Instructions to use botverse/Titans-MAC-Llama-3-8b-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use botverse/Titans-MAC-Llama-3-8b-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="botverse/Titans-MAC-Llama-3-8b-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("botverse/Titans-MAC-Llama-3-8b-Instruct", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("botverse/Titans-MAC-Llama-3-8b-Instruct", trust_remote_code=True)
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 botverse/Titans-MAC-Llama-3-8b-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "botverse/Titans-MAC-Llama-3-8b-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": "botverse/Titans-MAC-Llama-3-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/botverse/Titans-MAC-Llama-3-8b-Instruct

SGLang

How to use botverse/Titans-MAC-Llama-3-8b-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 "botverse/Titans-MAC-Llama-3-8b-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": "botverse/Titans-MAC-Llama-3-8b-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 "botverse/Titans-MAC-Llama-3-8b-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": "botverse/Titans-MAC-Llama-3-8b-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use botverse/Titans-MAC-Llama-3-8b-Instruct with Docker Model Runner:
```
docker model run hf.co/botverse/Titans-MAC-Llama-3-8b-Instruct
```

Error when loading

by irodkin - opened Feb 16

Discussion

irodkin

Feb 16

Code:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch # Added import for example

model_id = "botverse/Titans-MAC-Llama-3-8b-Instruct" # Replace with your repo ID

# Load the model and tokenizer, allowing custom code execution
# Requires sufficient VRAM for the Llama 8B model + memory buffer
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    torch_dtype=torch.float16, # Recommended for memory
    device_map="auto"
)

Error:

ValueError                                Traceback (most recent call last)
Cell In[1], line 8
      4 model_id = "botverse/Titans-MAC-Llama-3-8b-Instruct" # Replace with your repo ID
      6 # Load the model and tokenizer, allowing custom code execution
      7 # Requires sufficient VRAM for the Llama 8B model + memory buffer
----> 8 model = AutoModelForCausalLM.from_pretrained(
      9     model_id,
     10     trust_remote_code=True,
     11     torch_dtype=torch.float16, # Recommended for memory
     12     device_map="auto"
     13 )
     14 tokenizer = AutoTokenizer.from_pretrained(model_id)
     16 # Example prompt

File /opt/homebrew/Caskroom/miniconda/base/envs/ai/lib/python3.10/site-packages/transformers/models/auto/auto_factory.py:356, in _BaseAutoModelClass.from_pretrained(cls, pretrained_model_name_or_path, *model_args, **kwargs)
    353 kwargs["adapter_kwargs"] = adapter_kwargs
    355 if has_remote_code and trust_remote_code:
--> 356     model_class = get_class_from_dynamic_module(
    357         class_ref, pretrained_model_name_or_path, code_revision=code_revision, **hub_kwargs, **kwargs
    358     )
    359     _ = hub_kwargs.pop("code_revision", None)
    360     # This block handles the case where the user is loading a model with `trust_remote_code=True`
    361     # but a library model exists with the same name. We don't want to override the autoclass
    362     # mappings in this case, or all future loads of that model will be the remote code model.

File /opt/homebrew/Caskroom/miniconda/base/envs/ai/lib/python3.10/site-packages/transformers/dynamic_module_utils.py:567, in get_class_from_dynamic_module(class_reference, pretrained_model_name_or_path, cache_dir, force_download, proxies, token, revision, local_files_only, repo_type, code_revision, **kwargs)
    565 else:
    566     repo_id = pretrained_model_name_or_path
--> 567 module_file, class_name = class_reference.split(".")
    569 if code_revision is None and pretrained_model_name_or_path == repo_id:
    570     code_revision = revision

ValueError: too many values to unpack (expected 2)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment