Downloads · 30 days
2
6% of all-time downloads
iscreamai/gemma-3-1b-agentbank-checkpoint-57500
gemma-3-1b-agentbank-checkpoint-57500 is a machine learning model from iscreamai. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
이 모델은 Google Gemma-3-1B-IT 모델을 AgentBank 데이터셋으로 파인튜닝한 체크포인트입니다.
Downloads · 30 days
2
6% of all-time downloads
All-time downloads
31
Public
Parameters
1000M
6 GB on disk
Likes
0
Public
Click a slice to open those files.
.pt4 GB · 66%
From the Hugging Face model README
이 모델은 Google Gemma-3-1B-IT 모델을 AgentBank 데이터셋으로 파인튜닝한 체크포인트입니다.
from transformers import AutoModelForCausalLM, AutoTokenizer
# 모델과 토크나이저 로드
model = AutoModelForCausalLM.from_pretrained(
"iscreamai/gemma-3-1b-agentbank-checkpoint-57500",
torch_dtype="auto",
device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained("iscreamai/gemma-3-1b-agentbank-checkpoint-57500")
# 추론 예시
prompt = "안녕하세요! 무엇을 도와드릴까요?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=100, do_sample=True, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)
{
"checkpoint_path": "outputs/google_gemma_3_1b_it-agentbank-20250717_231738/checkpoint-57500",
"checkpoint_name": "checkpoint-57500",
"upload_timestamp": "2025-07-18T22:17:26.745422",
"framework": "transformers",
"training_framework": "AgentBank",
"model_type": "gemma3_text",
"architectures": [
"Gemma3ForCausalLM"
],
"vocab_size": 262144,
"hidden_size": 1152,
"num_hidden_layers": 26,
"torch_dtype": "bfloat16",
"transformers_version": "4.53.2",
"global_step": 57500,
"epoch": 0.3093745187040436,
"total_flos": 3.3421318490571264e+17,
"train_batch_size": 4,
"learning_rate": null,
"last_training_log": {
"epoch": 0.3093745187040436,
"grad_norm": 11.375,
"learning_rate": 4.9302202076188976e-05,
"loss": 2.41,
"step": 57500
},
"file_count": 12,
"total_size_bytes": 6035148749,
"total_size_gb": 5.62
}
이 모델은 LLM Training Recipes 프레임워크를 사용하여 학습되었습니다.