Instructions to use solidrust/Trillama-8B-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Trillama-8B-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Trillama-8B-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Trillama-8B-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Trillama-8B-AWQ", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/Trillama-8B-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Trillama-8B-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": "solidrust/Trillama-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/Trillama-8B-AWQ

SGLang

How to use solidrust/Trillama-8B-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 "solidrust/Trillama-8B-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": "solidrust/Trillama-8B-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 "solidrust/Trillama-8B-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": "solidrust/Trillama-8B-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/Trillama-8B-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Trillama-8B-AWQ
```

Configuration Parsing Warning:In config.json: "quantization_config.modules_to_not_convert" must be an array

senseable/Trillama-8B AWQ

Model creator: senseable
Original model: Trillama-8B

Model Summary

Trillama-8B is a 8B LLM that builds upon the foundation of Llama-3-8B, the lastest model from Meta. It's a fine-tune focused on improving the model's already strong logic and reasoning.

import transformers
import torch

model_id = "senseable/Trillama-8B"

pipeline = transformers.pipeline(
    "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device_map="auto"
)
pipeline("Explain the meaning of life.")

Downloads last month: 15

Safetensors

Model size

8B params

Tensor type

I32

F16

Model tree for solidrust/Trillama-8B-AWQ

Base model

senseable/Trillama-8B

Quantized

(3)

this model

Collection including solidrust/Trillama-8B-AWQ

8B AWQ

Collection

162 items • Updated Mar 2 • 2