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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/sergisimi/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-timid_enormous_eel

SGLang

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

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

sergisimi commited on Apr 30, 2025

Commit

19b4434

verified ·

1 Parent(s): 1dd1cb1

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 +111 -111
training_args.bin +1 -1

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.003851097657752689,
-    "train_runtime": 129.1561,
     "train_samples": 28,
-    "train_samples_per_second": 2.478,
-    "train_steps_per_second": 0.155
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.207645982503891e-05,
+    "train_runtime": 260.6418,
     "train_samples": 28,
+    "train_samples_per_second": 1.228,
+    "train_steps_per_second": 0.077
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145886aa5c5830166affa98806c6645f1a8177b70da9b4b948543e554f5e30b9
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:ccb14be2a41de230ea96fa3215b25d5068fd9eb7c5636a202f6ec721482e538b
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 0.003851097657752689,
-    "train_runtime": 129.1561,
     "train_samples": 28,
-    "train_samples_per_second": 2.478,
-    "train_steps_per_second": 0.155
 }

 {
     "total_flos": 0.0,
+    "train_loss": 1.207645982503891e-05,
+    "train_runtime": 260.6418,
     "train_samples": 28,
+    "train_samples_per_second": 1.228,
+    "train_steps_per_second": 0.077
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 190.46875,
       "epoch": 0.5714285714285714,
-      "grad_norm": 22.96297836303711,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
-      "reward": 2.654471319168806,
-      "reward_std": 0.9432444697595201,
-      "rewards/concensus_correctness_reward_func": 0.5451875026337802,
-      "rewards/consensus_reward_func": 0.6875,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
-      "rewards/question_recreation_reward_func": 0.5615963010350242,
-      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.782062495010905,
       "step": 2
     },
     {
-      "completion_length": 133.54166666666666,
       "epoch": 1.0,
-      "grad_norm": 8.931957244873047,
-      "kl": 0.011637070410264036,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 3.8756035367647805,
-      "reward_std": 0.9740458515007049,
-      "rewards/concensus_correctness_reward_func": 1.0921666671832402,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6650618463754654,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.11837500333786,
       "step": 4
     },
     {
-      "completion_length": 128.59375,
       "epoch": 1.5714285714285714,
-      "grad_norm": 18.16290283203125,
-      "kl": 0.11650527472374961,
       "learning_rate": 4.472851273490984e-07,
-      "loss": 0.0001,
-      "reward": 3.67178101092577,
-      "reward_std": 1.011768163589295,
-      "rewards/concensus_correctness_reward_func": 0.989875003695488,
-      "rewards/consensus_reward_func": 0.625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6460934048518538,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1608124859631062,
       "step": 6
     },
     {
-      "completion_length": 153.83333333333334,
       "epoch": 2.0,
-      "grad_norm": 11.27619457244873,
-      "kl": 0.2840066327092548,
       "learning_rate": 3.867370395306068e-07,
-      "loss": 0.0002,
-      "reward": 5.526396517952283,
-      "reward_std": 1.5645808371870469,
-      "rewards/concensus_correctness_reward_func": 2.0540833373864493,
-      "rewards/consensus_reward_func": 1.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.7542715296149254,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1347083399693172,
       "step": 8
     },
     {
-      "completion_length": 179.4375,
       "epoch": 2.571428571428571,
-      "grad_norm": 11.838638305664062,
-      "kl": 0.7659143807541113,
       "learning_rate": 3.1137137178519977e-07,
-      "loss": 0.0008,
-      "reward": 3.2476816549897194,
-      "reward_std": 0.7884021905483678,
-      "rewards/concensus_correctness_reward_func": 0.607437502592802,
-      "rewards/consensus_reward_func": 0.75,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.6339628454297781,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1312812343239784,
       "step": 10
     },
     {
-      "completion_length": 123.83333333333333,
       "epoch": 3.0,
