Instructions to use Kquant03/L3-Pneuma-8B-6bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kquant03/L3-Pneuma-8B-6bpw with Transformers:

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

pipe = pipeline("text-generation", model="Kquant03/L3-Pneuma-8B-6bpw")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Kquant03/L3-Pneuma-8B-6bpw")
model = AutoModelForCausalLM.from_pretrained("Kquant03/L3-Pneuma-8B-6bpw")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Kquant03/L3-Pneuma-8B-6bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kquant03/L3-Pneuma-8B-6bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/L3-Pneuma-8B-6bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Kquant03/L3-Pneuma-8B-6bpw

SGLang

How to use Kquant03/L3-Pneuma-8B-6bpw 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-Pneuma-8B-6bpw" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/L3-Pneuma-8B-6bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-Pneuma-8B-6bpw" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kquant03/L3-Pneuma-8B-6bpw",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Kquant03/L3-Pneuma-8B-6bpw with Docker Model Runner:
```
docker model run hf.co/Kquant03/L3-Pneuma-8B-6bpw
```

This is just a 6bpw EXL2 quant of the original model which can be found on my huggingface profile. I will write a real model card when I have the final model...it's an experimental tune using part of my sandevistan dataset.

See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Meta-Llama-3-8B

load_in_8bit: false
load_in_4bit: false
strict: false

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: Kquant03/Sandevistan_Reformat
    type: customllama3_stan
dataset_prepared_path: last_run_prepared
val_set_size: 0.05
output_dir: ./outputs/out
max_steps: 80000

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: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 0.00001
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/Meta-Llama-3-8B on the Sandevistan dataset. It achieves the following results on the evaluation set:

Loss: 2.7381

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 743

Training results

Training Loss	Epoch	Step	Validation Loss
1.0378	0.0013	1	3.0437
0.6816	0.3334	248	2.7341
0.6543	0.6667	496	2.7381

Framework versions

Transformers 4.45.1
Pytorch 2.3.1+cu121
Datasets 2.21.0
Tokenizers 0.20.1

Downloads last month: -

Model tree for Kquant03/L3-Pneuma-8B-6bpw

Base model

meta-llama/Meta-Llama-3-8B

Quantized

(273)

this model