| CSGO Coach Mia, Finetuned on mistralai/Mistral-7B-Instruct-v0.2 | |
| Sample usage : | |
| from huggingface_hub import hf_hub_download | |
| from llama_cpp import Llama | |
| import torch | |
| # Specify the path to your .gguf file | |
| model_path = '/content/finetuned8b/finetuned8b.Q5_K_M.gguf' | |
| # Instantiate the Llama model | |
| llm = Llama(model_path=model_path) | |
| prompt = "Coach Mia, help me with aiming " | |
| ## Generation kwargs | |
| generation_kwargs = { | |
| "max_tokens":200, | |
| "stop":'[INST]', | |
| "echo":False, # Echo the prompt in the output | |
| "top_k":1 # This is essentially greedy decoding, since the model will always return the highest-probability token. Set this value > 1 for sampling decoding | |
| } | |
| res = llm(prompt, **generation_kwargs) | |
| ## Unpack and the generated text from the LLM response dictionary and print it | |
| print(res["choices"][0]["text"]) | |
| # res is short for result | |
| #output | |
| 100% accuracy. [/INST] Aiming is a crucial aspect of CS:GO. Let's start by analyzing your sensitivity settings and crosshair placement. We can also run some aim training drills to improve your precision. | |