Instructions to use kuotient/Llama-3-8B-Instruct-vector-diff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kuotient/Llama-3-8B-Instruct-vector-diff with Transformers:

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

pipe = pipeline("text-generation", model="kuotient/Llama-3-8B-Instruct-vector-diff")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kuotient/Llama-3-8B-Instruct-vector-diff")
model = AutoModelForCausalLM.from_pretrained("kuotient/Llama-3-8B-Instruct-vector-diff")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kuotient/Llama-3-8B-Instruct-vector-diff with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kuotient/Llama-3-8B-Instruct-vector-diff"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/Llama-3-8B-Instruct-vector-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kuotient/Llama-3-8B-Instruct-vector-diff

SGLang

How to use kuotient/Llama-3-8B-Instruct-vector-diff 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 "kuotient/Llama-3-8B-Instruct-vector-diff" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/Llama-3-8B-Instruct-vector-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "kuotient/Llama-3-8B-Instruct-vector-diff" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kuotient/Llama-3-8B-Instruct-vector-diff",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kuotient/Llama-3-8B-Instruct-vector-diff with Docker Model Runner:
```
docker model run hf.co/kuotient/Llama-3-8B-Instruct-vector-diff
```

Llama-3 chat vector

Update 0426: A small problem with the deployment of the model 'Llama-3-Seagull-Evo-8B', but we hope to have it back in good time!
Update 0526: Check our newest EMM model, Alpha-Ko-8B-Instruct

This is 'modelified' version of chat vector from the paper Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages. So this is not a model, its just weight diff, just for ease to use myself(or you too)!

What I understand here: 'Chat vector method' is a merging method that utilizes the difference between the base model, the continuously pre-trained (usually language transferred) model, and the chat model; so the recipe is

model(base) + weight_diff(continous pretrained) + weight_diff(instruct) or

model(base) + weight_diff(continous pretrained + fine-tuned) + weight_diff(instruct).

So before (my) initial purpose in comparing which method is better, llama3 → CP + chat vector → FT vs. llama3 → CP → FT + chat vector, it seems reasonable to compare it with other methods in Mergekit.

Model	Method	Kobest(f1)	Haerae(acc)
beomi/Llama-3-Open-Ko-8B-Instruct-preview	chat vector	0.4368	0.439
kuotient/Llama-3-Ko-8B-ties	Ties	0.4821	0.5160
kuotient/Llama-3-Ko-8B-dare-ties	Dare-ties	0.4950	0.5399
kuotient/Llama-3-Ko-8B-TA	Task Arithmetic(maybe...? not sure about this)	-
WIP	Model stock(I don't read this paper yet but still)	-
kuotient/Llama-3-Seagull-Evo-8B	Evolutionary Model Merging	0.6139	0.5344
---	---	---	---
meta-llama/Meta-Llama-3-8B	Base	-	-
meta-llama/Meta-Llama-3-8B-Instruct	-	0.4239	0.4931
beomi/Llama-3-Open-Ko-8B	Korean Base	0.4374	0.3813

All that aside, I'd like to thank @beomi for creating such an awesome korean-based model.

Downloads last month: 4

Safetensors

Model size

8B params

Tensor type

BF16

Collection including kuotient/Llama-3-8B-Instruct-vector-diff

Base + Language + Instruct (Korean)

Collection

8 items • Updated May 24, 2024 • 3

Paper for kuotient/Llama-3-8B-Instruct-vector-diff

Chat Vector: A Simple Approach to Equip LLMs With New Language Chat Capabilities

Paper • 2310.04799 • Published Oct 7, 2023