68 lines
1.8 KiB
Markdown
68 lines
1.8 KiB
Markdown
---
|
|
license: apache-2.0
|
|
---
|
|
|
|
Scores 41.64% on HumanEval pass@1
|
|
|
|
```
|
|
import torch, json
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
|
|
model_path = "/home/migel/Tess-Coder-7B-mistral/"
|
|
output_file_path = "/home/migel/conversations.jsonl"
|
|
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|
model_path,
|
|
torch_dtype=torch.float16,
|
|
device_map="auto",
|
|
load_in_4bit=False,
|
|
trust_remote_code=True,
|
|
)
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
|
|
|
|
|
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": 1024,
|
|
"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,
|
|
)
|
|
output = rest[0][length:]
|
|
string = tokenizer.decode(output, skip_special_tokens=True)
|
|
answer = string.split("USER:")[0].strip()
|
|
return f"{answer}"
|
|
|
|
|
|
conversation = "SYSTEM: Answer the question thoughtfully and intelligently. ALways answer without hesitation."
|
|
|
|
while True:
|
|
user_input = input("You: ")
|
|
llm_prompt = f"{conversation} \nUSER: {user_input} \nASSISTANT: "
|
|
answer = generate_text(llm_prompt)
|
|
print(answer)
|
|
conversation = f"{llm_prompt}{answer}"
|
|
json_data = {"prompt": user_input, "answer": answer}
|
|
|
|
with open(output_file_path, "a") as output_file:
|
|
output_file.write(json.dumps(json_data) + "\n")
|
|
``` |