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

eb7481f

verified ·

1 Parent(s): 92f9626

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 +116 -116

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "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
 }

 {
     "total_flos": 0.0,
+    "train_loss": 276.2225516567356,
+    "train_runtime": 281.6381,
     "train_samples": 28,
+    "train_samples_per_second": 1.136,
+    "train_steps_per_second": 0.071
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5c451344506c116d5750e405899206c19429dd5a5d349918d3a3bc251aa0a3
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:34f60fcf4d19dd91f15bbcab04e57ac0642d096289b2fbf0935821e7fde1bc97
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "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
 }

 {
     "total_flos": 0.0,
+    "train_loss": 276.2225516567356,
+    "train_runtime": 281.6381,
     "train_samples": 28,
+    "train_samples_per_second": 1.136,
+    "train_steps_per_second": 0.071
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "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
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 221.78125,
       "epoch": 0.5714285714285714,
+      "grad_norm": 44.2175407409668,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": 0.0,
+      "reward": 2.9738675877451897,
+      "reward_std": 1.0762588446959853,
+      "rewards/concensus_correctness_reward_func": 0.5766874961555004,
+      "rewards/consensus_reward_func": 0.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.6785862769465894,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.125,
+      "rewards/xmlcount_reward_func": 0.7810937496833503,
       "step": 2
     },
     {
+      "completion_length": 135.91666666666666,
       "epoch": 1.0,
+      "grad_norm": 66.27912139892578,
+      "kl": 2.3285048588489494,
       "learning_rate": 4.864543104251586e-07,
+      "loss": 0.0017,
+      "reward": 5.826431592305501,
+      "reward_std": 0.526840340035657,
+      "rewards/concensus_correctness_reward_func": 1.7633333156506221,
+      "rewards/consensus_reward_func": 1.6666666666666667,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.16666666666666666,
+      "rewards/question_recreation_reward_func": 0.9518067538738251,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.14583333333333334,
+      "rewards/xmlcount_reward_func": 1.1321250200271606,
       "step": 4
     },
     {
+      "completion_length": 165.21875,
       "epoch": 1.5714285714285714,
+      "grad_norm": 119.87489318847656,
+      "kl": 6.061437373049557,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0061,
+      "reward": 5.755701020359993,
+      "reward_std": 0.4729832162265666,
+      "rewards/concensus_correctness_reward_func": 1.6936249807476997,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9547946453094482,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.25,
+      "rewards/xmlcount_reward_func": 1.1697812601923943,
       "step": 6
     },
     {
+      "completion_length": 221.70833333333334,
       "epoch": 2.0,
+      "grad_norm": 20.817134857177734,
+      "kl": 57.671127824423216,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0433,
+      "reward": 4.858392099539439,
+      "reward_std": 0.8551506837635922,
+      "rewards/concensus_correctness_reward_func": 1.325499986608823,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8866838018099467,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.1875,
+      "rewards/xmlcount_reward_func": 0.9587083285053571,
       "step": 8
     },
     {
+      "completion_length": 169.3125,
       "epoch": 2.571428571428571,
+      "grad_norm": 815.629638671875,
+      "kl": 396.3667468437925,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.3964,
+      "reward": 5.350141152739525,
+      "reward_std": 1.023946863017045,
+      "rewards/concensus_correctness_reward_func": 1.4176249876618385,
       "rewards/consensus_reward_func": 1.625,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.8144536353647709,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.28125,
+      "rewards/xmlcount_reward_func": 1.149312499910593,
       "step": 10
     },
     {
+      "completion_length": 154.91666666666666,
       "epoch": 3.0,
+      "grad_norm": 13.932165145874023,
+      "kl": 48.64000315094987,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0365,
+      "reward": 5.230659147103627,
+      "reward_std": 1.0175091188090544,
+      "rewards/concensus_correctness_reward_func": 1.4169166485468547,
       "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.9168258557717005,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.2916666666666667,
+      "rewards/xmlcount_reward_func": 1.1052500034372013,
       "step": 12
     },
     {
+      "completion_length": 157.1875,
       "epoch": 3.571428571428571,
+      "grad_norm": 104585.2109375,
+      "kl": 1291.072402872378,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 1.2911,
+      "reward": 5.096369080245495,
+      "reward_std": 0.6724874223291408,
+      "rewards/concensus_correctness_reward_func": 1.30749998614192,
+      "rewards/consensus_reward_func": 1.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.8557440210133791,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.203125,
+      "rewards/xmlcount_reward_func": 1.1050000004470348,
       "step": 14
     },
     {
+      "completion_length": 168.04166666666666,
       "epoch": 4.0,
+      "grad_norm": 60.78169250488281,
+      "kl": 69.18981406961878,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0519,
+      "reward": 5.668841242790222,
+      "reward_std": 0.5492350263909126,
+      "rewards/concensus_correctness_reward_func": 1.6425833106040955,
+      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.9639245718717575,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.22916666666666666,
+      "rewards/xmlcount_reward_func": 1.1665000071128209,
       "step": 16
     },
     {
+      "completion_length": 160.4375,
       "epoch": 4.571428571428571,
+      "grad_norm": 1224284.25,
+      "kl": 2755872.7097657053,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 2755.8726,
+      "reward": 5.473804086446762,
+      "reward_std": 0.5497146583074937,
+      "rewards/concensus_correctness_reward_func": 1.6534999832510948,
+      "rewards/consensus_reward_func": 1.6875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8431166224181652,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.171875,
+      "rewards/xmlcount_reward_func": 1.1178125068545341,
       "step": 18
     },
     {
+      "completion_length": 180.16666666666666,
       "epoch": 5.0,
+      "grad_norm": 4358.30029296875,
+      "kl": 6034.774716264258,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 4.5261,
+      "reward": 5.012901981671651,
+      "reward_std": 0.9920631875284016,
+      "rewards/concensus_correctness_reward_func": 1.3304999868075054,
+      "rewards/consensus_reward_func": 1.5833333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.8219852795203527,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.20833333333333334,
+      "rewards/xmlcount_reward_func": 1.0687500089406967,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 276.2225516567356,
+      "train_runtime": 281.6381,
+      "train_samples_per_second": 1.136,
+      "train_steps_per_second": 0.071
     }
   ],
   "logging_steps": 2,