Instructions to use Kquant03/L3.1-Pneuma-8B-0429 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kquant03/L3.1-Pneuma-8B-0429 with Transformers:

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

pipe = pipeline("text-generation", model="Kquant03/L3.1-Pneuma-8B-0429")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kquant03/L3.1-Pneuma-8B-0429")
model = AutoModelForCausalLM.from_pretrained("Kquant03/L3.1-Pneuma-8B-0429")
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 Kquant03/L3.1-Pneuma-8B-0429 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kquant03/L3.1-Pneuma-8B-0429"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/L3.1-Pneuma-8B-0429",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kquant03/L3.1-Pneuma-8B-0429

SGLang

How to use Kquant03/L3.1-Pneuma-8B-0429 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 "Kquant03/L3.1-Pneuma-8B-0429" \
    --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": "Kquant03/L3.1-Pneuma-8B-0429",
		"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 "Kquant03/L3.1-Pneuma-8B-0429" \
        --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": "Kquant03/L3.1-Pneuma-8B-0429",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kquant03/L3.1-Pneuma-8B-0429 with Docker Model Runner:
```
docker model run hf.co/Kquant03/L3.1-Pneuma-8B-0429
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

See axolotl config

axolotl version: 0.8.0

base_model: meta-llama/Llama-3.1-8B-Instruct

load_in_8bit: false
load_in_4bit: false
strict: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Sandevistan_cleaned.jsonl
    type: customllama3_stan
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/out

fix_untrained_tokens: true

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

wandb_project: Pneuma
wandb_entity: 
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 16
micro_batch_size: 8
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.000075
max_grad_norm: 1

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: unsloth
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
eval_sample_packing: false

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

hub_model_id: Replete-AI/L3-Pneuma-8B
hub_strategy: every_save

warmup_steps: 10
evals_per_epoch: 3
eval_table_size:
saves_per_epoch: 3
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<|begin_of_text|>"
  eos_token: "<|end_of_text|>"
  pad_token: "<|end_of_text|>"
tokens:

L3-Pneuma-8B

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the Sandevistan_cleaned.jsonl dataset. It achieves the following results on the evaluation set:

Loss: 0.7796

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 7.5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
num_epochs: 2.0