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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nethermind/Mpt-Instruct-DotNet-S", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Nethermind/Mpt-Instruct-DotNet-S", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

Mpt-Instruct-DotNet-S / README.md

Kabumbus

Update README.md

5eda52c almost 3 years ago

preview code

Raw

History Blame Contribute Delete

3.36 kB

	---
	license: cc-by-sa-3.0
	language:
	- en
	pipeline_tag: text-generation
	tags:
	- csharp
	- mpt
	- instruct
	- 7b
	- llm
	- .net
	---

	## Try it

	### C#
	Code for [use form .Net CSharp on CPU](https://github.com/NethermindEth/Mpt-Instruct-DotNet-S) that runs on Windows, Mac M and Linux

	### Python
	```python
	import torch
	import transformers
	from transformers import AutoTokenizer

	tokenizer = AutoTokenizer.from_pretrained("EleutherAI/gpt-neox-20b")
	tokenizer.pad_token = tokenizer.eos_token

	device = torch.device("cuda")
	model_name = "Nethermind/Mpt-Instruct-DotNet-S"
	config = transformers.AutoConfig.from_pretrained(model_name, trust_remote_code=True)
	config.init_device = device
	config.max_seq_len = 1024
	config.attn_config['attn_impl'] = 'torch'
	config.use_cache = False

	model = transformers.AutoModelForCausalLM.from_pretrained(
	model_name,
	config=config,
	torch_dtype=torch.bfloat16,
	trust_remote_code=True,
	ignore_mismatched_sizes=True,
	# load_in_8bit=True # when low on GPU memory
	)
	model.eval()

	INSTRUCTION_KEY = "### Instruction:"
	RESPONSE_KEY = "### Response:"
	PROMPT_FOR_GENERATION_FORMAT = """{system}
	{instruction_key}
	{instruction}
	{response_key}
	""".format(
	system="{system}",
	instruction_key=INSTRUCTION_KEY,
	instruction="{instruction}",
	response_key=RESPONSE_KEY
	)

	def give_answer(instruction="Create a loop over [0, 6, 7 , 77] that prints its contentrs", system="You are an experienced .Net C# developer. Below is an instruction that describes a task. Write a response that completes the request providing detailed explanations with code examples.", ):
	question = PROMPT_FOR_GENERATION_FORMAT.format(system=system, instruction=instruction)
	input_tokens = tokenizer.encode(question ,return_tensors='pt')
	model.generate(input_tokens.to(device), max_new_tokens=min(512, 1024 - input_tokens.shape[1]), do_sample=False, top_k=1, top_p=0.95)
	outputs = output_loop(tokenized_question)
	answer = tokenizer.batch_decode(outputs, skip_special_tokens=True)
	print(answer[0])

	```


	## Training
	Finetuned for CSharp [mosaicml/mpt-7b-instruct](https://huggingface.co/mosaicml/mpt-7b-instruct). Max context length is restricted to 1024 tokens.

	- 'Loss': 0.256045166015625 on 300k CSharp-related records
	- 'Loss': 0.095714599609375 on 50k specific short prompts

	## Sources
	data contained (most data was around 500 tokens long < 1000, except large code files):
	- codeparrot/github-code C# ("mit", "Apache-2.0", "Bsd-3-clause", "Bsd-2-clause", "Cc0-1.0", "Unlicense", "isc")
	- raw data Plain .cs files randomly cut at the 60-80% in the instruction, and we ask the network to continue last 40-20% (76k)
	- documented static functions 72k
	- SO 5q_5answer + 5q_5best (CC BY-SA 4.0) 70k
	- Dotnet wiki (30k, rendered out from [github repo](https://github.com/microsoft/dotnet), see also removed, GPT-4 generated short question to each file)
	- All NM Static Functions and Tests (from [nethermind client repo](https://github.com/NethermindEth/nethermind) documented and described via GPT-4 (4k)
	- GPT-4 questions, GPT-3.5 answers for CSharp: Short Q->Code, Explain Code X > Step-By-Step (35k)
	- GPT-4 questions, GPT-3.5 answers for nethermind client interface `IEthRpcModule `: Short Q->Code, Explain Code X -> Step-By-Step (7k)

	## Contents
	- HF compatible model
	- GGML compatible quantisations (f16, q8, q5)