Instructions to use Undi95/Llama-3-Chatty-2x8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Undi95/Llama-3-Chatty-2x8B with Transformers:

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

pipe = pipeline("text-generation", model="Undi95/Llama-3-Chatty-2x8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Undi95/Llama-3-Chatty-2x8B")
model = AutoModelForCausalLM.from_pretrained("Undi95/Llama-3-Chatty-2x8B")
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 Undi95/Llama-3-Chatty-2x8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Undi95/Llama-3-Chatty-2x8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Undi95/Llama-3-Chatty-2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Undi95/Llama-3-Chatty-2x8B

SGLang

How to use Undi95/Llama-3-Chatty-2x8B 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 "Undi95/Llama-3-Chatty-2x8B" \
    --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": "Undi95/Llama-3-Chatty-2x8B",
		"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 "Undi95/Llama-3-Chatty-2x8B" \
        --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": "Undi95/Llama-3-Chatty-2x8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Undi95/Llama-3-Chatty-2x8B with Docker Model Runner:
```
docker model run hf.co/Undi95/Llama-3-Chatty-2x8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Chatty-2x8B

Description

After some testing, finetuning and multiple merges of Llama-3 LLM models, here is something a little different.

This model is a MoE of 2x Llama-3 model trained on different RP format.

This repo contains FP16 files of Chatty-2x8B.

The idea

I started with two separate Llama-3-Instruct-8B models, each fine-tuned for specific RP formats.

Here is two simple exemple of how it was trained.

Expert 1: This model is trained to handle RP that requires actions and descriptions between asterisks. For example:
```
*nods* Yes, I understand.
```
Expert 2: This model is fine-tuned for plain text RP where characters’ dialogues and actions are described straightforwardly. For example:
```
Nods. "Yes, I understand."
```

My initial idea was to make a 11B or bigger Llama-3 model, or just make a 2x8B from existing model, but I got some issues, they were not stable enough, even after DPO and FFT on top my frankenmerge/moe of Llama-3, it was not working well enough to release them.

So I just tried the idea of having 2 different RP format trained on 2 separated Llama-3-Instruct-8B, and it worked pretty well!

The dataset

Based on Lumimaid 8B OAS success I still used the same "balance" between RP and non RP in the dataset, the maximum was 50% non RP data on each side.

RP data was different with some exception, the non RP data was exactly the same, despite that, I can't produce repetition so the double usage of non RP datasets didn't hurt the model in the end.

Prompt template: Llama3

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Others

Undi: If you want to support us, you can here.

IkariDev: Visit my retro/neocities style website please kek

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
arc_challenge	1	none	0	acc	0.5469	±	0.0145
		none	0	acc_norm	0.5853	±	0.0144
arc_easy	1	none	0	acc	0.8308	±	0.0077
		none	0	acc_norm	0.8258	±	0.0078
gsm8k	3	strict-match	5	exact_match	0.7149	±	0.0124
		flexible-extract	5	exact_match	0.7096	±	0.0125
hellaswag	1	none	0	acc	0.5945	±	0.0049
		none	0	acc_norm	0.7806	±	0.0041
piqa	1	none	0	acc	0.7943	±	0.0094
		none	0	acc_norm	0.7998	±	0.0093
truthfulqa_mc2	2	none	0	acc	0.5097	±	0.0150
winogrande	1	none	0	acc	0.7356	±	0.0124

Downloads last month: 7

Safetensors

Model size

14B params

Tensor type

BF16

Model tree for Undi95/Llama-3-Chatty-2x8B

Quantizations

4 models