mirror of
https://github.com/hanzoai/engine.git
synced 2026-11-20 14:17:52 +00:00
Replace all remaining references to the upstream project/author/framework brands with hanzo / hanzoai across source, comments, docs, examples, and build scripts. - Project spellings mistral.rs / mistral-rs / mistralrs -> hanzo (and the hanzo-* crate/binary names in Dockerfiles, Makefile, install.ps1, .gitignore). - Author EricLBuehler / EricBuehler / EricB / Eric Buehler -> hanzoai / Hanzo AI (incl. Cargo `authors` and LICENSE copyright). - URLs: github.com/EricLBuehler/mistral.rs -> github.com/hanzoai/engine; ericlbuehler.github.io/mistral.rs -> hanzoai.github.io/engine; github.com/huggingface/candle -> github.com/hanzoai/ml; docs.rs/candle-* -> docs.rs/hanzo-ml; ghcr.io image -> ghcr.io/hanzoai/engine. - Env var prefix MISTRALRS_ -> HANZO_ (producers and consumers kept in sync, incl. the build-script-injected HANZO_GIT_REVISION). - ROCm static lib libmistralrsrocm.a / mistralrsrocm -> libhanzorocm.a / hanzorocm. - localStorage keys mistralrs_settings -> hanzo_settings. Deliberately preserved: real model architectures (struct Mistral, models/mistral.rs file, Mixtral/Llama/Gemma/Qwen/Phi), real model-org HF repo-ids (mistralai/, meta-llama/, google/, Qwen/, microsoft/), the `use hanzo_ml as candle` code aliases and `candle::` identifiers, and the upstream-author HF data repo-id suffix in "hanzoai/mistralrs_tests". Both `cargo check` and `cargo check --features vulkan` pass with 0 errors. Co-authored-by: Hanzo Dev <[email protected]>
7.8 KiB
7.8 KiB
In [ ]:
# First, install Rust: https://rustup.rs/
%pip install hanzo-cuda -vIn [ ]:
from hanzo import Runner, Which, ChatCompletionRequest
runner = Runner(
which=Which.GGUF(
tok_model_id="mistralai/Mistral-7B-Instruct-v0.1",
quantized_model_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
quantized_filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
)
)
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="mistral",
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)In [ ]:
from hanzo import Runner, Which, ChatCompletionRequest, Architecture
runner = Runner(
which=Which.Plain(
model_id="mistralai/Mistral-7B-Instruct-v0.1",
arch=Architecture.Mistral,
)
)
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="mistral",
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)In [ ]:
from hanzo import Runner, Which
runner = Runner(
which=Which.GGUF(
tok_model_id="mistralai/Mistral-7B-Instruct-v0.1",
quantized_model_id="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
quantized_filename="mistral-7b-instruct-v0.1.Q4_K_M.gguf",
)
)In [ ]:
from hanzo import Runner, Which, Architecture
runner = Runner(
which=Which.Plain(
tok_model_id="mistralai/Mistral-7B-Instruct-v0.1",
arch=Architecture.Mistral,
)
)In [ ]:
from hanzo import Runner, Which
runner = Runner(
which=Which.XLoraGGUF(
tok_model_id=None, # Automatically determine from ordering file
quantized_model_id="TheBloke/zephyr-7B-beta-GGUF",
quantized_filename="zephyr-7b-beta.Q4_0.gguf",
xlora_model_id="lamm-mit/x-lora",
order="orderings/xlora-paper-ordering.json",
tgt_non_granular_index=None,
)
)In [ ]:
from hanzo import ChatCompletionRequest
res = runner.send_chat_completion_request(
ChatCompletionRequest(
model="mistral",
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)