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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/MajorJalud/Qwen2.5-0.5B-Instruct-Gensyn-Swarm-reptilian_strong_gull

SGLang

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

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

MajorJalud commited on Apr 30, 2025

Commit

0dfff95

verified ·

1 Parent(s): 765ac2e

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 +103 -103

all_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 1.5017203986644745e-05,
-    "train_runtime": 249.5767,
     "train_samples": 28,
-    "train_samples_per_second": 1.282,
-    "train_steps_per_second": 0.08
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.026718258014625462,
+    "train_runtime": 202.5588,
     "train_samples": 28,
+    "train_samples_per_second": 1.58,
+    "train_steps_per_second": 0.099
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7defa64ce918cc401a3f6174fc9f021e685b07b42799981cf297464c47e62b06
 size 1976163472

 version https://git-lfs.github.com/spec/v1
+oid sha256:3ebd44739dd8ca567a2df4bf951a6b978b5553c793bf98cf3ff89aeb274d4035
 size 1976163472

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
     "total_flos": 0.0,
-    "train_loss": 1.5017203986644745e-05,
-    "train_runtime": 249.5767,
     "train_samples": 28,
-    "train_samples_per_second": 1.282,
-    "train_steps_per_second": 0.08
 }

 {
     "total_flos": 0.0,
+    "train_loss": 0.026718258014625462,
+    "train_runtime": 202.5588,
     "train_samples": 28,
+    "train_samples_per_second": 1.58,
+    "train_steps_per_second": 0.099
 }

trainer_state.json CHANGED Viewed

@@ -10,203 +10,203 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "completion_length": 364.65625,
       "epoch": 0.5714285714285714,
-      "grad_norm": 10.477097511291504,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
-      "reward": 2.0702435802668333,
-      "reward_std": 1.4857124503687373,
-      "rewards/concensus_correctness_reward_func": 0.7316250018775463,
-      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.4942748392932117,
-      "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5318437432870269,
       "step": 2
     },
     {
-      "completion_length": 366.5416666666667,
       "epoch": 1.0,
-      "grad_norm": 4.934039115905762,
-      "kl": 0.0017826293381707121,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
-      "reward": 1.8575934693217278,
-      "reward_std": 0.3709045405654858,
-      "rewards/concensus_correctness_reward_func": 0.010416666666666666,
-      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6222184092427293,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.8916250020265579,
       "step": 4
     },
     {
-      "completion_length": 297.875,
       "epoch": 1.5714285714285714,
-      "grad_norm": 7.124934196472168,
-      "kl": 0.0036754943284904584,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
-      "reward": 2.0384698435664177,
-      "reward_std": 0.882993227802217,
-      "rewards/concensus_correctness_reward_func": 0.21437500044703484,
-      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.125,
-      "rewards/question_recreation_reward_func": 0.6718135485425591,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.7147812694311142,
       "step": 6
     },
     {
-      "completion_length": 320.75,
       "epoch": 2.0,
-      "grad_norm": 6.851337909698486,
-      "kl": 0.023235641710925847,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
-      "reward": 2.1065516571203866,
-      "reward_std": 2.2024015622834363,
-      "rewards/concensus_correctness_reward_func": 0.40991666354238987,
-      "rewards/consensus_reward_func": 0.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.16666666666666666,
-      "rewards/question_recreation_reward_func": 0.6723016227285067,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.44099996984004974,
       "step": 8
