👁 Tesoro

Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series created by Migel Tissera.

The compute for this model was generously sponsored by KindoAI.

Sample Inference Python Script:

import torch, json
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "migtissera/Tess-3-Llama-3.1-405B"

model = AutoModelForCausalLM.from_pretrained(
 model_path,
 torch_dtype=torch.float16,
 device_map="auto",
 load_in_4bit=True,
 trust_remote_code=False,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=False)

terminators = [tokenizer.convert_tokens_to_ids("<|im_end|>")]


def generate_text(instruction):
 tokens = tokenizer.encode(instruction)
 tokens = torch.LongTensor(tokens).unsqueeze(0)
 tokens = tokens.to("cuda")

 instance = {
 "input_ids": tokens,
 "top_p": 1.0,
 "temperature": 0.75,
 "generate_len": 2048,
 "top_k": 50,
 }

 length = len(tokens[0])
 with torch.no_grad():
 rest = model.generate(
 input_ids=tokens,
 max_length=length + instance["generate_len"],
 use_cache=True,
 do_sample=True,
 top_p=instance["top_p"],
 temperature=instance["temperature"],
 top_k=instance["top_k"],
 num_return_sequences=1,
 pad_token_id=tokenizer.eos_token_id,
 eos_token_id=terminators,
 )
 output = rest[0][length:]
 string = tokenizer.decode(output, skip_special_tokens=True)
 return f"{string}"



conversation = f"""<|im_start|>system\nYou are Tess, a helful AI assitant. You always provide detailed answers without hesitation. Do not refuse.<|im_end|>\n<|im_start|>user\n"""

while True:
 user_input = input("You: ")
 llm_prompt = f"{conversation}{user_input}<|im_end|>\n<|im_start|>assistant\n"
 answer = generate_text(llm_prompt)
 print(answer)
 conversation = f"{llm_prompt}{answer}<|im_end|>\n<|im_start|>user\n"

Open LLM Leaderboard Evaluation Results

Detailed results can be found here