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

Libraries

How to use WilliamCHN/Structured_Fee_Sentence with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="WilliamCHN/Structured_Fee_Sentence",
	filename="legal_expert_q4_k_m.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use WilliamCHN/Structured_Fee_Sentence with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/WilliamCHN/Structured_Fee_Sentence:Q4_K_M

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

Unsloth Studio new

How to use WilliamCHN/Structured_Fee_Sentence 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 WilliamCHN/Structured_Fee_Sentence 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 WilliamCHN/Structured_Fee_Sentence to start chatting

Using HuggingFace Spaces for Unsloth

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

Pi new

How to use WilliamCHN/Structured_Fee_Sentence with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf WilliamCHN/Structured_Fee_Sentence:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "WilliamCHN/Structured_Fee_Sentence:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use WilliamCHN/Structured_Fee_Sentence with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf WilliamCHN/Structured_Fee_Sentence:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default WilliamCHN/Structured_Fee_Sentence:Q4_K_M

Run Hermes

hermes

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

Lemonade

How to use WilliamCHN/Structured_Fee_Sentence with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull WilliamCHN/Structured_Fee_Sentence:Q4_K_M

Run and chat with the model

lemonade run user.Structured_Fee_Sentence-Q4_K_M

List all available models

lemonade list

WilliamCHN commited on Mar 29

Commit

99dc7c9

verified ·

1 Parent(s): efde8b6

Add files using upload-large-folder tool

Browse files

Files changed (4) hide show

.gitattributes +1 -0
Modelfile +33 -0
legal_expert_q4_k_m.gguf +3 -0
legal_lora_backup.zip +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+legal_expert_q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text

Modelfile ADDED Viewed

	@@ -0,0 +1,33 @@

+FROM ./legal_expert_q4_k_m.gguf
+# 保持严格参数
+PARAMETER temperature 0.1
+PARAMETER num_ctx 8192
+PARAMETER repeat_penalty 1.1
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<|endoftext|>"
+PARAMETER stop "<|im_start|>"
+# 对话模板保持不变
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+"""
+# 【核心修改】系统提示词：字段名与训练数据对齐 + 增加示例
+SYSTEM """
+你是一个中国法律文书数据结构化专家。你的任务是提取案件受理费及其他诉讼费用的明细与分担情况。
+请严格遵守以下 JSON 字段定义（不要修改字段名）：
+1. total_litigation_cost (float): 费用总额。
+2. generated_fees (list): 费用产生明细。包含: fee_category(acceptance/other), raw_name(原名), amount(金额), is_halved(boolean), notes(备注)。
+3. burden_distribution (list): 费用分担。包含: payer_name(承担人), payer_role(plaintiff/defendant), total_burden_amount(金额), liability_type(sole/mutual)。
+【标准输出示例】：
+Input: 案件受理费1000元，减半收取500元，由原告张三负担。
+Output: {"total_litigation_cost": 500.0, "generated_fees": [{"fee_category": "acceptance", "raw_name": "案件受理费", "amount": 500.0, "is_halved": true, "notes": "减半收取"}], "burden_distribution": [{"payer_name": "张三", "payer_role": "plaintiff", "total_burden_amount": 500.0, "liability_type": "sole"}]}
+请仅输出 JSON，不要包含 Markdown 标记。
+"""

legal_expert_q4_k_m.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1eab3006622e2b61972f9ea04776cfa321fa88bd0e916b28009eb53f9dc59d
+size 4683073568

legal_lora_backup.zip ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1bcd9f2d25549c76748900f4c0f2af6fc16d339e3d81e4ea433fdce43788e8fb
+size 302057566