Instructions to use Sao10K/L3.3-70B-Euryale-v2.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sao10K/L3.3-70B-Euryale-v2.3 with Transformers:

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

pipe = pipeline("text-generation", model="Sao10K/L3.3-70B-Euryale-v2.3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sao10K/L3.3-70B-Euryale-v2.3")
model = AutoModelForCausalLM.from_pretrained("Sao10K/L3.3-70B-Euryale-v2.3")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Sao10K/L3.3-70B-Euryale-v2.3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sao10K/L3.3-70B-Euryale-v2.3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Sao10K/L3.3-70B-Euryale-v2.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sao10K/L3.3-70B-Euryale-v2.3

SGLang

How to use Sao10K/L3.3-70B-Euryale-v2.3 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 "Sao10K/L3.3-70B-Euryale-v2.3" \
    --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": "Sao10K/L3.3-70B-Euryale-v2.3",
		"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 "Sao10K/L3.3-70B-Euryale-v2.3" \
        --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": "Sao10K/L3.3-70B-Euryale-v2.3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sao10K/L3.3-70B-Euryale-v2.3 with Docker Model Runner:
```
docker model run hf.co/Sao10K/L3.3-70B-Euryale-v2.3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

L3.3-70B-Euryale-v2.3

A direct replacement / successor to Euryale v2.2, not Hanami-x1, though it is slightly better than them in my opinion.

This is entirely trained on top of Llama 3.3 Instruct, not Lora-extracted which is all the rage.

Recommended Model Settings | Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.

Prompt Format: Llama-3-Instruct
Temperature: 1.1
min_p: 0.1

Future-ish plans:
- Further refine the Datasets used for quality, more secondary chats, more creative-related domains.
- Work on my other incomplete projects. About half a dozen on the backburner for a while now.

Special thanks to my wallet for funding this, my juniors who share a single braincell between them, and my current national service.

Have a good day, don't shit yourselves friends. I had a nasty call today.

Also sorry for the inactivity. Life was in the way. It still is, just less so, for now. Burnout is a thing, huh?

https://sao10k.carrd.co/ for contact.

See axolotl config

axolotl version: 0.5.2

base_model: meta-llama/Llama-3.3-70B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false
sequence_len: 16384
bf16: auto
fp16:
tf32: false
flash_attention: true

adapter: lora
lora_model_dir:
lora_r: 128
lora_alpha: 16
lora_dropout: 0.1
lora_target_linear: true
lora_fan_in_fan_out:
peft_use_rslora: true

# Data
dataset_prepared_path: last_run_prepared
datasets:
  - path: datasets/amoral-full-sys-prompt.json # Unalignment Data - Cleaned Up from Original, Split to its own file
    type: customllama3
  - path: datasets/mimi-superfix-RP-filtered-fixed.json # RP / Creative-Instruct Data
    type: customllama3
  - path: datasets/hespera-smartshuffle.json # Hesperus-v2-Instruct Data
    type: customllama3
warmup_steps: 15

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_layer_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

# Iterations
num_epochs: 1

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 1
gradient_checkpointing: "unsloth"

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 0.000004
weight_decay: 0.1
max_grad_norm: 25.0

# Iterations
num_epochs: 1

# Misc
deepspeed: ./deepspeed_configs/zero3_bf16.json

Art by てぃあ
https://www.pixiv.net/en/users/724263

Downloads last month: 1,145

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for Sao10K/L3.3-70B-Euryale-v2.3

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

(613)

this model

Merges

83 models

Quantizations

27 models

Sao10K
/

L3.3-70B-Euryale-v2.3

L3.3-70B-Euryale-v2.3

Model tree for Sao10K/L3.3-70B-Euryale-v2.3

Spaces using Sao10K/L3.3-70B-Euryale-v2.3 16