Instructions to use TRAC-MTRY/traclm-v3-7b-instruct-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TRAC-MTRY/traclm-v3-7b-instruct-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TRAC-MTRY/traclm-v3-7b-instruct-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TRAC-MTRY/traclm-v3-7b-instruct-AWQ")
model = AutoModelForCausalLM.from_pretrained("TRAC-MTRY/traclm-v3-7b-instruct-AWQ")
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 TRAC-MTRY/traclm-v3-7b-instruct-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TRAC-MTRY/traclm-v3-7b-instruct-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TRAC-MTRY/traclm-v3-7b-instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TRAC-MTRY/traclm-v3-7b-instruct-AWQ

SGLang

How to use TRAC-MTRY/traclm-v3-7b-instruct-AWQ 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 "TRAC-MTRY/traclm-v3-7b-instruct-AWQ" \
    --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": "TRAC-MTRY/traclm-v3-7b-instruct-AWQ",
		"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 "TRAC-MTRY/traclm-v3-7b-instruct-AWQ" \
        --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": "TRAC-MTRY/traclm-v3-7b-instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TRAC-MTRY/traclm-v3-7b-instruct-AWQ with Docker Model Runner:
```
docker model run hf.co/TRAC-MTRY/traclm-v3-7b-instruct-AWQ
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Model Card for traclm-v3-7b-instruct-AWQ

This repo contains an AWQ quantization of TRAC-MTRY/traclm-v3-7b-instruct for utilization of the model on low-resource hardware.

Prompt Format

This model was fine-tuned with the chatml prompt format. It is highly recommended that you use the same format for any interactions with the model. Failure to do so will degrade performance significantly.

ChatML Format:

<|im_start|>system 
Provide some context and/or instructions to the model.
<|im_end|> 
<|im_start|>user 
The user’s message goes here
<|im_end|> 
<|im_start|>assistant

The ChatML format can easily be applied to text you plan to process with the model using the chat_template included in the tokenizer. Read here for additional information.

Model Card Contact

MAJ Daniel C. Ruiz (daniel.ruiz@nps.edu)

Downloads last month: -

Safetensors

Model size

7B params

Tensor type

I32

F16

Dataset used to train TRAC-MTRY/traclm-v3-7b-instruct-AWQ

Paper for TRAC-MTRY/traclm-v3-7b-instruct-AWQ

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Paper • 2306.00978 • Published Jun 1, 2023 • 13