Downloads · 30 days
9
15% of all-time downloads
alirezaaminzadeh/soc-agent-traces-smollm3-3b
soc-agent-traces-smollm3-3b is a text generation model from alirezaaminzadeh. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
QLoRA fine-tune of SmolLM3-3B on SOC-Agent-Traces-10K, turning the base model into a SOC investigation agent that reasons step by step, calls nine read-only investigation tools in <toolcall format, and
Downloads · 30 days
9
15% of all-time downloads
All-time downloads
59
Public
Repo size
743 MB
Likes
0
Public
Click a slice to open those files.
.safetensors121 MB · 88%
From the Hugging Face model README
QLoRA fine-tune of SmolLM3-3B
on SOC-Agent-Traces-10K,
turning the base model into a SOC investigation agent that reasons step by
step, calls nine read-only investigation tools in <tool_call> format, and
closes with a structured JSON triage report.
alert → reasoning + <tool_call> → tool result → … → fenced JSON triage report
Trained with assistant-only loss on successful traces (success=true): tool
results and prompts are masked — only analyst reasoning, tool calls, and the
final report contribute to the gradient.
| Metric | Value |
|---|---|
| JSON parse rate | 0.617 |
| Verdict accuracy | 0.617 |
| Decision accuracy | 0.617 |
| Technique F1 | 1.0 |
Trained steps: 120 · eval samples: 60
import torch
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained(
"HuggingFaceTB/SmolLM3-3B", torch_dtype=torch.bfloat16, device_map="cuda")
model = PeftModel.from_pretrained(base, "alirezaaminzadeh/soc-agent-traces-smollm3-3b")
tokenizer = AutoTokenizer.from_pretrained("alirezaaminzadeh/soc-agent-traces-smollm3-3b")
prompt = tokenizer.apply_chat_template(messages, tokenize=False,
add_generation_prompt=True,
enable_thinking=False)
Parse <tool_call>...</tool_call> blocks from the generation, execute your
(read-only) tools, feed results back as role="tool" messages, and iterate
until the model emits the fenced JSON triage report. The companion demo Space
alirezaaminzadeh/soc-agent-traces
implements the full loop with smolagents.
Apache 2.0