Instructions to use four-two-labs/tinyllama-moe-nord-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use four-two-labs/tinyllama-moe-nord-chat with Transformers:

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

pipe = pipeline("text-generation", model="four-two-labs/tinyllama-moe-nord-chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("four-two-labs/tinyllama-moe-nord-chat")
model = AutoModelForCausalLM.from_pretrained("four-two-labs/tinyllama-moe-nord-chat")
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 four-two-labs/tinyllama-moe-nord-chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "four-two-labs/tinyllama-moe-nord-chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "four-two-labs/tinyllama-moe-nord-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/four-two-labs/tinyllama-moe-nord-chat

SGLang

How to use four-two-labs/tinyllama-moe-nord-chat 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 "four-two-labs/tinyllama-moe-nord-chat" \
    --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": "four-two-labs/tinyllama-moe-nord-chat",
		"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 "four-two-labs/tinyllama-moe-nord-chat" \
        --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": "four-two-labs/tinyllama-moe-nord-chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use four-two-labs/tinyllama-moe-nord-chat with Docker Model Runner:
```
docker model run hf.co/four-two-labs/tinyllama-moe-nord-chat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

See axolotl config

axolotl version: 0.4.0

base_model: four-two-labs/tinyllama-moe-nord-completion-6B

model_type: AutoModelForCausalLM
tokenizer_type: LlamaTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

rl: orpo
orpo_alpha: 0.1
remove_unused_columns: false

chat_template: chatml
datasets:
  - path: four-two-labs/nord-dpo-mix-181k-axolotl
    type: chat_template.argilla
    split: train

output_dir: ./runs/model/tinyllama-moe-orpo
dataset_prepared_path: ./runs/data/tinyllama-dpo-data

val_set_size: 0.01

sequence_len: 2048
sample_packing: false
pad_to_sequence_len: false

wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:

gradient_accumulation_steps: 1
micro_batch_size: 2
num_epochs: 3
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 3e-5

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

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

loss_watchdog_threshold: 5.0
loss_watchdog_patience: 3

warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_max_new_tokens: 128
saves_per_epoch: 1
debug:
deepspeed:
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:

runs/model/tinyllama-moe-orpo

This model is a fine-tuned version of four-two-labs/tinyllama-moe-nord-completion-6B on the None dataset.

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: 3e-05
train_batch_size: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 10
total_train_batch_size: 20
total_eval_batch_size: 80
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 10
training_steps: 27511

Training results

Framework versions

Transformers 4.40.0.dev0
Pytorch 2.1.2+cu118
Datasets 2.15.0
Tokenizers 0.15.0

Downloads last month: 5

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for four-two-labs/tinyllama-moe-nord-chat

Base model

four-two-labs/tinyllama-moe-nord-completion-6B

Finetuned

(1)

this model

Quantizations

1 model

Collection including four-two-labs/tinyllama-moe-nord-chat

TinyLlama

Collection

Fine-tunes of TinyLlama • 4 items • Updated May 12, 2024