Instructions to use solidrust/Llama-3-8B-flashback-v1-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/Llama-3-8B-flashback-v1-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/Llama-3-8B-flashback-v1-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/Llama-3-8B-flashback-v1-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/Llama-3-8B-flashback-v1-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use solidrust/Llama-3-8B-flashback-v1-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/Llama-3-8B-flashback-v1-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/Llama-3-8B-flashback-v1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/Llama-3-8B-flashback-v1-AWQ

SGLang

How to use solidrust/Llama-3-8B-flashback-v1-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/Llama-3-8B-flashback-v1-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/Llama-3-8B-flashback-v1-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/Llama-3-8B-flashback-v1-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/Llama-3-8B-flashback-v1-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/Llama-3-8B-flashback-v1-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/Llama-3-8B-flashback-v1-AWQ
```

Llama-3-8B-flashback-v1-AWQ

Commit History

Updated base_model tag in README.md

ed8dcb1
verified

Suparious commited on Sep 3, 2024

Update README.md

1b14b32
verified

Suparious commited on May 2, 2024

Update README.md

c95ef73
verified

Suparious commited on May 2, 2024

add default model card

195e86d

Ubuntu commited on May 1, 2024

adding quant config

276f79a

Ubuntu commited on May 1, 2024

adding AWQ model

1619877

Ubuntu commited on May 1, 2024

add processing notice

f58a3d5

Ubuntu commited on May 1, 2024

initial commit

dc59e2b
verified

Suparious commited on May 1, 2024

Commit History

Updated base_model tag in README.md ed8dcb1 verified

Update README.md 1b14b32 verified

Update README.md c95ef73 verified

add default model card 195e86d

adding quant config 276f79a

adding AWQ model 1619877

add processing notice f58a3d5

initial commit dc59e2b verified

Updated base_model tag in README.md

ed8dcb1
verified

Update README.md

1b14b32
verified

Update README.md

c95ef73
verified

add default model card

195e86d

adding quant config

276f79a

adding AWQ model

1619877

add processing notice

f58a3d5

initial commit

dc59e2b
verified