Instructions to use ponoma16/CodeKobzar13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ponoma16/CodeKobzar13B with Transformers:

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

pipe = pipeline("text-generation", model="ponoma16/CodeKobzar13B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ponoma16/CodeKobzar13B")
model = AutoModelForCausalLM.from_pretrained("ponoma16/CodeKobzar13B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ponoma16/CodeKobzar13B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ponoma16/CodeKobzar13B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ponoma16/CodeKobzar13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ponoma16/CodeKobzar13B

SGLang

How to use ponoma16/CodeKobzar13B 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 "ponoma16/CodeKobzar13B" \
    --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": "ponoma16/CodeKobzar13B",
		"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 "ponoma16/CodeKobzar13B" \
        --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": "ponoma16/CodeKobzar13B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ponoma16/CodeKobzar13B with Docker Model Runner:
```
docker model run hf.co/ponoma16/CodeKobzar13B
```

CodeKobzar13B

Commit History

Jun 26

07:37
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
762a24f

Jul 5, 2024

00:10
Update README.md

ponoma16

Verified signature
0ce08c2
00:10
Update README.md

ponoma16

Verified signature
088dc8f

Feb 27, 2024

06:09
Update README.md

ponoma16

Verified signature
a02f108
05:50
Update README.md

ponoma16

Verified signature
637dbb0
05:04
Update README.md

ponoma16

Verified signature
385bdf9
05:04
Update README.md

ponoma16

Verified signature
51b51e5
05:02
Create README.md

ponoma16

Verified signature
5c4d3b3
03:49
Upload tokenizer

ponoma16

Verified signature
2ac5b4d
03:48
Upload tokenizer

ponoma16

Verified signature
8c21353
03:46
Upload tokenizer

ponoma16

Verified signature
f3f2632
03:44
Upload tokenizer

ponoma16

Verified signature
dec337d
03:43
Upload tokenizer

ponoma16

Verified signature
5197e4d
03:41
Upload tokenizer

ponoma16

Verified signature
184343e
03:01
Upload tokenizer

ponoma16

Verified signature
2243fa6
02:59
Upload LlamaForCausalLM

ponoma16

Verified signature
4393836
02:24
initial commit

ponoma16

Verified signature
6d8afe4

Commit History

Jun 26

Adding `safetensors` variant of this model⁠

Jul 5, 2024

Update README.md

Update README.md

Feb 27, 2024

Update README.md

Update README.md

Update README.md

Update README.md

Create README.md

Upload tokenizer

Upload tokenizer

Upload tokenizer

Upload tokenizer

Upload tokenizer

Upload tokenizer

Upload tokenizer

Upload LlamaForCausalLM

initial commit