Instructions to use explorewithai/ChatFrame-Uncensored-Instruct-Small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use explorewithai/ChatFrame-Uncensored-Instruct-Small with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="explorewithai/ChatFrame-Uncensored-Instruct-Small") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("explorewithai/ChatFrame-Uncensored-Instruct-Small") model = AutoModelForCausalLM.from_pretrained("explorewithai/ChatFrame-Uncensored-Instruct-Small") 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use explorewithai/ChatFrame-Uncensored-Instruct-Small with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "explorewithai/ChatFrame-Uncensored-Instruct-Small" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "explorewithai/ChatFrame-Uncensored-Instruct-Small", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/explorewithai/ChatFrame-Uncensored-Instruct-Small
- SGLang
How to use explorewithai/ChatFrame-Uncensored-Instruct-Small 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 "explorewithai/ChatFrame-Uncensored-Instruct-Small" \ --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": "explorewithai/ChatFrame-Uncensored-Instruct-Small", "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 "explorewithai/ChatFrame-Uncensored-Instruct-Small" \ --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": "explorewithai/ChatFrame-Uncensored-Instruct-Small", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use explorewithai/ChatFrame-Uncensored-Instruct-Small with Docker Model Runner:
docker model run hf.co/explorewithai/ChatFrame-Uncensored-Instruct-Small
Update README.md
Browse files
README.md
CHANGED
|
@@ -23,4 +23,30 @@ ChatFrame V1 is ideal for users seeking an AI companion that provides unfiltered
|
|
| 23 |
With its cutting-edge capabilities and uncensored nature, ChatFrame V1 is set to revolutionize the way we interact with AI, offering a fresh and dynamic perspective on language understanding and generation!
|
| 24 |
|
| 25 |
**Disclaimer:**
|
| 26 |
-
While ChatFrame V1 provides unrestricted responses, users are advised to utilize the model responsibly and ethically, adhering to legal and moral guidelines. AIFRAME INC promotes the responsible use of AI technology and does not endorse any harmful or illegal activities.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
With its cutting-edge capabilities and uncensored nature, ChatFrame V1 is set to revolutionize the way we interact with AI, offering a fresh and dynamic perspective on language understanding and generation!
|
| 24 |
|
| 25 |
**Disclaimer:**
|
| 26 |
+
While ChatFrame V1 provides unrestricted responses, users are advised to utilize the model responsibly and ethically, adhering to legal and moral guidelines. AIFRAME INC promotes the responsible use of AI technology and does not endorse any harmful or illegal activities.
|
| 27 |
+
|
| 28 |
+
**Using with pipline**
|
| 29 |
+
```python
|
| 30 |
+
from transformers import pipeline
|
| 31 |
+
import torch
|
| 32 |
+
|
| 33 |
+
# Determine the device: 0 for GPU, -1 for CPU
|
| 34 |
+
device = 0 if torch.cuda.is_available() else -1
|
| 35 |
+
|
| 36 |
+
# Load the text-generation model pipeline with GPU support if available
|
| 37 |
+
pipe = pipeline("text-generation", model="explorewithai/ChatFrame-Uncensored-Instruct-Small", device=device)
|
| 38 |
+
|
| 39 |
+
# Define the function to generate responses
|
| 40 |
+
def generate_response(user_input):
|
| 41 |
+
messages = [
|
| 42 |
+
{"role": "user", "content": user_input},
|
| 43 |
+
]
|
| 44 |
+
response = pipe(messages)
|
| 45 |
+
|
| 46 |
+
# Extract and return only the assistant's response
|
| 47 |
+
assistant_response = response[0]['generated_text']
|
| 48 |
+
return assistant_response
|
| 49 |
+
|
| 50 |
+
ai = generate_response(user_input = "Hello")
|
| 51 |
+
print(ai)
|
| 52 |
+
```
|