mirror of
https://github.com/hanzo-apps/hanzo.ai.git
synced 2026-10-29 07:20:43 +00:00
zooqueenandHanzo Dev
ec7a79fdc6
lib/data/zen.json is @zenlm/models read through lib/upstream at prebuild (scripts/zen.mjs); no page or client chunk imports the package. The Flash command finds its files by quantization, so no loader name ships. Co-authored-by: Hanzo Dev <[email protected]>
51 lines
1.6 KiB
TypeScript
51 lines
1.6 KiB
TypeScript
/**
|
|
* The commands the current weight cards print. The local command finds the
|
|
* Flash files by their quantization, so it runs against the repository as
|
|
* published and names nothing but Zen.
|
|
*/
|
|
|
|
export const CURL = `curl https://api.hanzo.ai/v1/chat/completions \\
|
|
-H "Authorization: Bearer $HANZO_API_KEY" \\
|
|
-H "Content-Type: application/json" \\
|
|
-d '{"model": "zen6", "messages": [{"role": "user", "content": "Hello"}]}'`
|
|
|
|
/** The official OpenAI SDK pointed at the gateway — the shape /sdks publishes. */
|
|
export const PYTHON = `from openai import OpenAI
|
|
|
|
client = OpenAI(
|
|
base_url="https://api.hanzo.ai/v1",
|
|
api_key="hk-...", # your Hanzo API key
|
|
)
|
|
|
|
resp = client.chat.completions.create(
|
|
model="zen6",
|
|
messages=[{"role": "user", "content": "Hello"}],
|
|
)
|
|
print(resp.choices[0].message.content)`
|
|
|
|
export const DOWNLOAD_ZEN = 'hf download zenlm/zen6'
|
|
export const DOWNLOAD_FLASH = 'hf download zenlm/zen6-flash'
|
|
|
|
export const SGLANG = `hf download zenlm/zen6 --local-dir zen6
|
|
|
|
python3 -m sglang.launch_server \\
|
|
--model-path ./zen6 \\
|
|
--speculative-draft-model-path ./zen6/dflash2 \\
|
|
--speculative-num-steps 3 \\
|
|
--speculative-algorithm DFLASH \\
|
|
--kv-cache-dtype fp8_e5m2 \\
|
|
--context-length 1048576 \\
|
|
--port 30000 \\
|
|
--host 0.0.0.0`
|
|
|
|
/** Zen 6 Flash on llama.cpp: the weights, the vision projector and the drafter, each the one file of its kind. */
|
|
export const LLAMA = `hf download zenlm/zen6-flash --local-dir zen6-flash
|
|
|
|
llama-server \\
|
|
-m zen6-flash/*-PQ2_0.gguf \\
|
|
--mmproj zen6-flash/*-mmproj-Q8_0.gguf \\
|
|
-md zen6-flash/*-DFlash2-Q8_0.gguf \\
|
|
--spec-draft-n-max 3 \\
|
|
-c 32768 \\
|
|
--port 8080`
|