Instructions to use miqudev/miqu-1-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use miqudev/miqu-1-70b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="miqudev/miqu-1-70b", filename="miqu-1-70b.q2_K.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use miqudev/miqu-1-70b with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: llama cli -hf miqudev/miqu-1-70b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: llama cli -hf miqudev/miqu-1-70b:Q4_K_M
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf miqudev/miqu-1-70b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf miqudev/miqu-1-70b:Q4_K_M
Use Docker
docker model run hf.co/miqudev/miqu-1-70b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use miqudev/miqu-1-70b with Ollama:
ollama run hf.co/miqudev/miqu-1-70b:Q4_K_M
- Unsloth Studio
How to use miqudev/miqu-1-70b with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for miqudev/miqu-1-70b to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for miqudev/miqu-1-70b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for miqudev/miqu-1-70b to start chatting
- Atomic Chat new
- Docker Model Runner
How to use miqudev/miqu-1-70b with Docker Model Runner:
docker model run hf.co/miqudev/miqu-1-70b:Q4_K_M
- Lemonade
How to use miqudev/miqu-1-70b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull miqudev/miqu-1-70b:Q4_K_M
Run and chat with the model
lemonade run user.miqu-1-70b-Q4_K_M
List all available models
lemonade list
How to use miku model in spaces ?
#23
by Empereur-Pirate - opened
from fastapi import FastAPI, Request, Depends
from fastapi.responses import FileResponse, JSONResponse
from fastapi.staticfiles import StaticFiles
from transformers import pipeline
from pydantic import BaseModel
from typing import Optional, Any
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
# Helper function to read raw request bodies
async def parse_raw(request: Request):
return await request.body()
app = FastAPI()
# Serve the static files
app.mount("/static", StaticFiles(directory="static"), name="static")
pipe_flan = pipeline("text2text-generation", model="google/flan-t5-small")
def t5(input: str) -> dict[str, str]:
output = pipe_flan(input)
return {"output": output[0].get("generated_text", "")}
class ParseRaw(BaseModel):
raw: bytes
@app.post("/infer_t5")
async def infer_endpoint(data: ParseRaw = Depends(parse_raw)):
"""Receive input and generate text."""
try:
input_text = data.raw.decode("utf-8")
# Validate that the input is a string
assert isinstance(input_text, str), "Input must be a string."
if input_text is None:
return {"error": "No input text detected."}
result = t5(input_text)
return result
except AssertionError as e:
return JSONResponse({"error": f"Invalid Input Format: {e}"}, status_code=400)
@app.get("/infer_t5")
def get_default_inference_endpoint():
return {"message": "Use POST method to submit input data"}
# Load the MIKU model and tokenizer
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
try:
# Attempt to load the model and tokenizer regularly
model_config = AutoConfig.from_pretrained("miqudev/miqu-1-70b")
model = AutoModelForCausalLM.from_pretrained("miqudev/miqu-1-70b", config=model_config).to(device)
tokenizer = AutoTokenizer.from_pretrained("miqudev/miqu-1-70b")
except Exception as e:
print("[WARNING]: Failed to load model and tokenizer conventionally.")
print(f"Exception: {e}")
# Construct a dummy configuration object
model_config = AutoConfig.from_pretrained("miqudev/miqu-1-70b", trust_remote_code=True)
# Load the model using the constructed configuration
model = AutoModelForCausalLM.from_pretrained("miqudev/miqu-1-70b", config=model_config).to(device)
tokenizer = AutoTokenizer.from_pretrained("miqudev/miqu-1-70b")
def miuk_answer(query: str) -> str:
query_tokens = tokenizer.encode(query, return_tensors="pt")
query_tokens = query_tokens.to(device)
answer = model.generate(query_tokens, max_length=128, temperature=1, pad_token_id=tokenizer.pad_token_id)
return tokenizer.decode(answer[:, 0]).replace(" ", "")
@app.post("/infer_miku")
async def infer_endpoint(data: ParseRaw = Depends(parse_raw)):
"""Receive input and generate text."""
