My Experimental Model
Collection
2 items
•
Updated
This is a mix between teknium/OpenHermes-2.5-Mistral-7B and Intel/neural-chat-7b-v3-3. Using mistralai/Mistral-7B-v0.1 as the base model.
This Mixture of Expert was done using mergekit
method.
import torch
from transformers import pipeline
pipe = pipeline("text-generation", model="ibndias/NeuralHermes-MoE-2x7B",torch_dtype=torch.bfloat16, device_map="auto")
prompt = """<|system|> You are a helpful assistant.
<|user|>
Write me bash script to scan ip 192.3.1.4 with nmap only port that ends with 9 from 1-100.
<|assistant|>
"""
outputs = pipe(prompt, max_new_tokens=512, do_sample=True, temperature=0.2, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])
Output:
<|system|> You are a helpful assistant. <|user|> Write me bash script to scan ip 192.3.1.4 with nmap only port that ends with 9 from 1-100. <|assistant|> Sure, here's a bash script that scans the specified IP address with nmap for open ports that end with 9 from 1 to 100:
#!/bin/bash IP_ADDRESS="192.3.1.4" START_PORT=1 END_PORT=100 for ((i=$START_PORT; i<=$END_PORT; i++)); do PORT=$i if [[ $PORT % 10 == 9 ]]; then nmap -p $PORT $IP_ADDRESS fi done
Save the script with a.sh extension (e.g., scan_ports.sh) and make it executable by running
chmod +x scan_ports.sh
. Then, run the script by executing./scan_ports.sh
. ...
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 64.08 |
AI2 Reasoning Challenge (25-Shot) | 62.12 |
HellaSwag (10-Shot) | 84.21 |
MMLU (5-Shot) | 64.56 |
TruthfulQA (0-shot) | 43.61 |
Winogrande (5-shot) | 78.14 |
GSM8k (5-shot) | 51.86 |