Instructions to use ruslandev/llama-3-70b-tagengo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ruslandev/llama-3-70b-tagengo with Transformers:

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

pipe = pipeline("text-generation", model="ruslandev/llama-3-70b-tagengo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ruslandev/llama-3-70b-tagengo")
model = AutoModelForCausalLM.from_pretrained("ruslandev/llama-3-70b-tagengo")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ruslandev/llama-3-70b-tagengo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ruslandev/llama-3-70b-tagengo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ruslandev/llama-3-70b-tagengo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ruslandev/llama-3-70b-tagengo

SGLang

How to use ruslandev/llama-3-70b-tagengo 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 "ruslandev/llama-3-70b-tagengo" \
    --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": "ruslandev/llama-3-70b-tagengo",
		"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 "ruslandev/llama-3-70b-tagengo" \
        --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": "ruslandev/llama-3-70b-tagengo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use ruslandev/llama-3-70b-tagengo with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ruslandev/llama-3-70b-tagengo to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for ruslandev/llama-3-70b-tagengo to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ruslandev/llama-3-70b-tagengo to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="ruslandev/llama-3-70b-tagengo",
    max_seq_length=2048,
)

Docker Model Runner
How to use ruslandev/llama-3-70b-tagengo with Docker Model Runner:
```
docker model run hf.co/ruslandev/llama-3-70b-tagengo
```

Uploaded model

Developed by: ruslandev
License: apache-2.0
Finetuned from model : unsloth/llama-3-70b-bnb-4bit

This model is finetuned on the Tagengo dataset. Please note - this model has been created for educational purposes and it needs further training/fine tuning.

How to use

The easiest way to use this model on your own computer is to use the GGUF version of this model (ruslandev/llama-3-70b-tagengo-GGUF) using a program such as llama.cpp. If you want to use this model directly with the Huggingface Transformers stack, I recommend using my framework gptchain.

git clone https://github.com/RuslanPeresy/gptchain.git
cd gptchain
pip install -r requirements-train.txt
python gptchain.py chat -m ruslandev/llama-3-70b-tagengo \
    --chatml true \
    -q '[{"from": "human", "value": "Из чего состоит нейронная сеть?"}]'

Training

gptchain framework has been used for training.

python gptchain.py train -m unsloth/llama-3-70b-bnb-4bit \
    -dn tagengo_gpt4 \
    -sp checkpoints/llama-3-70b-tagengo \
    -hf llama-3-70b-tagengo \
    --max-steps 2400

Training hyperparameters

learning_rate: 2e-4
seed: 3407
gradient_accumulation_steps: 4
per_device_train_batch_size: 2
optimizer: adamw_8bit
lr_scheduler_type: linear
warmup_steps: 5
max_steps: 2400
weight_decay: 0.01

Training results

wandb report

2400 steps took 7 hours on a single H100

Downloads last month: 4

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for ruslandev/llama-3-70b-tagengo

Base model

unsloth/llama-3-70b-bnb-4bit

Finetuned

(20)

this model

ruslandev
/

llama-3-70b-tagengo