Instructions to use TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ

SGLang

How to use TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ 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 "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ with Docker Model Runner:
```
docker model run hf.co/TechxGenus/DeepSeek-Coder-V2-Lite-Instruct-AWQ
```

DeepSeek-Coder-V2-Lite-Instruct-AWQ / tokenization_deepseek_fast.py

TechxGenus

Upload folder using huggingface_hub

1cb23ed verified almost 2 years ago

raw

history blame contribute delete

1.37 kB

	from typing import List, Optional, Union


	from transformers.models.llama import LlamaTokenizerFast


	class DeepseekTokenizerFast(LlamaTokenizerFast):

	def convert_ids_to_tokens(
	self, ids: Union[int, List[int]], skip_special_tokens: bool = False
	) -> Union[str, List[str]]:
	"""
	Converts a single index or a sequence of indices in a token or a sequence of tokens, using the vocabulary and
	added tokens.

	Args:
	ids (`int` or `List[int]`):
	The token id (or token ids) to convert to tokens.
	skip_special_tokens (`bool`, optional, defaults to `False`):
	Whether or not to remove special tokens in the decoding.

	Returns:
	`str` or `List[str]`: The decoded token(s).
	"""
	if isinstance(ids, int):
	return self._convert_id_to_token(ids)
	tokens = []
	for index in ids:
	index = int(index)
	if skip_special_tokens and index in self.all_special_ids:
	continue
	token = self._tokenizer.id_to_token(index)
	tokens.append(token if token is not None else "")
	return tokens

	def _convert_id_to_token(self, index: int) -> Optional[str]:
	token = self._tokenizer.id_to_token(int(index))
	return token if token is not None else ""