Instructions to use AnhLee0/Lab22 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AnhLee0/Lab22 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AnhLee0/Lab22",
	filename="adapters/merged-fp16_gguf/merged-fp16.Q4_K_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AnhLee0/Lab22 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AnhLee0/Lab22:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AnhLee0/Lab22:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AnhLee0/Lab22:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf AnhLee0/Lab22: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 AnhLee0/Lab22:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf AnhLee0/Lab22: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 AnhLee0/Lab22:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AnhLee0/Lab22:Q4_K_M

Use Docker

docker model run hf.co/AnhLee0/Lab22:Q4_K_M

LM Studio
Jan
Ollama
How to use AnhLee0/Lab22 with Ollama:
```
ollama run hf.co/AnhLee0/Lab22:Q4_K_M
```

Unsloth Studio new

How to use AnhLee0/Lab22 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 AnhLee0/Lab22 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 AnhLee0/Lab22 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AnhLee0/Lab22 to start chatting

Docker Model Runner
How to use AnhLee0/Lab22 with Docker Model Runner:
```
docker model run hf.co/AnhLee0/Lab22:Q4_K_M
```

Lemonade

How to use AnhLee0/Lab22 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AnhLee0/Lab22:Q4_K_M

Run and chat with the model

lemonade run user.Lab22-Q4_K_M

List all available models

lemonade list

Lab22 / data /eval /benchmark_results.json

AnhLee0

Cập nhật toàn bộ kết quả Lab 22 (SFT, DPO, GGUF)

7ab1d88 verified 18 days ago

raw

history blame contribute delete

443 Bytes

Invalid JSON:Unexpected token 'N', ..." "sft": NaN, "... is not valid JSON

	{
	"compute_tier": "T4",
	"limits": {
	"ifeval": 540,
	"gsm8k": 500,
	"mmlu": 500,
	"alpaca_lite": 100
	},
	"metrics": {
	"IFEval": {
	"sft": NaN,
	"dpo": NaN
	},
	"GSM8K": {
	"sft": NaN,
	"dpo": NaN
	},
	"MMLU": {
	"sft": NaN,
	"dpo": NaN
	},
	"AlpacaEval-lite": {
	"sft": 0.5,
	"dpo": 0.555
	}
	},
	"deltas": {
	"AlpacaEval-lite": 0.05500000000000005
	}
	}