Instructions to use JoeiBanana/ai-network-llms with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use JoeiBanana/ai-network-llms with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use JoeiBanana/ai-network-llms 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 JoeiBanana/ai-network-llms:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf JoeiBanana/ai-network-llms:Q4_K_M

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/JoeiBanana/ai-network-llms:Q4_K_M

LM Studio
Jan

vLLM

How to use JoeiBanana/ai-network-llms with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/JoeiBanana/ai-network-llms:Q4_K_M

Ollama
How to use JoeiBanana/ai-network-llms with Ollama:
```
ollama run hf.co/JoeiBanana/ai-network-llms:Q4_K_M
```
Unsloth Desktop

How to use JoeiBanana/ai-network-llms with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JoeiBanana/ai-network-llms:Q4_K_M

Configure the model in Pi

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

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use JoeiBanana/ai-network-llms with Docker Model Runner:
```
docker model run hf.co/JoeiBanana/ai-network-llms:Q4_K_M
```

Lemonade

How to use JoeiBanana/ai-network-llms with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull JoeiBanana/ai-network-llms:Q4_K_M

Run and chat with the model

lemonade run user.ai-network-llms-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use JoeiBanana/ai-network-llms with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JoeiBanana/ai-network-llms: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 JoeiBanana/ai-network-llms:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use JoeiBanana/ai-network-llms with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf JoeiBanana/ai-network-llms:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "JoeiBanana/ai-network-llms:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

ai-network-llms / training /train_llm-t.py

JoeiBanana

Upload batch 8/8

3453f3d verified 5 months ago

Raw

History Blame Contribute Delete

1.71 kB

	from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments, Trainer
	from peft import LoraConfig, get_peft_model
	from datasets import load_dataset
	import torch
	import json

	MODEL_PATH = r"D:\dKorpesio\git_llm_wazuh\hermes\Hermes-3-Llama-3.1-8B"
	DATA_PATH = "llm_t_dataset_750.jsonl"
	OUTPUT = "./lora_llm_t"

	tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)

	base = AutoModelForCausalLM.from_pretrained(
	MODEL_PATH,
	device_map="auto",
	torch_dtype=torch.float16
	)

	lora_cfg = LoraConfig(
	r=8,
	lora_alpha=32,
	lora_dropout=0.1,
	target_modules=["q_proj","v_proj"],
	task_type="CAUSAL_LM"
	)

	model = get_peft_model(base, lora_cfg)

	ds = load_dataset("json", data_files=DATA_PATH)["train"]

	def fmt(example):
	prompt = (
	"### Instruction:\nConvert the following show commands into RESTCONF API calls.\n\n"
	f"### Device:\n{example['device']}\n\n"
	f"### Show commands:\n{json.dumps(example['show_commands'],indent=2)}\n\n"
	"### Response:\n"
	f"{json.dumps(example['api_output'],indent=2)}"
	)
	tokens = tokenizer(prompt, truncation=True, padding="max_length", max_length=1024)
	tokens["labels"] = tokens["input_ids"].copy()
	return tokens

	train = ds.map(fmt)

	args = TrainingArguments(
	output_dir=OUTPUT,
	num_train_epochs=3,
	per_device_train_batch_size=1,
	gradient_accumulation_steps=4,
	learning_rate=2e-4,
	fp16=True,
	logging_steps=20,
	save_strategy="epoch",
	save_total_limit=2
	)

	trainer = Trainer(
	model=model,
	args=args,
	train_dataset=train
	)

	trainer.train()
	model.save_pretrained(OUTPUT)