-      "grad_norm": 18.716581344604492,
-      "kl": 47.08470957400277,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0353,
-      "reward": 4.630525499582291,
-      "reward_std": 1.063371850070439,
-      "rewards/concensus_correctness_reward_func": 1.1735000101228554,
-      "rewards/consensus_reward_func": 1.1666666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3333333333333333,
-      "rewards/question_recreation_reward_func": 0.7733586716155211,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1836666464805603,
       "step": 12
     },
     {
-      "completion_length": 162.375,
       "epoch": 3.571428571428571,
-      "grad_norm": 18.296457290649414,
-      "kl": 0.4606957195792347,
       "learning_rate": 1.4957614383675767e-07,
-      "loss": 0.0005,
-      "reward": 4.084726072847843,
-      "reward_std": 1.7117217276827432,
-      "rewards/concensus_correctness_reward_func": 1.0414374987594783,
-      "rewards/consensus_reward_func": 0.9375,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.375,
-      "rewards/question_recreation_reward_func": 0.7195072192698717,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.0112812332808971,
       "step": 14
     },
     {
-      "completion_length": 149.25,
       "epoch": 4.0,
-      "grad_norm": 155.23793029785156,
-      "kl": 0.5404547471553087,
       "learning_rate": 8.067960709356478e-08,
-      "loss": 0.0004,
-      "reward": 3.666865130265554,
-      "reward_std": 1.0499570483031373,
-      "rewards/concensus_correctness_reward_func": 1.1503333350022633,
-      "rewards/consensus_reward_func": 0.9166666666666666,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.48182345802585286,
       "rewards/soft_format_reward_func": 0.0,
-      "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1180416742960613,
       "step": 16
     },
     {
-      "completion_length": 139.28125,
       "epoch": 4.571428571428571,
-      "grad_norm": 19.596712112426758,
-      "kl": 0.8444672944024205,
       "learning_rate": 3.013156219837776e-08,
-      "loss": 0.0008,
-      "reward": 4.524556450545788,
-      "reward_std": 1.2153915358403538,
-      "rewards/concensus_correctness_reward_func": 1.2592500033788383,
-      "rewards/consensus_reward_func": 1.125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.3125,
-      "rewards/question_recreation_reward_func": 0.6572438427247107,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.1705625094473362,
       "step": 18
     },
     {
-      "completion_length": 148.5,
       "epoch": 5.0,
-      "grad_norm": 10.512721061706543,
-      "kl": 0.5247808119747788,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0004,
-      "reward": 2.8889845808347068,
-      "reward_std": 1.294389241724275,
-      "rewards/concensus_correctness_reward_func": 0.6051666686932246,
-      "rewards/consensus_reward_func": 0.5833333333333334,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.5186512110133966,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 1.18183334171772,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 0.003851097657752689,
-      "train_runtime": 129.1561,
-      "train_samples_per_second": 2.478,
-      "train_steps_per_second": 0.155
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 412.3125,
       "epoch": 0.5714285714285714,
+      "grad_norm": 8.693182945251465,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
+      "reward": 0.6507176775485277,
+      "reward_std": 0.6124092356913025,
+      "rewards/concensus_correctness_reward_func": 0.08781250286847353,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0625,
+      "rewards/question_recreation_reward_func": 0.28593642602209,
+      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.214468750404194,
       "step": 2
     },
     {
+      "completion_length": 466.25,
       "epoch": 1.0,
+      "grad_norm": 6.593066692352295,
+      "kl": 0.0008837033092277125,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 0.01616879238281399,
+      "reward_std": 0.5097802079787167,
+      "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": 0.15091879002284259,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.13475000113248825,
       "step": 4
     },
     {
+      "completion_length": 355.6875,
       "epoch": 1.5714285714285714,
+      "grad_norm": 11.000882148742676,
+      "kl": 0.0023792490392224863,
       "learning_rate": 4.472851273490984e-07,
+      "loss": 0.0,
+      "reward": 0.39020980754867196,
