Instructions to use diegi97/dolly-v2-6.9b-sharded-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diegi97/dolly-v2-6.9b-sharded-bf16 with Transformers:

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

pipe = pipeline("text-generation", model="diegi97/dolly-v2-6.9b-sharded-bf16")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("diegi97/dolly-v2-6.9b-sharded-bf16")
model = AutoModelForCausalLM.from_pretrained("diegi97/dolly-v2-6.9b-sharded-bf16")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use diegi97/dolly-v2-6.9b-sharded-bf16 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diegi97/dolly-v2-6.9b-sharded-bf16"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diegi97/dolly-v2-6.9b-sharded-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/diegi97/dolly-v2-6.9b-sharded-bf16

SGLang

How to use diegi97/dolly-v2-6.9b-sharded-bf16 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 "diegi97/dolly-v2-6.9b-sharded-bf16" \
    --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": "diegi97/dolly-v2-6.9b-sharded-bf16",
		"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 "diegi97/dolly-v2-6.9b-sharded-bf16" \
        --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": "diegi97/dolly-v2-6.9b-sharded-bf16",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use diegi97/dolly-v2-6.9b-sharded-bf16 with Docker Model Runner:
```
docker model run hf.co/diegi97/dolly-v2-6.9b-sharded-bf16
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

The Dolly v2 model but sharded to reduce the CPU memory required to load it on the GPU and also reduce the load time. By sharding it you don't need to load the full model on the CPU RAM before sending it to the GPU, just load it shard by shard.

Downloads last month: 5

Model tree for diegi97/dolly-v2-6.9b-sharded-bf16

Adapters

4 models

diegi97
/

dolly-v2-6.9b-sharded-bf16

Model tree for diegi97/dolly-v2-6.9b-sharded-bf16

Space using diegi97/dolly-v2-6.9b-sharded-bf16 1