Instructions to use gardner/TinyLlama-1.1B-Instruct-3T with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use gardner/TinyLlama-1.1B-Instruct-3T with Transformers:

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

pipe = pipeline("text-generation", model="gardner/TinyLlama-1.1B-Instruct-3T")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("gardner/TinyLlama-1.1B-Instruct-3T")
model = AutoModelForCausalLM.from_pretrained("gardner/TinyLlama-1.1B-Instruct-3T")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use gardner/TinyLlama-1.1B-Instruct-3T with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "gardner/TinyLlama-1.1B-Instruct-3T"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "gardner/TinyLlama-1.1B-Instruct-3T",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/gardner/TinyLlama-1.1B-Instruct-3T

SGLang

How to use gardner/TinyLlama-1.1B-Instruct-3T 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 "gardner/TinyLlama-1.1B-Instruct-3T" \
    --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": "gardner/TinyLlama-1.1B-Instruct-3T",
		"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 "gardner/TinyLlama-1.1B-Instruct-3T" \
        --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": "gardner/TinyLlama-1.1B-Instruct-3T",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use gardner/TinyLlama-1.1B-Instruct-3T with Docker Model Runner:
```
docker model run hf.co/gardner/TinyLlama-1.1B-Instruct-3T
```

TinyLlama 1.1B Instruct 3T

This is the 3T base model trained on openhermes instruct dataset for 4 epochs. It is intended to be used for further finetuning.

Loss

axolotl config file: lora.yml

base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: true
load_in_4bit: false
strict: false

datasets:
  - path: teknium/openhermes
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./tiny-llama-instruct-lora

sequence_len: 4096
sample_packing: true
pad_to_sequence_len: true

adapter: lora
lora_model_dir:
lora_r: 32
lora_alpha: 16
lora_dropout: 0.05
lora_target_linear: true
lora_fan_in_fan_out:

gradient_accumulation_steps: 4
micro_batch_size: 2
num_epochs: 4
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002

train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 10
evals_per_epoch: 4
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens: