lucyknada/prince-canuma_Ministral-8B-Instruct-2410-HF-exl2

exl2 quant (measurement.json in main branch)

---

check revisions for quants

---

Ministral-8B-Instruct-2410-HF

Model Description

Ministral-8B-Instruct-2410-HF is the Hugging Face version of Ministral-8B-Instruct-2410 by Mistral AI. It is a multilingual instruction-tuned language model based on the Mistral architecture, designed for various natural language processing tasks with a focus on chat-based interactions.

Installation

To use this model, install the required packages:

pip install -U transformers

Usage Example

Here's a Python script demonstrating how to use the model for chat completion:

from transformers import AutoModelForCausalLM, AutoTokenizer

# Model setup
model_name = "prince-canuma/Ministral-8B-Instruct-2410-HF"
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Chat interaction
prompt = "Tell me a short story about a robot learning to paint."
messages = [{"role": "user", "content": prompt}]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
input_ids = tokenizer(text, return_tensors="pt").to(model.device)

# Generate response
output = model.generate(**input_ids, max_new_tokens=500, temperature=0.7, do_sample=True)
response = tokenizer.decode(output[0][input_ids.input_ids.shape[1]:])

print("User:", prompt)
print("Model:", response)

Model Details

• Developed by: Mistral AI
• Model type: Causal Language Model
• Language(s): English
• License: mrl
• Resources for more information:
  • Model Repository
  • Mistral AI GitHub