Instructions to use deltanym/llama-3.1-120b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deltanym/llama-3.1-120b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="deltanym/llama-3.1-120b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("deltanym/llama-3.1-120b-instruct")
model = AutoModelForCausalLM.from_pretrained("deltanym/llama-3.1-120b-instruct")
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

vLLM

How to use deltanym/llama-3.1-120b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deltanym/llama-3.1-120b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deltanym/llama-3.1-120b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deltanym/llama-3.1-120b-instruct

SGLang

How to use deltanym/llama-3.1-120b-instruct 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 "deltanym/llama-3.1-120b-instruct" \
    --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": "deltanym/llama-3.1-120b-instruct",
		"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 "deltanym/llama-3.1-120b-instruct" \
        --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": "deltanym/llama-3.1-120b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use deltanym/llama-3.1-120b-instruct with Docker Model Runner:
```
docker model run hf.co/deltanym/llama-3.1-120b-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

llama-3.1-120b-instruct

This is a merge of pre-trained language models created using mergekit. It's a recreation of mlabonne/Meta-Llama-3-120B-Instruct but using Llama 3.1 70b instead of Llama 3, with the same configuration.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

meta-llama/Llama-3.1-70B-Instruct

Configuration

The following YAML configuration was used to produce this model:

slices:
- sources:
  - layer_range: [0, 20]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [10, 30]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [20, 40]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [30, 50]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [40, 60]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [50, 70]
    model: meta-llama/Llama-3.1-70B-Instruct
- sources:
  - layer_range: [60, 80]
    model: meta-llama/Llama-3.1-70B-Instruct
merge_method: passthrough
dtype: float16

Downloads last month: 3

Safetensors

Model size

122B params

Tensor type

F16

Model tree for deltanym/llama-3.1-120b-instruct

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.1-70B-Instruct

Finetuned

(90)

this model

Quantizations

2 models