Instructions to use rccmsu/ruadapt_llama2_7b_v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rccmsu/ruadapt_llama2_7b_v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="rccmsu/ruadapt_llama2_7b_v0.1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rccmsu/ruadapt_llama2_7b_v0.1")
model = AutoModelForCausalLM.from_pretrained("rccmsu/ruadapt_llama2_7b_v0.1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use rccmsu/ruadapt_llama2_7b_v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rccmsu/ruadapt_llama2_7b_v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rccmsu/ruadapt_llama2_7b_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/rccmsu/ruadapt_llama2_7b_v0.1

SGLang

How to use rccmsu/ruadapt_llama2_7b_v0.1 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 "rccmsu/ruadapt_llama2_7b_v0.1" \
    --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": "rccmsu/ruadapt_llama2_7b_v0.1",
		"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 "rccmsu/ruadapt_llama2_7b_v0.1" \
        --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": "rccmsu/ruadapt_llama2_7b_v0.1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use rccmsu/ruadapt_llama2_7b_v0.1 with Docker Model Runner:
```
docker model run hf.co/rccmsu/ruadapt_llama2_7b_v0.1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ruadapt_llama2_7b_v0.1

This model is a fine-tuned (embeddings, lm head) version of TheBloke/Llama-2-7B-fp16 on the Russian dataset (33GB). It achieves the following results on the evaluation set:

Loss: 2.7569
Accuracy: 0.4617

Instruct version: https://huggingface.co/rccmsu/ruadapt_saiga2_7b_v0.1

Model description

Russian adaptation of LLaMa-2-7B by replacing the tokenizer. Paper: Tikhomirov M., Chernyshev D. Impact of Tokenization on LLaMa Russian Adaptation //arXiv preprint arXiv:2312.02598. – 2023.

Intended uses & limitations

LLAMA 2 COMMUNITY LICENSE AGREEMENT

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 6
eval_batch_size: 6
seed: 42
distributed_type: multi-GPU
num_devices: 16
gradient_accumulation_steps: 2
total_train_batch_size: 192
total_eval_batch_size: 96
optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
lr_scheduler_type: linear
num_epochs: 2.0

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1

Downloads last month: 10

Model tree for rccmsu/ruadapt_llama2_7b_v0.1

Quantizations

1 model

Space using rccmsu/ruadapt_llama2_7b_v0.1 1

Paper for rccmsu/ruadapt_llama2_7b_v0.1

Impact of Tokenization on LLaMa Russian Adaptation

Paper • 2312.02598 • Published Dec 5, 2023 • 7