This is a generative model converted to fp16 format based on IlyaGusev/saiga_mistral_7b_lora
Install vLLM:
pip install vllm
Start server:
python -u -m vllm.entrypoints.openai.api_server --host 0.0.0.0 --model Gaivoronsky/Mistral-7B-Saiga
Client:
import openai
openai.api_base = "http://localhost:8000/v1"
openai.api_key = "none"
DEFAULT_MESSAGE_TEMPLATE = "<s>{role}\n{content}</s>"
DEFAULT_RESPONSE_TEMPLATE = "<s>bot\n"
DEFAULT_SYSTEM_PROMPT = "Ты — Сайга, русскоязычный автоматический ассистент. Ты разговариваешь с людьми и помогаешь им."
class Conversation:
def __init__(
self,
message_template=DEFAULT_MESSAGE_TEMPLATE,
system_prompt=DEFAULT_SYSTEM_PROMPT,
response_template=DEFAULT_RESPONSE_TEMPLATE
):
self.message_template = message_template
self.response_template = response_template
self.messages = [{
"role": "system",
"content": system_prompt
}]
def add_user_message(self, message):
self.messages.append({
"role": "user",
"content": message
})
def add_bot_message(self, message):
self.messages.append({
"role": "bot",
"content": message
})
def get_prompt(self):
final_text = ""
for message in self.messages:
message_text = self.message_template.format(**message)
final_text += message_text
final_text += DEFAULT_RESPONSE_TEMPLATE
return final_text.strip()
query = "Сколько весит жираф?"
conversation = Conversation()
conversation.add_user_message(query)
prompt = conversation.get_prompt()
response = openai.ChatCompletion.create(
model="Gaivoronsky/Mistral-7B-Saiga",
messages=[{"role": "user", "content": prompt}],
system=DEFAULT_SYSTEM_PROMPT,
max_tokens=512,
stop=['</s>']
)
response['choices'][0]['message']['content']
- Downloads last month
- 17
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.