Downloads · 30 days
13
22% of all-time downloads
gpt-oss-20b-li-founder-sft-adapter
complix-ai/gpt-oss-20b-li-founder-sft-adapter
gpt-oss-20b-li-founder-sft-adapter is a text generation model from complix-ai. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Fine-tuned from openai/gpt-oss-20b on Together AI.
All-time downloads
60
Public
Repo size
155 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors127 MB · 82%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- gpt_oss
- Access
- Public
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026
- SHA
- e1941d60
Try a prompt
Base models
Model card
From the Hugging Face model README
gpt-oss-20b LinkedIn founder-style (adapter)
Fine-tuned from openai/gpt-oss-20b on Together AI.
- Job:
ft-87f33f4a-0031 - Type: LoRA SFT (style: tech founder / builder LinkedIn writing)
- Checkpoint:
adapter
Usage
Merged weights
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "complix-ai/gpt-oss-20b-li-founder-sft-adapter"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
repo, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)
Adapter only
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("openai/gpt-oss-20b", torch_dtype="auto", device_map="auto", trust_remote_code=True)
model = PeftModel.from_pretrained(base, "complix-ai/gpt-oss-20b-li-founder-sft-adapter")
Training notes
- Conversational SFT with reasoning fields for gpt-oss
- ~1338 train / 163 val examples
- Anti-slop DPO planned as a follow-on stage
- Task
- Text Generation
- Library
- transformers
- Type
- gpt_oss
- License
- apache-2.0
- Created
- Aug 4, 2026
- Updated
- Aug 4, 2026