4.0,
-      "grad_norm": 13.368642807006836,
-      "kl": 4.039107416756451,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.003,
-      "reward": 6.920491377512614,
-      "reward_std": 0.11067443523400773,
-      "rewards/concensus_correctness_reward_func": 2.134166677792867,
-      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.5,
-      "rewards/question_recreation_reward_func": 0.9634080330530802,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.2395833333333333,
       "step": 16
     },
     {
-      "completion_length": 136.28125,
       "epoch": 4.571428571428571,
-      "grad_norm": 17.66895866394043,
-      "kl": 3.521453890018165,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0035,
-      "reward": 6.361488223075867,
-      "reward_std": 0.6193077564239502,
-      "rewards/concensus_correctness_reward_func": 1.7603125115856528,
-      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.9722694717347622,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.453125,
-      "rewards/xmlcount_reward_func": 1.23828125,
       "step": 18
     },
     {
-      "completion_length": 137.41666666666666,
       "epoch": 5.0,
-      "grad_norm": 662.1502075195312,
-      "kl": 19.95021714673688,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.015,
-      "reward": 6.395626028378804,
-      "reward_std": 0.2608049809932709,
-      "rewards/concensus_correctness_reward_func": 1.999333341916402,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3333333333333333,
-      "rewards/question_recreation_reward_func": 0.9889176686604818,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.4166666666666667,
-      "rewards/xmlcount_reward_func": 1.1573749979337056,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.017387026955839248,
-      "train_runtime": 118.6454,
-      "train_samples_per_second": 2.697,
-      "train_steps_per_second": 0.169
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 211.65625,
       "epoch": 0.5714285714285714,
+      "grad_norm": 20.791494369506836,
       "kl": 0.0,
       "learning_rate": 5e-07,
+      "loss": 0.0,
+      "reward": 4.107439412735403,
+      "reward_std": 1.7247951165772974,
+      "rewards/concensus_correctness_reward_func": 1.373625005595386,
+      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7017831737175584,
+      "rewards/soft_format_reward_func": 0.015625,
+      "rewards/strict_format_reward_func": 0.21875,
+      "rewards/xmlcount_reward_func": 0.8601562511175871,
       "step": 2
     },
     {
+      "completion_length": 130.04166666666666,
       "epoch": 1.0,
+      "grad_norm": 1.9268100261688232,
+      "kl": 0.4157913678015272,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0003,
+      "reward": 6.637332359949748,
+      "reward_std": 0.07566171201566856,
+      "rewards/concensus_correctness_reward_func": 2.1075000067551932,
       "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.3333333333333333,
+      "rewards/question_recreation_reward_func": 0.9777490695317587,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4791666666666667,
+      "rewards/xmlcount_reward_func": 1.2395833333333333,
       "step": 4
     },
     {
+      "completion_length": 134.0,
       "epoch": 1.5714285714285714,
+      "grad_norm": 74.8565444946289,
+      "kl": 4.160505174426362,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0042,
+      "reward": 6.412162959575653,
+      "reward_std": 0.29878656659275293,
+      "rewards/concensus_correctness_reward_func": 1.9511249959468842,
       "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9766630195081234,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.453125,
+      "rewards/xmlcount_reward_func": 1.21875,
       "step": 6
     },
     {
+      "completion_length": 148.54166666666666,
       "epoch": 2.0,
+      "grad_norm": 13.83748722076416,
+      "kl": 0.5608995507160822,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0004,
+      "reward": 6.205713093280792,
+      "reward_std": 0.3365480999151866,
+      "rewards/concensus_correctness_reward_func": 1.6840833413104217,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.9122547407944998,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4583333333333333,
+      "rewards/xmlcount_reward_func": 1.234375,
       "step": 8
     },
     {
+      "completion_length": 140.15625,
       "epoch": 2.571428571428571,
+      "grad_norm": 3.1813089847564697,
+      "kl": 3.372719679493457,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0034,
+      "reward": 6.181028991937637,
+      "reward_std": 0.03739988969755359,
+      "rewards/concensus_correctness_reward_func": 1.7086249999701977,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.9958414621651173,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.484375,
+      "rewards/xmlcount_reward_func": 1.2421875,
       "step": 10
     },
     {
+      "completion_length": 128.25,
       "epoch": 3.0,
+      "grad_norm": 8.330719947814941,
+      "kl": 1.0418670388559501,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0008,
+      "reward": 6.871687571207683,
+      "reward_std": 0.17767540445008004,
+      "rewards/concensus_correctness_reward_func": 2.097833334157864,
+      "rewards/consensus_reward_func": 1.8333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3333333333333333,
+      "rewards/question_recreation_reward_func": 0.9821876039107641,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4166666666666667,
+      "rewards/xmlcount_reward_func": 1.2083333333333333,
       "step": 12
     },
     {
+      "completion_length": 129.84375,
       "epoch": 3.571428571428571,
+      "grad_norm": 38.57124710083008,
+      "kl": 16.248831458739005,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0162,
+      "reward": 6.711082369089127,
+      "reward_std": 0.24221534383832477,
+      "rewards/concensus_correctness_reward_func": 2.039750005118549,
+      "rewards/consensus_reward_func": 1.75,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.3125,
+      "rewards/question_recreation_reward_func": 0.9135198723524809,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.453125,
+      "rewards/xmlcount_reward_func": 1.2421875,
       "step": 14
     },
     {
+      "completion_length": 131.0,
       "epoch": 4.0,
+      "grad_norm": 0.27678772807121277,
+      "kl": 0.5124543802812696,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0004,
+      "reward": 5.603793223698934,
+      "reward_std": 0.5071550731857618,
+      "rewards/concensus_correctness_reward_func": 1.4969999939203262,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9036682297786077,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.4583333333333333,
+      "rewards/xmlcount_reward_func": 1.2447916666666667,
       "step": 16
     },
     {
+      "completion_length": 132.4375,
       "epoch": 4.571428571428571,
+      "grad_norm": 84.5380630493164,
+      "kl": 4.638578184763901,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0046,
+      "reward": 6.585173666477203,
+      "reward_std": 0.27560414862819016,
+      "rewards/concensus_correctness_reward_func": 1.7800624957308173,
+      "rewards/consensus_reward_func": 1.875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9621737338602543,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.46875,
+      "rewards/xmlcount_reward_func": 1.2491874992847443,
       "step": 18
     },
     {
+      "completion_length": 130.58333333333334,
       "epoch": 5.0,
+      "grad_norm": 14.72094440460205,
+      "kl": 0.3941649453093608,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0003,
+      "reward": 5.7585296630859375,
+      "reward_std": 0.5860855033000311,
+      "rewards/concensus_correctness_reward_func": 1.6730833401282628,
+      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.9187796910603842,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.5,
+      "rewards/xmlcount_reward_func": 1.25,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.0030604461819166316,
+      "train_runtime": 117.2262,
+      "train_samples_per_second": 2.73,
+      "train_steps_per_second": 0.171
     }
   ],
   "logging_steps": 2,