Instructions to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/meta-llama-3.1-8b-bnb-4bit")
model = PeftModel.from_pretrained(base_model, "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3")

Transformers

How to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3

SGLang

How to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3 with Docker Model Runner:
```
docker model run hf.co/hobbesthecomputerscientist/Llama-3.1-8B-Mock-Trial-AI-v3
```

hobbesthecomputerscientist commited on Apr 6

Commit

caee3a6

verified ·

1 Parent(s): 58e2a17

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -2

README.md CHANGED Viewed

@@ -18,10 +18,12 @@ This model is a fine-tuned version of **Meta-Llama-3.1-8B**, specifically optimi
 ---
 ### 🚀 Try the Live Interface!
-If you want to experience the model's reasoning without writing code, check out the **Mock Trial AI V3 Production Space**:
 👉 [**Mock Trial AI V3 on Hugging Face Spaces**](https://huggingface.co/spaces/hobbesthecomputerscientist/mock-trial-v3)
-**If you find these weights or the dataset useful, please consider leaving a ❤️ Like on this repository!** It helps the project reach more law students and developers in the community.
 ---

 ---
 ### 🚀 Try the Live Interface!
+If you want to experience the logic of this project in a high-speed production environment, check out the **Mock Trial AI V3 Space**:
 👉 [**Mock Trial AI V3 on Hugging Face Spaces**](https://huggingface.co/spaces/hobbesthecomputerscientist/mock-trial-v3)
+> **Note on Architecture:** To ensure sub-second latency and 24/7 availability, the live Production Space utilizes the **Llama 3.1 Base Model** accelerated by the **Groq LPU**, using **Instruction Distillation** derived from this fine-tuning research. These weights remain available here for developers looking to run the specialized LoRA adapter locally.
+**If you find these weights or the dataset useful, please consider leaving a ❤️ Like on this repository!**
 ---