Instructions to use MadKFC/CPsyCode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MadKFC/CPsyCode with Transformers:

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

pipe = pipeline("text-generation", model="MadKFC/CPsyCode")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("MadKFC/CPsyCode", device_map="auto")

PEFT
How to use MadKFC/CPsyCode with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MadKFC/CPsyCode with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/MadKFC/CPsyCode

SGLang

How to use MadKFC/CPsyCode 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 "MadKFC/CPsyCode" \
    --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": "MadKFC/CPsyCode",
		"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 "MadKFC/CPsyCode" \
        --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": "MadKFC/CPsyCode",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MadKFC/CPsyCode with Docker Model Runner:
```
docker model run hf.co/MadKFC/CPsyCode
```

CPsyCode / README.md

MadKFC

Update README.md

409d939 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

1.4 kB

	---
	tags:
	- autotrain
	- text-generation-inference
	- text-generation
	- peft
	library_name: transformers
	base_model: meta-llama/Meta-Llama-3-8B-Instruct
	widget:
	- messages:
	- role: user
	content: What is your favorite condiment?
	license: other
	---

	# Model Trained Using AutoTrain

	This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).

	# Usage

	```python

	from transformers import pipeline

	pipe = pipeline("text-generation", "MadKFC/CPsyCode",device_map="auto")

	messages = [
	{"role": "user", "content": "I'm stupid!"},
	{'role': "assistant", "content": "I'm so sorry to hear you're feeling that way! It's completely normal to have moments where we doubt ourselves or feel uncertain. But here's the thing: being 'stupid' is not a fact, it's an opinion. And opinions are subjective and can be influenced by many factors, including our own self-talk and the opinions of other\n\ns.You are not stupid. You are capable, unique, and deserving of kindness and compassion - from yourself and others. It's okay to make mistakes, and it's okay to not know something. That's how we learn and grow!\n\nWould you like to talk about what's going on"},
	{"role": "user", "content": "I make a big mistake in the lab"},
	]

	answer = pipe(messages)

	# Print the assistant's response
	print(answer[0]['generated_text'][-1])
	```