mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
2.8 KiB
2.8 KiB
DeepSeek V3: deepseek-ai/DeepSeek-V3, deepseek-ai/DeepSeek-R1
The DeepSeek V3 is a mixture of expert (MoE) model.
Quick Start
hanzo run --isq 4 -m deepseek-ai/DeepSeek-R1
Note: The non-distill versions of the DeepSeek R1 models share the DeepSeek V3 architecture.
Note: This model supports MoQE which can be activated in the ISQ organization parameter within the various APIs, as demonstrated below:
hanzo run --isq 4 -m deepseek-ai/DeepSeek-R1 --isq-organization moqe
Running the distill models
The various distillation models can be run out of the box.
hanzo run --isq 4 -m deepseek-ai/DeepSeek-R1-Distill-Llama-8B
hanzo run --isq 4 -m deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
hanzo run --isq 4 -m deepseek-ai/DeepSeek-R1-Distill-Qwen-32B
HTTP API
hanzo serve --isq 4 -p 1234 -m deepseek-ai/DeepSeek-R1
from openai import OpenAI
client = OpenAI(api_key="foobar", base_url="http://localhost:1234/v1/")
completion = client.chat.completions.create(
model="default",
messages=[
{"role": "user", "content": "Tell me a story about the Rust type system."}
],
max_tokens=256,
)
print(completion.choices[0].message.content)
Python SDK
from hanzo import Runner, Which, ChatCompletionRequest, Architecture
runner = Runner(
which=Which.Plain(
model_id="deepseek-ai/DeepSeek-R1",
arch=Architecture.DeepseekV3,
),
)
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="default",
messages=[
{"role": "user", "content": "Tell me a story about the Rust type system."}
],
max_tokens=256,
presence_penalty=1.0,
top_p=0.1,
temperature=0.1,
)
)
print(res.choices[0].message.content)
print(res.usage)
Rust SDK
You can find this example here.
use anyhow::Result;
use hanzo::{
IsqType, PagedAttentionMetaBuilder, TextMessageRole, TextMessages, TextModelBuilder,
};
#[tokio::main]
async fn main() -> Result<()> {
let model = TextModelBuilder::new("deepseek-ai/DeepSeek-R1")
.with_isq(IsqType::Q4K)
.with_logging()
.with_paged_attn(|| PagedAttentionMetaBuilder::default().build())?
.build()
.await?;
let messages = TextMessages::new()
.add_message(TextMessageRole::User, "Hello!");
let response = model.send_chat_request(messages).await?;
println!("{}", response.choices[0].message.content.as_ref().unwrap());
Ok(())
}