Instructions to use T145/Meta-Llama-3.1-8B-Instruct-TIES with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use T145/Meta-Llama-3.1-8B-Instruct-TIES with Transformers:

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

pipe = pipeline("text-generation", model="T145/Meta-Llama-3.1-8B-Instruct-TIES")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("T145/Meta-Llama-3.1-8B-Instruct-TIES")
model = AutoModelForCausalLM.from_pretrained("T145/Meta-Llama-3.1-8B-Instruct-TIES", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use T145/Meta-Llama-3.1-8B-Instruct-TIES with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "T145/Meta-Llama-3.1-8B-Instruct-TIES"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "T145/Meta-Llama-3.1-8B-Instruct-TIES",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/T145/Meta-Llama-3.1-8B-Instruct-TIES

SGLang

How to use T145/Meta-Llama-3.1-8B-Instruct-TIES 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 "T145/Meta-Llama-3.1-8B-Instruct-TIES" \
    --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": "T145/Meta-Llama-3.1-8B-Instruct-TIES",
		"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 "T145/Meta-Llama-3.1-8B-Instruct-TIES" \
        --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": "T145/Meta-Llama-3.1-8B-Instruct-TIES",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use T145/Meta-Llama-3.1-8B-Instruct-TIES with Docker Model Runner:
```
docker model run hf.co/T145/Meta-Llama-3.1-8B-Instruct-TIES
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Rombo Llama Merge Test

This merge provides a baseline for performance when the instruct model is merged on the base. It follows Rombodawg's merge method on Qwen models, and should prove if it works with Llama models. Running hypothesis is that the IFEval benchmark will get nuked. A success will be little to no performance change over the vanilla instruct model.

Merge Details

Merge Method

This model was merged using the TIES merge method using unsloth/Meta-Llama-3.1-8B as a base.

Models Merged

The following models were included in the merge:

unsloth/Meta-Llama-3.1-8B-Instruct

Configuration

The following YAML configuration was used to produce this model:

base_model: unsloth/Meta-Llama-3.1-8B
dtype: bfloat16
merge_method: ties
parameters:
  density: 1.0
  weight: 1.0
slices:
- sources:
  - layer_range: [0, 32]
    model: unsloth/Meta-Llama-3.1-8B-Instruct
    parameters:
      density: 1.0
      weight: 1.0
  - layer_range: [0, 32]
    model: unsloth/Meta-Llama-3.1-8B
tokenizer_source: unsloth/Meta-Llama-3.1-8B-Instruct