try:
input_text = data.raw.decode("utf-8")
# Validate that the input is a string
assert isinstance(input_text, str), "Input must be a string."
if input_text is None:
return {"error": "No input text detected."}
result = {"output": miuk_answer(input_text)}
return result
except AssertionError as e:
return JSONResponse({"error": f"Invalid Input Format: {e}"}, status_code=400)
@app.get("/infer_miku")
def get_default_inference_endpoint():
return {"message": "Use POST method to submit input data"}
Traceback (most recent call last):
File "/usr/local/bin/uvicorn", line 8, in <module>
sys.exit(main())
File "/usr/local/lib/python3.9/site-packages/click/core.py", line 1157, in __call__
return self.main(*args, **kwargs)
File "/usr/local/lib/python3.9/site-packages/click/core.py", line 1078, in main
rv = self.invoke(ctx)
File "/usr/local/lib/python3.9/site-packages/click/core.py", line 1434, in invoke
return ctx.invoke(self.callback, **ctx.params)
File "/usr/local/lib/python3.9/site-packages/click/core.py", line 783, in invoke
return __callback(*args, **kwargs)
File "/usr/local/lib/python3.9/site-packages/uvicorn/main.py", line 437, in main
run(app, **kwargs)
File "/usr/local/lib/python3.9/site-packages/uvicorn/main.py", line 463, in run
server.run()
File "/usr/local/lib/python3.9/site-packages/uvicorn/server.py", line 60, in run
return asyncio.run(self.serve(sockets=sockets))
File "/usr/local/lib/python3.9/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "uvloop/loop.pyx", line 1517, in uvloop.loop.Loop.run_until_complete
File "/usr/local/lib/python3.9/site-packages/uvicorn/server.py", line 67, in serve
config.load()
File "/usr/local/lib/python3.9/site-packages/uvicorn/config.py", line 458, in load
self.loaded_app = import_from_string(self.app)
File "/usr/local/lib/python3.9/site-packages/uvicorn/importer.py", line 21, in import_from_string
module = importlib.import_module(module_str)
File "/usr/local/lib/python3.9/importlib/__init__.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "<frozen importlib._bootstrap>", line 1030, in _gcd_import
File "<frozen importlib._bootstrap>", line 1007, in _find_and_load
File "<frozen importlib._bootstrap>", line 986, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 680, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 850, in exec_module
File "<frozen importlib._bootstrap>", line 228, in _call_with_frames_removed
File "/home/user/app/./main.py", line 63, in <module>
model_config = AutoConfig.from_pretrained("miqudev/miqu-1-70b", trust_remote_code=True)
File "/usr/local/lib/python3.9/site-packages/transformers/models/auto/configuration_auto.py", line 1100, in from_pretrained
config_dict, unused_kwargs = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/usr/local/lib/python3.9/site-packages/transformers/configuration_utils.py", line 634, in get_config_dict
config_dict, kwargs = cls._get_config_dict(pretrained_model_name_or_path, **kwargs)
File "/usr/local/lib/python3.9/site-packages/transformers/configuration_utils.py", line 689, in _get_config_dict
resolved_config_file = cached_file(
File "/usr/local/lib/python3.9/site-packages/transformers/utils/hub.py", line 436, in cached_file
raise EnvironmentError(
OSError: miqudev/miqu-1-70b does not appear to have a file named config.json. Checkout 'https://huggingface.co/miqudev/miqu-1-70b/main' for available files.
You should use ctransformers for quantised models . Or use dequantised versions of miqu-1-70b. There are few on HF such as 152334H/miqu-1-70b-sf
thanks for the reply, it actually helped me very much. I now have an issue installing the library sentencepiece : https://huggingface.co/152334H/miqu-1-70b-sf/discussions/20