     },
     {
-      "completion_length": 431.15625,
       "epoch": 2.571428571428571,
-      "grad_norm": 5.705810070037842,
-      "kl": 0.005559436991461553,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
-      "reward": 1.4008867628872395,
-      "reward_std": 1.075131708290428,
-      "rewards/concensus_correctness_reward_func": 0.1301250010728836,
-      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.7091679945588112,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.24909375607967377,
       "step": 10
     },
     {
-      "completion_length": 332.75,
       "epoch": 3.0,
-      "grad_norm": 6.264803886413574,
-      "kl": 0.08360444092735027,
       "learning_rate": 2.2935516363191693e-07,
-      "loss": 0.0001,
-      "reward": 1.9641168316205342,
-      "reward_std": 1.355897097537915,
-      "rewards/concensus_correctness_reward_func": 0.12266666690508525,
-      "rewards/consensus_reward_func": 0.16666666666666666,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.7957418213287989,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.6290416792035103,
       "step": 12
     },
     {
-      "completion_length": 311.84375,
       "epoch": 3.571428571428571,
-      "grad_norm": 14.850531578063965,
-      "kl": 0.027085226800409146,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
-      "reward": 2.7452946454286575,
-      "reward_std": 1.3187832357507432,
-      "rewards/concensus_correctness_reward_func": 0.453187498729676,
-      "rewards/consensus_reward_func": 0.5625,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.1875,
-      "rewards/question_recreation_reward_func": 0.7929508425295353,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.7491562552750111,
       "step": 14
     },
     {
-      "completion_length": 457.75,
       "epoch": 4.0,
-      "grad_norm": 182.8489532470703,
-      "kl": 0.007795430457917973,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
-      "reward": 0.8547929128011068,
-      "reward_std": 1.6759886934111516,
-      "rewards/concensus_correctness_reward_func": 0.08216666678587596,
-      "rewards/consensus_reward_func": 0.08333333333333333,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.08333333333333333,
-      "rewards/question_recreation_reward_func": 0.6429179199039936,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": -0.036958351731300354,
       "step": 16
     },
     {
-      "completion_length": 320.71875,
       "epoch": 4.571428571428571,
-      "grad_norm": 6.350405216217041,
-      "kl": 0.02030823429231532,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
-      "reward": 2.1387240011245012,
-      "reward_std": 0.8510065458249301,
-      "rewards/concensus_correctness_reward_func": 0.33274999214336276,
-      "rewards/consensus_reward_func": 0.3125,
       "rewards/cumulative_reward_2": 0.0,
-      "rewards/final_correctness_reward_func": 0.25,
-      "rewards/question_recreation_reward_func": 0.6963489514309913,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.5471250005066395,
       "step": 18
     },
     {
-      "completion_length": 333.9583333333333,
       "epoch": 5.0,
-      "grad_norm": 4.745396614074707,
-      "kl": 0.011538434812488655,
       "learning_rate": 3.4096741493194193e-09,
-      "loss": 0.0,
-      "reward": 1.4878136217594147,
-      "reward_std": 1.510166530807813,
-      "rewards/concensus_correctness_reward_func": 0.2243333359559377,
-      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
-      "rewards/question_recreation_reward_func": 0.6901885569095612,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
-      "rewards/xmlcount_reward_func": 0.3232916792233785,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
-      "train_loss": 1.5017203986644745e-05,
-      "train_runtime": 249.5767,
-      "train_samples_per_second": 1.282,
-      "train_steps_per_second": 0.08
     }
   ],
   "logging_steps": 2,

