Instructions to use lastmass/llama3.2-chinese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lastmass/llama3.2-chinese with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="lastmass/llama3.2-chinese",
	filename="unsloth.BF16.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 lastmass/llama3.2-chinese with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lastmass/llama3.2-chinese:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lastmass/llama3.2-chinese:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf lastmass/llama3.2-chinese:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf lastmass/llama3.2-chinese: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 lastmass/llama3.2-chinese:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf lastmass/llama3.2-chinese: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 lastmass/llama3.2-chinese:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf lastmass/llama3.2-chinese:Q4_K_M

Use Docker

docker model run hf.co/lastmass/llama3.2-chinese:Q4_K_M

LM Studio
Jan
Ollama
How to use lastmass/llama3.2-chinese with Ollama:
```
ollama run hf.co/lastmass/llama3.2-chinese:Q4_K_M
```

Unsloth Studio

How to use lastmass/llama3.2-chinese 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 lastmass/llama3.2-chinese 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 lastmass/llama3.2-chinese to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for lastmass/llama3.2-chinese to start chatting

Docker Model Runner
How to use lastmass/llama3.2-chinese with Docker Model Runner:
```
docker model run hf.co/lastmass/llama3.2-chinese:Q4_K_M
```

Lemonade

How to use lastmass/llama3.2-chinese with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull lastmass/llama3.2-chinese:Q4_K_M

Run and chat with the model

lemonade run user.llama3.2-chinese-Q4_K_M

List all available models

lemonade list

llama3.2-chinese / Modelfile

lastmass

Update Modelfile

82bc66b verified over 1 year ago

raw

history blame contribute delete

1.31 kB

	FROM /home/featurize/work/lastmass/llama3.2-chinese/unsloth.Q4_K_M.gguf


	TEMPLATE """以下是描述一项任务的指令。请输出合适的内容回应指令。
	### Input:
	大象和猎豹的奔跑速度谁更快，简单说明原因.

	### Response:
	猎豹的奔跑速度比大象快得多。

	猎豹：是世界上奔跑速度最快的陆地动物之一，短距离内可以达到约 100-120 公里/小时（约 60-75 英里/小时）。
	大象：虽然大象体型巨大，但它们的速度较慢，奔跑速度最高约为 40 公里/小时（约 25 英里/小时）。
	因此，猎豹在速度上远远超过了大象。

	### Input:
	鱼为什么能在水里呼吸。

	### Response:
	鱼能够在水中呼吸，主要是因为它们有一种特殊的呼吸器官——鳃。鳃能够从水中提取氧气，并排出二氧化碳，这个过程使鱼能够在水中生存。
	{{ if .Prompt }}

	### 指令：
	{{ .Prompt }}

	{{ end }}### 回应：
	{{ .Response }}<\|end_of_text\|>"""

	PARAMETER stop "<\|eot_id\|>"
	PARAMETER stop "<\|end_header_id\|>"
	PARAMETER stop "<\|finetune_right_pad_id\|>"
	PARAMETER stop "<\|eom_id\|>"
	PARAMETER stop "<\|python_tag\|>"
	PARAMETER stop "<\|start_header_id\|>"
	PARAMETER stop "<\|end_of_text\|>"
	PARAMETER stop "<\|reserved_special_token_"
	PARAMETER temperature 1.5
	PARAMETER min_p 0.1