Downloads · 30 days
9
22% of all-time downloads
mineral-1b
Mineral-Dev/mineral-1b
mineral-1b is a machine learning model from Mineral-Dev. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Mineral-1B is a lightweight open language model under the Apache License 2.0, built using Hugging Face AutoTrain for smart and automatic model management. The project aims to create a flexible LLM capable of natural c…
All-time downloads
41
Public
Parameters
1.6B
6.3 GB on disk
Likes
5
Public
Repo makeup
Click a slice to open those files.
.safetensors6.3 GB · 100%
At a glance
- Model type
- mineral
- Access
- Public
- Created
- Oct 22, 2025
- Updated
- Oct 23, 2025
- SHA
- edd4ead2
Model card
From the Hugging Face model README
🧠 Mineral-1B
Mineral-1B is a lightweight open language model under the Apache License 2.0, built using Hugging Face AutoTrain for smart and automatic model management.
The project aims to create a flexible LLM capable of natural conversation, reasoning, and code assistance.
⚙️ Configuration
- Base model:
microsoft/phi-2 - Pipeline:
text-generation - Library:
transformers - License: Apache 2.0
- Training: AutoTrain (no dataset yet — pretrained mode)
🚀 Goals
- Serve as a foundation for text generation and conversational tasks
- Support English and optionally other languages
- Enable later fine-tuning with domain-specific data
📘 Usage
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("prelington/Mineral-1B")
model = AutoModelForCausalLM.from_pretrained("prelington/Mineral-1B")
prompt = "Hello! What is Mineral-1B?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
- Type
- mineral
- Created
- Oct 22, 2025
- Updated
- Oct 23, 2025