Instructions to use Berkem/finetune_deepspeed_deepseek with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Berkem/finetune_deepspeed_deepseek with Transformers:

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

pipe = pipeline("text-generation", model="Berkem/finetune_deepspeed_deepseek")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Berkem/finetune_deepspeed_deepseek")
model = AutoModelForCausalLM.from_pretrained("Berkem/finetune_deepspeed_deepseek")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Berkem/finetune_deepspeed_deepseek with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Berkem/finetune_deepspeed_deepseek

SGLang

How to use Berkem/finetune_deepspeed_deepseek 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 "Berkem/finetune_deepspeed_deepseek" \
    --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": "Berkem/finetune_deepspeed_deepseek",
		"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 "Berkem/finetune_deepspeed_deepseek" \
        --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": "Berkem/finetune_deepspeed_deepseek",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Berkem/finetune_deepspeed_deepseek with Docker Model Runner:
```
docker model run hf.co/Berkem/finetune_deepspeed_deepseek
```

finetune_deepspeed_deepseek

This model is a fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.2286

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: 5e-05
train_batch_size: 1
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 4
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss
0.1482	1.0	1559	0.2420
0.0969	2.0	3118	0.2178
0.0761	3.0	4677	0.1981
0.0561	4.0	6236	0.1966
0.0469	5.0	7795	0.1977
0.0401	6.0	9354	0.1979
0.032	7.0	10913	0.2009
0.028	8.0	12472	0.2091
0.0254	9.0	14031	0.2252
0.0275	10.0	15590	0.2286

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0

Downloads last month: 4

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Berkem/finetune_deepspeed_deepseek

Base model

deepseek-ai/deepseek-coder-6.7b-instruct

Finetuned

(65)

this model