Instructions to use solidrust/dolphin-2.9-llama3-8b-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use solidrust/dolphin-2.9-llama3-8b-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="solidrust/dolphin-2.9-llama3-8b-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("solidrust/dolphin-2.9-llama3-8b-AWQ")
model = AutoModelForCausalLM.from_pretrained("solidrust/dolphin-2.9-llama3-8b-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

vLLM

How to use solidrust/dolphin-2.9-llama3-8b-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "solidrust/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/solidrust/dolphin-2.9-llama3-8b-AWQ

SGLang

How to use solidrust/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-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/dolphin-2.9-llama3-8b-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use solidrust/dolphin-2.9-llama3-8b-AWQ with Docker Model Runner:
```
docker model run hf.co/solidrust/dolphin-2.9-llama3-8b-AWQ
```

cognitivecomputations/dolphin-2.9-llama3-8b AWQ

Curated and trained by Eric Hartford, Lucas Atkins, and Fernando Fernandes, and Cognitive Computations

Discord: https://discord.gg/8fbBeC7ZGx

My appreciation for the sponsors of Dolphin 2.9:

Crusoe Cloud - provided excellent on-demand 10xL40S node

This model is based on Llama-3-8b, and is governed by META LLAMA 3 COMMUNITY LICENSE AGREEMENT

The base model has 8k context, and the full-weight fine-tuning was with 4k sequence length.

It took 2.5 days on 8x L40S provided by Crusoe Cloud

This model was trained FFT on all parameters, using ChatML prompt template format.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Downloads last month: 102

Safetensors

Model size

8B params

Tensor type

I32

F16

Model tree for solidrust/dolphin-2.9-llama3-8b-AWQ

Base model

meta-llama/Meta-Llama-3-8B

Quantized

(276)

this model

Datasets used to train solidrust/dolphin-2.9-llama3-8b-AWQ

Collection including solidrust/dolphin-2.9-llama3-8b-AWQ

8B AWQ

Collection

162 items • Updated Mar 2 • 2