Instructions to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code with Transformers:

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

pipe = pipeline("text-generation", model="taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code")
model = AutoModelForMultimodalLM.from_pretrained("taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code")
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 Settings

vLLM

How to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code

SGLang

How to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code 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 "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code" \
    --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": "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code",
		"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 "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code" \
        --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": "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code",
    max_seq_length=2048,
)

Docker Model Runner
How to use taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code with Docker Model Runner:
```
docker model run hf.co/taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code
```

deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code / README.md

taoki

Upload tokenizer

aaad939 verified over 2 years ago

preview code

Raw

History Blame Contribute Delete

2.72 kB

metadata

language:
  - ja
license: other
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - trl
  - deepseek
datasets:
  - kunishou/amenokaku-code-instruct
license_name: deepseek
base_model: deepseek-ai/deepseek-coder-7b-instruct-v1.5

Uploaded model

Developed by: taoki
License: deepseek
Finetuned from model : deepseek-ai/deepseek-coder-7b-instruct-v1.5

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

tokenizer = AutoTokenizer.from_pretrained(
  "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code"
)
model = AutoModelForCausalLM.from_pretrained(
  "taoki/deepseek-coder-7b-instruct-v1.5-qlora-amenokaku-code"
)

if torch.cuda.is_available():
    model = model.to("cuda")

prompt="""You are an AI programming assistant, utilizing the DeepSeek Coder model, developed by DeepSeek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
### Instruction:
OpenCVを用いて定点カメラから画像を保存するコードを示してください。
### Response:
"""

input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **input_ids,
    max_new_tokens=256,
    do_sample=True,
    top_p=0.9,
    temperature=0.2,
    repetition_penalty=1.1,
)
print(tokenizer.decode(outputs[0]))

Output

<｜begin▁of▁sentence｜>You are an AI programming assistant, utilizing the DeepSeek Coder model, developed by DeepSeek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.
### Instruction:
OpenCVを用いて定点カメラから画像を保存するコードを示してください。
### Response:
```python
import cv2
cap = cv2.VideoCapture(0) # カメラの設定
fourcc = cv2.VideoWriter_fourcc(*'XVID') # 動画の形式
out = cv2.VideoWriter('output.avi', fourcc, 20.0, (640, 480)) # 出力先、fps、解像度
while True:
    ret, frame = cap.read() # 映像読み込み
    if not ret: break
    out.write(frame) # 書き込み
    cv2.imshow('Frame', frame) # 表示
    if cv2.waitKey(1) & 0xFF == ord('q'): # qで終了
        break
cap.release()
cv2.destroyAllWindows()
```
<|EOT|>

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.