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

Libraries
PEFT
How to use cpiuk/htech_compliance with PEFT:
```
Task type is invalid.
```

How to use cpiuk/htech_compliance with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cpiuk/htech_compliance",
	filename="phi-4-mini-instruct.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use cpiuk/htech_compliance with llama.cpp:

Install from brew

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

Install from WinGet (Windows)

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

Use Docker

docker model run hf.co/cpiuk/htech_compliance:Q4_K_M

LM Studio
Jan

vLLM

How to use cpiuk/htech_compliance with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/cpiuk/htech_compliance:Q4_K_M

Ollama
How to use cpiuk/htech_compliance with Ollama:
```
ollama run hf.co/cpiuk/htech_compliance:Q4_K_M
```

Unsloth Studio

How to use cpiuk/htech_compliance 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 cpiuk/htech_compliance 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 cpiuk/htech_compliance to start chatting

Using HuggingFace Spaces for Unsloth

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

How to use cpiuk/htech_compliance with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cpiuk/htech_compliance: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": "cpiuk/htech_compliance:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cpiuk/htech_compliance with Hermes Agent:

Start the llama.cpp server

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

Run Hermes

hermes

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

Lemonade

How to use cpiuk/htech_compliance with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cpiuk/htech_compliance:Q4_K_M

Run and chat with the model

lemonade run user.htech_compliance-Q4_K_M

List all available models

lemonade list

cpiuk commited on Apr 15

Commit

241a47f

verified ·

1 Parent(s): e829e30

Add v3 training summary

Browse files

Files changed (1) hide show

training_data_v3/training_summary.json +64 -0

training_data_v3/training_summary.json ADDED Viewed

	@@ -0,0 +1,64 @@

+{
+  "model": "unsloth/Phi-4-mini-instruct",
+  "lora": {
+    "r": 32,
+    "alpha": 32,
+    "targets": [
+      "q_proj",
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "gate_proj",
+      "up_proj",
+      "down_proj"
+    ]
+  },
+  "training": {
+    "epochs": 7,
+    "batch_size": 32,
+    "grad_accum": 2,
+    "effective_batch": 64,
+    "lr": 0.0002,
+    "max_seq_len": 512,
+    "packing": true,
+    "optimizer": "adamw_8bit",
+    "scheduler": "cosine",
+    "warmup_steps": 30
+  },
+  "dataset": {
+    "train": 9268,
+    "val": 1034,
+    "total": 10302
+  },
+  "total_steps": 870,
+  "loss_curve": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.40697577595710754
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.14752867817878723
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.09198899567127228
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.06869391351938248
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.06067777797579765
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.05765723064541817
+    }
+  ],
+  "final_train_loss": 0.0327,
+  "final_eval_loss": 0.05765723064541817,
+  "gpu": "NVIDIA RTX A6000 48GB",
+  "framework": "Unsloth 2026.4.4 + TRL SFTTrainer"
+}