Instructions to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with Transformers:

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

pipe = pipeline("text-generation", model="aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara")
model = AutoModelForCausalLM.from_pretrained("aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara", 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 aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara

SGLang

How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara 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 "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara" \
    --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": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"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 "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara" \
        --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": "aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara with Docker Model Runner:
```
docker model run hf.co/aayasmin880/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-colorful_fanged_capybara
```

aayasmin880 commited on Apr 14, 2025

Commit

92f9626

verified ·

1 Parent(s): 4194b7f

End of training

Browse files

Files changed (4) hide show

all_results.json +3 -3
model.safetensors +1 -1
train_results.json +3 -3
trainer_state.json +115 -115

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 12557.179350649192,
-    "train_runtime": 313.5081,
     "train_samples": 28,
-    "train_samples_per_second": 1.021,
     "train_steps_per_second": 0.064
 }

 {
     "total_flos": 0.0,
+    "train_loss": 43033.42119616177,
+    "train_runtime": 312.1714,
     "train_samples": 28,
+    "train_samples_per_second": 1.025,
     "train_steps_per_second": 0.064
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e25c2e14d5e63f3c46a728cc660dde808fac00dc195b10adf5c6e984bba1c9
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:ac5c451344506c116d5750e405899206c19429dd5a5d349918d3a3bc251aa0a3
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 12557.179350649192,
-    "train_runtime": 313.5081,
     "train_samples": 28,
-    "train_samples_per_second": 1.021,
     "train_steps_per_second": 0.064
 }

 {
     "total_flos": 0.0,
+    "train_loss": 43033.42119616177,
+    "train_runtime": 312.1714,
     "train_samples": 28,
+    "train_samples_per_second": 1.025,
     "train_steps_per_second": 0.064
 }

