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

Libraries

How to use Tensoic/TinyLlama-1.1B-3T-openhermes with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Tensoic/TinyLlama-1.1B-3T-openhermes with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Tensoic/TinyLlama-1.1B-3T-openhermes

SGLang

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

Docker Model Runner
How to use Tensoic/TinyLlama-1.1B-3T-openhermes with Docker Model Runner:
```
docker model run hf.co/Tensoic/TinyLlama-1.1B-3T-openhermes
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is the Instruction Fine Tuned version of Tiny Llama on @Teknium1's openhermes dataset.

"The TinyLlama project aims to pretrain a 1.1B Llama model on 3 trillion tokens. With some proper optimization, we can achieve this within a span of "just" 90 days using 16 A100-40G GPUs 🚀🚀. The training has started on 2023-09-01."

See axolotl config

axolotl version: 0.3.0

base_model: ./TinyLlama-1.1B-intermediate-step-1431k-3T

model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
is_llama_derived_model: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: ./openhermes
    type: alpaca
dataset_prepared_path:
val_set_size: 0.05
output_dir: ./out

sequence_len: 4096
sample_packing: false

adapter: 
lora_model_dir:
lora_r: 
lora_alpha: 
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:

wandb_project: tinyllama-openhermes
wandb_entity: tensoic
wandb_watch:
wandb_name: 
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 8
num_epochs: 1
optimizer: adamw_bnb_8bit
adam_epsilon: 0.00001
max_grad_norm: 1.0
lr_scheduler: cosine
learning_rate: 0.0002

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

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

warmup_steps: 100
evals_per_epoch: 4
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: zero2.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  bos_token: "<s>"
  eos_token: "</s>"
  unk_token: "<unk>"

The model achieves the following loss:

Loss: 1.3647

The loss exploded after a couple hundred steps. As suggested by winglian, we set the following values in the config file:

adam_epsilon: 0.00001
max_grad_norm: 1.0

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-05
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
num_epochs: 1
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.0006	0.0	1	1.6838
0.8195	0.25	451	1.4620
0.6836	0.5	902	1.4158
0.6811	0.75	1353	1.3647

Framework versions

Transformers 4.36.2
Pytorch 2.0.1+cu117
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 10

Model tree for Tensoic/TinyLlama-1.1B-3T-openhermes

Merges

4 models

Quantizations

1 model

Tensoic
/

TinyLlama-1.1B-3T-openhermes

Training hyperparameters

Training results

Framework versions

Model tree for Tensoic/TinyLlama-1.1B-3T-openhermes

Dataset used to train Tensoic/TinyLlama-1.1B-3T-openhermes