Downloads · 30 days
0
pink-elephant-llm-14b-adapters
pinkelephantlimited/pink-elephant-llm-14b-adapters
pink-elephant-llm-14b-adapters is a machine learning model from pinkelephantlimited. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.
Intermediate and final LoRA adapters produced while training pink-elephant-llm-14b (the 14.8B parameter efficient LLM by Pink Elephant Limited, fine-tuned for code and mathematical reasoning).
Access
Public
Updated Aug 14, 2026
Repo size
9.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors13.7 GB · 100%
At a glance
- Library
- peft
- License
- mit
- Access
- Public
- Created
- Aug 7, 2026
- Updated
- Aug 14, 2026
- SHA
- 42ca572a
Model card
From the Hugging Face model README
Pink Elephant LLM 14B � LoRA Adapters
Intermediate and final LoRA adapters produced while training
pink-elephant-llm-14b
(the 14.8B parameter efficient LLM by Pink Elephant Limited, fine-tuned for code
and mathematical reasoning).
Each adapters/step-N/ folder holds a checkpoint of the parameter-efficient
adapters plus optional resume state. The final merged weights live in the
parent model repository.
Usage
Load with the peft library against the base model:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("<base model id>", torch_dtype="auto")
model = PeftModel.from_pretrained(base, "pinkelephantlimited/pink-elephant-llm-14b-adapters", subfolder="adapters/step-1000")
User Manual
Full family user manual: USER_MANUAL.pdf - what / which / where / how for every public artifact across the whole family, including how to load any step adapter and rebuild the loss curves.
About the company
Pink Elephant Limited is a commercial AI technology development company registered in Hong Kong.
- Library
- peft
- License
- mit
- Languages
- en
- Created
- Aug 7, 2026
- Updated
- Aug 14, 2026