Instructions to use h2oai/h2ogpt-32k-codellama-34b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h2oai/h2ogpt-32k-codellama-34b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="h2oai/h2ogpt-32k-codellama-34b-instruct")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-32k-codellama-34b-instruct")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-32k-codellama-34b-instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use h2oai/h2ogpt-32k-codellama-34b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h2oai/h2ogpt-32k-codellama-34b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h2oai/h2ogpt-32k-codellama-34b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/h2oai/h2ogpt-32k-codellama-34b-instruct

SGLang

How to use h2oai/h2ogpt-32k-codellama-34b-instruct 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 "h2oai/h2ogpt-32k-codellama-34b-instruct" \
    --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": "h2oai/h2ogpt-32k-codellama-34b-instruct",
		"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 "h2oai/h2ogpt-32k-codellama-34b-instruct" \
        --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": "h2oai/h2ogpt-32k-codellama-34b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use h2oai/h2ogpt-32k-codellama-34b-instruct with Docker Model Runner:
```
docker model run hf.co/h2oai/h2ogpt-32k-codellama-34b-instruct
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Same as h2oai/h2ogpt-16k-codellama-34b-instruct but with config.json modified to be 32k for embeddings, which still functions fine as 16k model and allows stretching into 32k in vLLM that otherwise cannot modify maximum sequence length.

Downloads last month: 28

Safetensors

Model size

34B params

Tensor type

F16

Model tree for h2oai/h2ogpt-32k-codellama-34b-instruct

Quantizations

1 model

h2oai
/

h2ogpt-32k-codellama-34b-instruct

Model tree for h2oai/h2ogpt-32k-codellama-34b-instruct

Space using h2oai/h2ogpt-32k-codellama-34b-instruct 1