Instructions to use Sao10K/L3-8B-Stheno-v3.3-32K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Sao10K/L3-8B-Stheno-v3.3-32K with Transformers:

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

pipe = pipeline("text-generation", model="Sao10K/L3-8B-Stheno-v3.3-32K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Sao10K/L3-8B-Stheno-v3.3-32K")
model = AutoModelForMultimodalLM.from_pretrained("Sao10K/L3-8B-Stheno-v3.3-32K")
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 Settings

vLLM

How to use Sao10K/L3-8B-Stheno-v3.3-32K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Sao10K/L3-8B-Stheno-v3.3-32K"
# 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/L3-8B-Stheno-v3.3-32K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Sao10K/L3-8B-Stheno-v3.3-32K

SGLang

How to use Sao10K/L3-8B-Stheno-v3.3-32K 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/L3-8B-Stheno-v3.3-32K" \
    --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/L3-8B-Stheno-v3.3-32K",
		"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/L3-8B-Stheno-v3.3-32K" \
        --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/L3-8B-Stheno-v3.3-32K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Sao10K/L3-8B-Stheno-v3.3-32K with Docker Model Runner:
```
docker model run hf.co/Sao10K/L3-8B-Stheno-v3.3-32K
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Trained with compute from Backyard.ai | Thanks to them and @dynafire for helping me out.

Training Details:
Trained at 8K Context -> Expanded to 32K Context with PoSE training.

Dataset Modifications:
- Further Cleaned up Roleplaying Samples -> Quality Check
- Removed Low Quality Samples from Manual Check -> Increased Baseline Quality Floor
- More Creative Writing Samples -> 2x Samples
- Remade and Refined Detailed Instruct Data

Notes:
- Training run is much less aggressive than previous Stheno versions.
- This model works when tested in bf16 with the same configs as within the file.
- I do not know the effects quantisation has on it.
- Roleplays pretty well. Feels nice in my opinion.
- It has some issues on long context understanding and reasoning. Much better vs rope scaling normally though, so that is a plus.
- Reminder, this isn't a native 32K model. It has it's issues, but it's coherent and working well.

Sanity Check // Needle in a Haystack Results:
- This is not as complex as RULER or NIAN, but it's a basic evaluator. Some improper train examples had Haystack scores ranging from Red to Orange for most of the extended contexts.

Wandb Run:

Relevant Axolotl Configurations:
-> Taken from winglian/Llama-3-8b-64k-PoSE
- I tried to find my own configs, hours of tinkering but the one he used worked best, so I stuck to it.
- 2M Rope Theta had the best loss results during training compared to other values.
- Leaving it at 500K rope wasn't that much worse, but 4M and 8M Theta made the grad_norm values worsen even if loss drops fast.
- Mixing in Pretraining Data was a PITA. Made it a lot worse with formatting.
- Pretraining / Noise made it worse at Haystack too? It wasn't all Green, Mainly Oranges.
- Improper / Bad Rope Theta shows in Grad_Norm exploding to thousands. It'll drop to low values alright, but it's a scary fast drop even with gradient clipping.

sequence_len: 8192
use_pose: true
pose_max_context_len: 32768

overrides_of_model_config:
  rope_theta: 2000000.0
  max_position_embeddings: 32768

  # peft_use_dora: true
adapter: lora
peft_use_rslora: true
lora_model_dir:
lora_r: 256
lora_alpha: 256
lora_dropout: 0.1
lora_target_linear: true
lora_target_modules:
  - gate_proj
  - down_proj
  - up_proj
  - q_proj
  - v_proj
  - k_proj
  - o_proj

warmup_steps: 80
gradient_accumulation_steps: 6
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine_with_min_lr
learning_rate: 0.00004
lr_scheduler_kwargs:
    min_lr: 0.000004

Downloads last month: 30

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Sao10K/L3-8B-Stheno-v3.3-32K

Finetunes

3 models

Merges

6 models

Quantizations

12 models

Sao10K
/

L3-8B-Stheno-v3.3-32K

Model tree for Sao10K/L3-8B-Stheno-v3.3-32K

Spaces using Sao10K/L3-8B-Stheno-v3.3-32K 25