Instructions to use Sao10K/70B-L3.3-mhnnn-x1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sao10K/70B-L3.3-mhnnn-x1 with Transformers:

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

pipe = pipeline("text-generation", model="Sao10K/70B-L3.3-mhnnn-x1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Sao10K/70B-L3.3-mhnnn-x1")
model = AutoModelForCausalLM.from_pretrained("Sao10K/70B-L3.3-mhnnn-x1")
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/70B-L3.3-mhnnn-x1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sao10K/70B-L3.3-mhnnn-x1"
# 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/70B-L3.3-mhnnn-x1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sao10K/70B-L3.3-mhnnn-x1

SGLang

How to use Sao10K/70B-L3.3-mhnnn-x1 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/70B-L3.3-mhnnn-x1" \
    --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/70B-L3.3-mhnnn-x1",
		"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/70B-L3.3-mhnnn-x1" \
        --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/70B-L3.3-mhnnn-x1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sao10K/70B-L3.3-mhnnn-x1 with Docker Model Runner:
```
docker model run hf.co/Sao10K/70B-L3.3-mhnnn-x1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

my mental when things do not go well

70B-L3.3-mhnnn-x1

I quite liked it, after messing around. Same data composition as Freya, applied differently.

Has occasional brainfarts which are fixed with a regen, the price for more creative outputs.

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: 0.05

Types of Data included within Sets

Completion - Novels / eBooks
Text Adventure - Include details like 'Text Adventure Narrator' in the System Prompt, give it a one-shot example and it'll fly.
Amoral Assistant - Include the terms 'Amoral', 'Neutral' along with the regular assistant prompt for better results.
Instruct / Assistant - The usual assistant tasks.
Roleplay - As per Usual, Regular Sets

Training time in total was ~14 Hours on a 8xH100 Node, shout out to SCDF for not sponsoring this run. My funds are dry doing random things.

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

See axolotl config

axolotl version: 0.6.0

adapter: lora # 16-bit
lora_r: 64
lora_alpha: 64
lora_dropout: 0.2
peft_use_rslora: true
lora_target_linear: true
  
# Data
dataset_prepared_path: dataset_run_freya
datasets:
# S1 - Writing / Completion
  - path: datasets/eBooks-cleaned-75K
    type: completion
  - path: datasets/novels-clean-dedupe-10K
    type: completion
# S2 - Instruct
  - path: datasets/10k-amoral-full-fixed-sys.json
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/44k-hespera-smartshuffle.json
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
  - path: datasets/5k_rpg_adventure_instruct-sys.json
    type: chat_template
    chat_template: llama3
    roles_to_train: ["gpt"]
    field_messages: conversations
    message_field_role: from
    message_field_content: value
    train_on_eos: turn
shuffle_merged_datasets: true
warmup_ratio: 0.1

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

# Sampling
sample_packing: true
pad_to_sequence_len: true
train_on_inputs: false
group_by_length: false

# Batching
gradient_accumulation_steps: 4
micro_batch_size: 2
gradient_checkpointing: unsloth

# Evaluation
val_set_size: 0.025
evals_per_epoch: 5
eval_table_size:
eval_max_new_tokens: 256
eval_sample_packing: false
eval_batch_size: 1

# Optimizer
optimizer: paged_ademamix_8bit
lr_scheduler: cosine
learning_rate: 0.00000242
weight_decay: 0.2
max_grad_norm: 10.0

# Garbage Collection
gc_steps: 10

# Misc
deepspeed: ./deepspeed_configs/zero3_bf16.json

Downloads last month: 23

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for Sao10K/70B-L3.3-mhnnn-x1

Base model

meta-llama/Llama-3.1-70B

Finetuned

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

Finetuned

(613)

this model

Merges

46 models

Quantizations

4 models