+      "reward_std": 0.26090634902357124,
+      "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": 0.20180355216143653,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.18840625090524554,
       "step": 6
     },
     {
+      "completion_length": 280.9583333333333,
       "epoch": 2.0,
+      "grad_norm": 6.325510025024414,
+      "kl": 0.0049716349846373005,
       "learning_rate": 3.867370395306068e-07,
+      "loss": 0.0,
+      "reward": 0.5647080475852514,
+      "reward_std": 0.42333035657187185,
+      "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": 0.23416637043313435,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.16387500427663326,
       "step": 8
     },
     {
+      "completion_length": 416.375,
       "epoch": 2.571428571428571,
+      "grad_norm": 13.391995429992676,
+      "kl": 0.0028864733321825042,
       "learning_rate": 3.1137137178519977e-07,
+      "loss": 0.0,
+      "reward": 0.48623845574911684,
+      "reward_std": 0.5935565652034711,
+      "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": 0.36095721216406673,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.12528124917298555,
       "step": 10
     },
     {
+      "completion_length": 364.9166666666667,
       "epoch": 3.0,
+      "grad_norm": 3.5537571907043457,
+      "kl": 0.0015641524660168216,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0,
+      "reward": 0.19067977027346691,
+      "reward_std": 0.23696730316927037,
+      "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": 0.2990131077046196,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.19166666952272257,
       "step": 12
     },
     {
+      "completion_length": 443.375,
       "epoch": 3.571428571428571,
+      "grad_norm": 79.65965270996094,
+      "kl": 0.003594304173020646,
       "learning_rate": 1.4957614383675767e-07,
+      "loss": 0.0,
+      "reward": 0.3781135913450271,
+      "reward_std": 0.6029232723958557,
+      "rewards/concensus_correctness_reward_func": 0.0390625,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.25133233331143856,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": -0.037281252443790436,
       "step": 14
     },
     {
+      "completion_length": 411.375,
       "epoch": 4.0,
+      "grad_norm": 4.510103225708008,
+      "kl": 0.004420468278112821,
       "learning_rate": 8.067960709356478e-08,
+      "loss": 0.0,
+      "reward": 0.5334217097455015,
+      "reward_std": 0.7162827632710105,
+      "rewards/concensus_correctness_reward_func": 0.00016666667458290854,
+      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.08333333333333333,
+      "rewards/question_recreation_reward_func": 0.24838005809579045,
       "rewards/soft_format_reward_func": 0.0,
+      "rewards/strict_format_reward_func": 0.020833333333333332,
+      "rewards/xmlcount_reward_func": 0.09737498976755887,
       "step": 16
     },
     {
+      "completion_length": 318.71875,
       "epoch": 4.571428571428571,
+      "grad_norm": 23.564010620117188,
+      "kl": 0.09915753048335318,
       "learning_rate": 3.013156219837776e-08,
+      "loss": 0.0001,
+      "reward": 0.5345051889307797,
+      "reward_std": 0.42700082808732986,
+      "rewards/concensus_correctness_reward_func": 0.0,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.2431302194017917,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.16637500002980232,
       "step": 18
     },
     {
+      "completion_length": 363.1666666666667,
       "epoch": 5.0,
+      "grad_norm": 3.7814338207244873,
+      "kl": 0.004537726340155738,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.0,
+      "reward": 0.39819195633754134,
+      "reward_std": 0.39827561921750504,
+      "rewards/concensus_correctness_reward_func": 0.010416666666666666,
+      "rewards/consensus_reward_func": 0.0,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.27081696409732103,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.11695832991972566,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 1.207645982503891e-05,
+      "train_runtime": 260.6418,
+      "train_samples_per_second": 1.228,
+      "train_steps_per_second": 0.077
     }
   ],
   "logging_steps": 2,

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40ef5faf9a65254b35bda94df2410f3b0c3fffeda22fd687a95db9eb6dab75d
 size 6008

 version https://git-lfs.github.com/spec/v1
+oid sha256:e23441016674501e92849d3e95ba05462a09eeb9a19b8186b12160b64e449c0b
 size 6008