Instructions to use agentlans/Llama3-Prime with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use agentlans/Llama3-Prime with Transformers:

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

pipe = pipeline("text-generation", model="agentlans/Llama3-Prime")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("agentlans/Llama3-Prime")
model = AutoModelForCausalLM.from_pretrained("agentlans/Llama3-Prime")
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 agentlans/Llama3-Prime with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "agentlans/Llama3-Prime"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "agentlans/Llama3-Prime",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/agentlans/Llama3-Prime

SGLang

How to use agentlans/Llama3-Prime 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 "agentlans/Llama3-Prime" \
    --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": "agentlans/Llama3-Prime",
		"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 "agentlans/Llama3-Prime" \
        --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": "agentlans/Llama3-Prime",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use agentlans/Llama3-Prime with Docker Model Runner:
```
docker model run hf.co/agentlans/Llama3-Prime
```

agentlans commited on Jun 27, 2024

Commit

e4f2a7d

verified ·

1 Parent(s): 9c6e793

Update README.md

Browse files

Files changed (1) hide show

README.md +28 -3

README.md CHANGED Viewed

@@ -1,3 +1,28 @@
----
-license: llama3
----

+---
+license: llama3
+---
+# Llama3-Prime
+This [Llama 3 8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) model is a merge of other pretrained Llama 3 language models that were optimized for user preference. As a result, this merged model should be strong at providing relevant answers to user queries. Here, usability is more important than beating benchmarks.
+- Input: text only
+- Output: text only
+- Prompt format: Llama 3
+- Language: English
+This model was created by merging multiple models with equal weights through the use of [MergeKit's](https://github.com/arcee-ai/mergekit) `model_stock` method.
+Base Model: [Daredevil-8B](https://huggingface.co/mlabonne/Daredevil-8B)
+Models Used:
+- [Llama-3-Instruct-8B-SimPO-ExPO](https://huggingface.co/chujiezheng/Llama-3-Instruct-8B-SimPO-ExPO)
+- [Llama-3-8B-Magpie-Pro-SFT-v0.1](https://huggingface.co/Magpie-Align/Llama-3-8B-Magpie-Pro-SFT-v0.1)
+- [SELM-Llama-3-8B-Instruct-iter-3](https://huggingface.co/ZhangShenao/SELM-Llama-3-8B-Instruct-iter-3)
+- [LLaMA3-iterative-DPO-final-ExPO](https://huggingface.co/chujiezheng/LLaMA3-iterative-DPO-final-ExPO)
+- [Llama-3-Instruct-8B-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Llama-3-Instruct-8B-SPPO-Iter3)
+- [MAmmoTH2-8B-Plus](https://huggingface.co/TIGER-Lab/MAmmoTH2-8B-Plus)
+- [Bagel-8b-v1.0](https://huggingface.co/jondurbin/bagel-8b-v1.0)
+Training Details:
+The merged model was trained using [LLaMA Factory](https://github.com/hiyouga/LLaMA-Factory) on the `alpaca_en_demo` dataset to ensure the model can respond in the Llama 3 Instruct format. The training parameters included a rank of 1, an alpha value of 1, and a 0.3 dropout rate. In other words, very weak training to prevent interfering with the merged model's capabilities.