trainer_state.json CHANGED Viewed

@@ -10,202 +10,202 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 193.03125,
       "epoch": 0.5714285714285714,
-      "grad_norm": 58.96494674682617,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
-      "reward": 3.9653831757605076,
-      "reward_std": 1.6660508274399035,
-      "rewards/concensus_correctness_reward_func": 1.3522499948740005,
-      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.6935394024476409,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.09375,
-      "rewards/xmlcount_reward_func": 0.8258437626063824,
       "step": 2
     },
     {
-      "completion_length": 158.45833333333334,
       "epoch": 1.0,
-      "grad_norm": 11952.29296875,
-      "kl": 184.58293704595417,
       "learning_rate": 4.864543104251586e-07,
-      "loss": 0.1384,
-      "reward": 4.575585693120956,
-      "reward_std": 1.3194325535247724,
-      "rewards/concensus_correctness_reward_func": 1.4599166363477707,
-      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.6824189899489284,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.14583333333333334,
-      "rewards/xmlcount_reward_func": 0.8707499926288923,
       "step": 4
     },
     {
-      "completion_length": 167.125,
       "epoch": 1.5714285714285714,
-      "grad_norm": 13332.767578125,
-      "kl": 3023.1682174415328,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 3.0232,
-      "reward": 5.874457582831383,
-      "reward_std": 0.6478101983811939,
-      "rewards/concensus_correctness_reward_func": 1.811624988913536,
-      "rewards/consensus_reward_func": 1.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.9079888015985489,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.296875,
-      "rewards/xmlcount_reward_func": 1.1079687476158142,
       "step": 6
     },
     {
-      "completion_length": 152.04166666666666,
       "epoch": 2.0,
-      "grad_norm": 79987.484375,
-      "kl": 90168.79363891482,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 67.6266,
-      "reward": 5.187588373819987,
-      "reward_std": 1.0589998407910268,
-      "rewards/concensus_correctness_reward_func": 1.417999967932701,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.8533799548943838,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.20833333333333334,
-      "rewards/xmlcount_reward_func": 1.1245416700839996,
       "step": 8
     },
     {
-      "completion_length": 157.53125,
       "epoch": 2.571428571428571,
-      "grad_norm": 3333359360.0,
-      "kl": 125493555.85986722,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 125493.5625,
-      "reward": 5.848238706588745,
-      "reward_std": 0.6607750835828483,
-      "rewards/concensus_correctness_reward_func": 1.6875624880194664,
       "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.9156449176371098,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.265625,
-      "rewards/xmlcount_reward_func": 1.1669062599539757,
       "step": 10
     },
     {
-      "completion_length": 195.79166666666666,
       "epoch": 3.0,
-      "grad_norm": 271.3752136230469,
-      "kl": 273.68281539777917,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.2053,
-      "reward": 4.707200989127159,
-      "reward_std": 1.0174018343289692,
-      "rewards/concensus_correctness_reward_func": 1.2951666414737701,
-      "rewards/consensus_reward_func": 1.25,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.88674263159434,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.20833333333333334,
-      "rewards/xmlcount_reward_func": 0.9836249972383181,
       "step": 12
     },
     {
-      "completion_length": 166.96875,
       "epoch": 3.571428571428571,
-      "grad_norm": 110.81871032714844,
-      "kl": 381.98320501018316,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.382,
-      "reward": 5.036348949186504,
-      "reward_std": 0.7069780651872861,
-      "rewards/concensus_correctness_reward_func": 1.4621874764561653,
-      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.8386613675393164,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.15625,
-      "rewards/xmlcount_reward_func": 1.016749992966652,
       "step": 14
     },
     {
-      "completion_length": 156.625,
       "epoch": 4.0,
-      "grad_norm": 134596.234375,
-      "kl": 2400.9205045119547,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 1.8007,
-      "reward": 6.160478989283244,
-      "reward_std": 0.551658857613802,
-      "rewards/concensus_correctness_reward_func": 1.9151666462421417,
-      "rewards/consensus_reward_func": 1.8333333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.936062236626943,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.2916666666666667,
-      "rewards/xmlcount_reward_func": 1.1009166712562244,
       "step": 16
     },
     {
-      "completion_length": 164.0,
       "epoch": 4.571428571428571,
-      "grad_norm": 263.9651184082031,
-      "kl": 4597.32190877432,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 4.5973,
-      "reward": 5.041443020105362,
-      "reward_std": 1.1247155531891622,
-      "rewards/concensus_correctness_reward_func": 1.4394999742507935,
-      "rewards/consensus_reward_func": 1.4375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.8013805472292006,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.296875,
-      "rewards/xmlcount_reward_func": 1.066187497228384,
       "step": 18
     },
     {
-      "completion_length": 171.20833333333334,
       "epoch": 5.0,
-      "grad_norm": 50.64336395263672,
-      "kl": 610.0436264934639,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.4575,
-      "reward": 5.777886807918549,
-      "reward_std": 0.557022233454821,
-      "rewards/concensus_correctness_reward_func": 1.7898333221673965,
-      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.9035117427508036,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.2708333333333333,
-      "rewards/xmlcount_reward_func": 1.1470416635274887,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 12557.179350649192,
-      "train_runtime": 313.5081,
-      "train_samples_per_second": 1.021,
       "train_steps_per_second": 0.064
     }
   ],