   "is_world_process_zero": true,
   "log_history": [
     {
+      "completion_length": 277.4375,
       "epoch": 0.5714285714285714,
+      "grad_norm": 6.789405822753906,
       "kl": 0.0,
       "learning_rate": 5e-07,
       "loss": -0.0,
+      "reward": 2.3237390760332346,
+      "reward_std": 1.5290137782576494,
+      "rewards/concensus_correctness_reward_func": 0.8025624714791775,
+      "rewards/consensus_reward_func": 0.125,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.5013640912948176,
+      "rewards/soft_format_reward_func": 0.015625,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.6916875028982759,
       "step": 2
     },
     {
+      "completion_length": 240.41666666666666,
       "epoch": 1.0,
+      "grad_norm": 4.878081798553467,
+      "kl": 0.002382916432300893,
       "learning_rate": 4.864543104251586e-07,
       "loss": 0.0,
+      "reward": 2.5553423265616098,
+      "reward_std": 0.5683276208971316,
+      "rewards/concensus_correctness_reward_func": 0.42125000059604645,
+      "rewards/consensus_reward_func": 0.4166666666666667,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6468839564671119,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.0705416450897853,
       "step": 4
     },
     {
+      "completion_length": 320.875,
       "epoch": 1.5714285714285714,
+      "grad_norm": 81.54737091064453,
+      "kl": 0.0035806876549031585,
       "learning_rate": 4.472851273490984e-07,
       "loss": 0.0,
+      "reward": 2.4654137454926968,
+      "reward_std": 1.087094948044978,
+      "rewards/concensus_correctness_reward_func": 0.2971874997019768,
+      "rewards/consensus_reward_func": 0.5,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.7451949981041253,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.9230312146246433,
       "step": 6
     },
     {
+      "completion_length": 322.5416666666667,
       "epoch": 2.0,
+      "grad_norm": 4.378849506378174,
+      "kl": 0.006137622442717354,
       "learning_rate": 3.867370395306068e-07,
       "loss": 0.0,
+      "reward": 2.417641818523407,
+      "reward_std": 0.9718923264493545,
+      "rewards/concensus_correctness_reward_func": 0.27650000154972076,
+      "rewards/consensus_reward_func": 0.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.7511000943680605,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.8067083209753036,
       "step": 8
     },
     {
+      "completion_length": 263.78125,
       "epoch": 2.571428571428571,
+      "grad_norm": 7.5848822593688965,
+      "kl": 0.010713139752624556,
       "learning_rate": 3.1137137178519977e-07,
       "loss": 0.0,
+      "reward": 2.334370069205761,
+      "reward_std": 1.0359732687065843,
+      "rewards/concensus_correctness_reward_func": 0.2455000001937151,
+      "rewards/consensus_reward_func": 0.4375,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6358388164080679,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.0155312195420265,
       "step": 10
     },
     {
+      "completion_length": 265.6666666666667,
       "epoch": 3.0,
+      "grad_norm": 6.6377458572387695,
+      "kl": 0.0317639890126884,
       "learning_rate": 2.2935516363191693e-07,
+      "loss": 0.0,
+      "reward": 2.7291881144046783,
+      "reward_std": 0.9668942355783656,
+      "rewards/concensus_correctness_reward_func": 0.49399999777475995,
+      "rewards/consensus_reward_func": 0.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.25,
+      "rewards/question_recreation_reward_func": 0.6956047763427099,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.9562499796350797,
       "step": 12
     },
     {
+      "completion_length": 258.9375,
       "epoch": 3.571428571428571,
+      "grad_norm": 5.181027889251709,
+      "kl": 0.01114592287922278,
       "learning_rate": 1.4957614383675767e-07,
       "loss": 0.0,
+      "reward": 2.9897976852953434,
+      "reward_std": 1.4940979477250949,
+      "rewards/concensus_correctness_reward_func": 0.7932500019669533,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.125,
+      "rewards/question_recreation_reward_func": 0.7159852180629969,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 1.1055624894797802,
       "step": 14
     },
     {
+      "completion_length": 292.5,
       "epoch": 4.0,
+      "grad_norm": 5.158603191375732,
+      "kl": 0.03570538493416583,
       "learning_rate": 8.067960709356478e-08,
       "loss": 0.0,
+      "reward": 2.0371210873126984,
+      "reward_std": 0.7878820024585972,
+      "rewards/concensus_correctness_reward_func": 0.23308333257834116,
+      "rewards/consensus_reward_func": 0.25,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6077877643207709,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.9462499924314519,
       "step": 16
     },
     {
+      "completion_length": 276.5625,
       "epoch": 4.571428571428571,
+      "grad_norm": 5.967617988586426,
+      "kl": 0.018310003797523677,
       "learning_rate": 3.013156219837776e-08,
       "loss": 0.0,
+      "reward": 2.2351491451263428,
+      "reward_std": 0.8348404020653106,
+      "rewards/concensus_correctness_reward_func": 0.1536250002682209,
+      "rewards/consensus_reward_func": 0.1875,
       "rewards/cumulative_reward_2": 0.0,
+      "rewards/final_correctness_reward_func": 0.1875,
+      "rewards/question_recreation_reward_func": 0.7462741751223803,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.9602499902248383,
       "step": 18
     },
     {
+      "completion_length": 427.9583333333333,
       "epoch": 5.0,
+      "grad_norm": 4.099704265594482,
+      "kl": 356.1126844395476,
       "learning_rate": 3.4096741493194193e-09,
+      "loss": 0.2671,
+      "reward": 1.3956897395352523,
+      "reward_std": 1.659088636127611,
+      "rewards/concensus_correctness_reward_func": 0.18975000083446503,
+      "rewards/consensus_reward_func": 0.3333333333333333,
       "rewards/cumulative_reward_2": 0.0,
       "rewards/final_correctness_reward_func": 0.0,
+      "rewards/question_recreation_reward_func": 0.6243564016185701,
       "rewards/soft_format_reward_func": 0.0,
       "rewards/strict_format_reward_func": 0.0,
+      "rewards/xmlcount_reward_func": 0.2482500026623408,
       "step": 20
     },
     {
       "epoch": 5.0,
       "step": 20,
       "total_flos": 0.0,
+      "train_loss": 0.026718258014625462,
+      "train_runtime": 202.5588,
+      "train_samples_per_second": 1.58,
+      "train_steps_per_second": 0.099
     }
   ],
   "logging_steps": 2,