mirror of
https://github.com/zenlm/engine.git
synced 2026-10-30 15:00:05 +00:00
Eric BuehlerandGitHub
ebf1c27adc
* Nice, easy rust API * Nicer example * Docs * Update docs * Support lora rust api model * Reorganize * Add the examples * Update tool calling example * Fix crate name * Add messages_ref * Add llama 8b specific example * Add gguf, lora/xlora models * Export them * Doctests build * Add support for vision models * Add some docs * Even *more* docs * Format
41 lines
1.2 KiB
Rust
41 lines
1.2 KiB
Rust
use anyhow::Result;
|
|
use mistralrs::{
|
|
IsqType, MemoryGpuConfig, PagedAttentionMetaBuilder, TextMessageRole, TextMessages,
|
|
TextModelBuilder,
|
|
};
|
|
|
|
#[tokio::main]
|
|
async fn main() -> Result<()> {
|
|
let model = TextModelBuilder::new("microsoft/Phi-3.5-mini-instruct")
|
|
.with_isq(IsqType::Q8_0)
|
|
.with_logging()
|
|
.with_paged_attn(|| {
|
|
PagedAttentionMetaBuilder::default()
|
|
.with_block_size(32)
|
|
.with_gpu_memory(MemoryGpuConfig::ContextSize(1024))
|
|
.build()
|
|
})?
|
|
.build()
|
|
.await?;
|
|
|
|
let messages = TextMessages::new()
|
|
.add_message(
|
|
TextMessageRole::System,
|
|
"You are an AI agent with a specialty in programming.",
|
|
)
|
|
.add_message(
|
|
TextMessageRole::User,
|
|
"Hello! How are you? Please write generic binary search function in Rust.",
|
|
);
|
|
|
|
let response = model.send_chat_request(messages).await?;
|
|
|
|
println!("{}", response.choices[0].message.content.as_ref().unwrap());
|
|
dbg!(
|
|
response.usage.avg_prompt_tok_per_sec,
|
|
response.usage.avg_compl_tok_per_sec
|
|
);
|
|
|
|
Ok(())
|
|
}
|