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 210.03125,
       "epoch": 0.5714285714285714,
+      "grad_norm": 38.42770004272461,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 3.1439394298940897,
+      "reward_std": 0.5252274667145684,
+      "rewards/concensus_correctness_reward_func": 0.656312495470047,
+      "rewards/consensus_reward_func": 0.8125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.7196894609369338,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.078125,
+      "rewards/xmlcount_reward_func": 0.8148124924628064,
       "step": 2
     },
     {
+      "completion_length": 156.33333333333334,
       "epoch": 1.0,
+      "grad_norm": 4170.4482421875,
+      "kl": 156.81029507890344,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.1176,
+      "reward": 5.1805073618888855,
+      "reward_std": 1.0655745367209117,
+      "rewards/concensus_correctness_reward_func": 1.6409999926884968,
+      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.8420073688030243,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.14583333333333334,
+      "rewards/xmlcount_reward_func": 1.0516666769981384,
       "step": 4
     },
     {
+      "completion_length": 165.53125,
       "epoch": 1.5714285714285714,
+      "grad_norm": 5900.6318359375,
+      "kl": 277.0447297161445,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.277,
+      "reward": 5.539489239454269,
+      "reward_std": 1.0853041551599745,
+      "rewards/concensus_correctness_reward_func": 1.744750004261732,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.9061142913997173,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.296875,
+      "rewards/xmlcount_reward_func": 1.1542499959468842,
       "step": 6
     },
     {
+      "completion_length": 154.33333333333334,
       "epoch": 2.0,
+      "grad_norm": 40.677032470703125,
+      "kl": 573743646.4254172,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 430307.7812,
+      "reward": 4.766020397345225,
+      "reward_std": 0.8017827707032362,
+      "rewards/concensus_correctness_reward_func": 1.1446666518847148,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.9214786340792974,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.14583333333333334,
+      "rewards/xmlcount_reward_func": 1.0540416638056438,
       "step": 8
     },
     {
+      "completion_length": 169.25,
       "epoch": 2.571428571428571,
+      "grad_norm": 85725.234375,
+      "kl": 10783.553622539155,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 10.7836,
+      "reward": 5.778173103928566,
+      "reward_std": 0.2837759969988838,
+      "rewards/concensus_correctness_reward_func": 1.6284999996423721,
       "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.8933918830007315,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.28125,
+      "rewards/xmlcount_reward_func": 1.1625312454998493,
       "step": 10
     },
     {
+      "completion_length": 182.375,
       "epoch": 3.0,
+      "grad_norm": 140.15249633789062,
+      "kl": 4297.434334080045,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 3.2231,
+      "reward": 5.077693402767181,
+      "reward_std": 1.1513101535771664,
+      "rewards/concensus_correctness_reward_func": 1.5054999937613804,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7867766891916593,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.3125,
+      "rewards/xmlcount_reward_func": 0.9729166626930237,
       "step": 12
     },
     {
+      "completion_length": 158.34375,
       "epoch": 3.571428571428571,
+      "grad_norm": 183.3424072265625,
+      "kl": 572.9574657063931,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.573,
+      "reward": 5.174263447523117,
+      "reward_std": 0.9106845755595714,
+      "rewards/concensus_correctness_reward_func": 1.2946874983608723,
+      "rewards/consensus_reward_func": 1.375,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9312321078032255,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.1875,
+      "rewards/xmlcount_reward_func": 1.1358437575399876,
       "step": 14
     },
     {
+      "completion_length": 208.375,
       "epoch": 4.0,
+      "grad_norm": 42.9337158203125,
+      "kl": 14125.317962361849,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 10.594,
+      "reward": 5.136576334635417,
+      "reward_std": 0.760711227504847,
+      "rewards/concensus_correctness_reward_func": 1.6896666636069615,
+      "rewards/consensus_reward_func": 1.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8056180228789648,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 0.9746249914169312,
       "step": 16
     },
     {
+      "completion_length": 175.25,
       "epoch": 4.571428571428571,
+      "grad_norm": 51.13330078125,
+      "kl": 732.6771075335273,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.7327,
+      "reward": 5.404990047216415,
+      "reward_std": 0.9904180687153712,
+      "rewards/concensus_correctness_reward_func": 1.6389999948441982,
+      "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.8332400787621737,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.234375,
+      "rewards/xmlcount_reward_func": 1.0108749978244305,
       "step": 18
     },
     {
+      "completion_length": 224.16666666666666,
       "epoch": 5.0,
+      "grad_norm": 35.779361724853516,
+      "kl": 173.07598784628013,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.1298,
+      "reward": 5.683184266090393,
+      "reward_std": 0.5729284691042267,
+      "rewards/concensus_correctness_reward_func": 1.6922499934832256,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.9066841577490171,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.22916666666666666,
+      "rewards/xmlcount_reward_func": 1.1050833364327748,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 43033.42119616177,
+      "train_runtime": 312.1714,
+      "train_samples_per_second": 1.025,
       "train_steps_per_second": 0.064
     }
   ],