Instructions to use MANSTAGE/analysis-llm-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use MANSTAGE/analysis-llm-v2 with PEFT:
```
Task type is invalid.
```

How to use MANSTAGE/analysis-llm-v2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="MANSTAGE/analysis-llm-v2",
	filename="ggml-vocab-aquila.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use MANSTAGE/analysis-llm-v2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MANSTAGE/analysis-llm-v2
# Run inference directly in the terminal:
llama-cli -hf MANSTAGE/analysis-llm-v2

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf MANSTAGE/analysis-llm-v2
# Run inference directly in the terminal:
llama-cli -hf MANSTAGE/analysis-llm-v2

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 MANSTAGE/analysis-llm-v2
# Run inference directly in the terminal:
./llama-cli -hf MANSTAGE/analysis-llm-v2

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 MANSTAGE/analysis-llm-v2
# Run inference directly in the terminal:
./build/bin/llama-cli -hf MANSTAGE/analysis-llm-v2

Use Docker

docker model run hf.co/MANSTAGE/analysis-llm-v2

LM Studio
Jan

vLLM

How to use MANSTAGE/analysis-llm-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MANSTAGE/analysis-llm-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MANSTAGE/analysis-llm-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MANSTAGE/analysis-llm-v2

Ollama
How to use MANSTAGE/analysis-llm-v2 with Ollama:
```
ollama run hf.co/MANSTAGE/analysis-llm-v2
```

Unsloth Studio new

How to use MANSTAGE/analysis-llm-v2 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 MANSTAGE/analysis-llm-v2 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 MANSTAGE/analysis-llm-v2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for MANSTAGE/analysis-llm-v2 to start chatting

Docker Model Runner
How to use MANSTAGE/analysis-llm-v2 with Docker Model Runner:
```
docker model run hf.co/MANSTAGE/analysis-llm-v2
```

Lemonade

How to use MANSTAGE/analysis-llm-v2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull MANSTAGE/analysis-llm-v2

Run and chat with the model

lemonade run user.analysis-llm-v2-{{QUANT_TAG}}

List all available models

lemonade list

analysis-llm-v2

这是一个基于 DeepSeek-R1-Distill-Llama-8B 微调的前端需求分析模型。

模型描述

该模型专门用于生成前端技术分析文档，能够：

分析前端项目需求
生成详细的技术方案
提供页面路径规划
输出标准的前端项目结构

使用方法

使用HuggingFace格式

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

# 加载模型
model_name = "MANSTAGE/analysis-llm-v2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16,
    device_map="auto"
)

# 推理
question = "请帮我生成一个企业管理系统"
inputs = tokenizer(question, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=1000,
    temperature=0.7,
    do_sample=True
)

response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

使用GGUF格式

本仓库包含多种GGUF量化格式：

model_q4_0/ - 4位量化（最小文件大小）
model_q4_k_m/ - 4位量化（平衡版本）
model_q8_0/ - 8位量化（高质量）
model_f16/ - 16位浮点（最高质量）

使用llama.cpp加载GGUF文件：

# 下载GGUF文件
wget https://huggingface.co/MANSTAGE/analysis-llm-v2/resolve/main/model_q4_0/unsloth.Q4_0.gguf

# 使用llama.cpp运行
./main -m unsloth.Q4_0.gguf -p "请帮我生成一个企业管理系统"

训练详情

基础模型: unsloth/DeepSeek-R1-Distill-Llama-8B
训练数据: 219条前端需求分析数据
训练步数: 100步
学习率: 2e-4
LoRA配置: r=16, alpha=16, dropout=0.1
量化: 4-bit量化训练

文件说明

final_model/ - HuggingFace格式的完整模型
model_q4_0/ - 4位量化GGUF文件
model_q4_k_m/ - 4位量化GGUF文件（平衡版）
model_q8_0/ - 8位量化GGUF文件
model_f16/ - 16位浮点GGUF文件

许可证

Apache 2.0

Downloads last month: 72

Safetensors

Model size

8B params

Tensor type

F16

F32

Model tree for MANSTAGE/analysis-llm-v2

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Finetuned

unsloth/DeepSeek-R1-Distill-Llama-8B

Adapter

(4)

this model