Instructions to use Nethermind/Mpt-Instruct-DotNet-XS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nethermind/Mpt-Instruct-DotNet-XS with Transformers:

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

pipe = pipeline("text-generation", model="Nethermind/Mpt-Instruct-DotNet-XS", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Nethermind/Mpt-Instruct-DotNet-XS", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nethermind/Mpt-Instruct-DotNet-XS with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Nethermind/Mpt-Instruct-DotNet-XS

SGLang

How to use Nethermind/Mpt-Instruct-DotNet-XS 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 "Nethermind/Mpt-Instruct-DotNet-XS" \
    --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": "Nethermind/Mpt-Instruct-DotNet-XS",
		"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 "Nethermind/Mpt-Instruct-DotNet-XS" \
        --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": "Nethermind/Mpt-Instruct-DotNet-XS",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Nethermind/Mpt-Instruct-DotNet-XS with Docker Model Runner:
```
docker model run hf.co/Nethermind/Mpt-Instruct-DotNet-XS
```

Kabumbus commited on Sep 11, 2023

Commit

56d7c99

1 Parent(s): 59929e0

GGML models that can run f16 41.68 ms per token and q8 23.76 ms per token giving good results

Browse files

Files changed (2) hide show

ggml-model-f16.bin +3 -0
ggml-model-q8_0.bin +3 -0

ggml-model-f16.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b12534933201810c5cc5b6eb033f07ff6232e03f1b3cc4820b0e18566d113f3e
+size 2623816724

ggml-model-q8_0.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4af6467cf42a8e5341c471fe0b370e5d038e521877b4612284c3ce8abbd26f4a
+size 1394525204