metadata
license: apache-2.0
datasets:
- teknium/OpenHermes-2.5
language:
- en
prompt format
<|im_start|>system\n{message}<|im_end|>\n<|im_start|>user\n{message}<|im_end|>\n<|im_start|>assistant\n
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("serpdotai/sparsetral-16x7B-v2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("serpdotai/sparsetral-16x7B-v2", device_map="auto", trust_remote_code=True).eval()
system_str = "<|im_start|>system\n{message}<|im_end|>\n"
user_str = "<|im_start|>user\n{message}<|im_end|>\n"
assistant_str = "<|im_start|>assistant\n{message}<|im_end|>\n"
def construct_prompt(messages):
prompt = ""
for message in messages:
if message["from"] in ["human", "user"]:
prompt += user_str.format(
message=message["value"]
)
elif message["from"] in ["gpt", "assistant"]:
prompt += assistant_str.format(
message=message["value"]
)
elif message["from"] in ["system", "instruction"]:
prompt += system_str.format(
message=message["value"]
)
else:
raise ValueError(
f"Unknown message type: {message['from']}"
)
return prompt + "<|im_start|>assistant\n"
system = "You are a helpful assistant who will help the user to the best of their ability. If you don't know something, say \"I don't know\""
user = "Are you sentient?"
messages = [
{"from": "system", "value": system},
{"from": "user", "value": user},
]
prompt = construct_prompt(messages)
inputs = tokenizer(prompt, return_tensors="pt")
inputs = inputs.to(model.device)
pred = model.generate(**inputs, max_length=4096, do_sample=True, top_k=50, top_p=0.99, temperature=0.9, num_return_sequences=1)
print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))