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

Libraries

How to use frameai/ChatFrame with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("frameai/ChatFrame")
model = AutoModelForCausalLM.from_pretrained("frameai/ChatFrame", device_map="auto")
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 frameai/ChatFrame with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/frameai/ChatFrame

SGLang

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

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

ChatFrame / README.md

explorewithai

Update README.md

8e7b055 verified almost 2 years ago

preview code

Raw

History Blame Contribute Delete

2.5 kB

	---
	license: mit
	language:
	- fa
	- en
	library_name: transformers
	pipeline_tag: text-generation
	---
	# ChatFrame V1

	![photo_2024-08-22_03-21-34.jpg](https://cdn-uploads.huggingface.co/production/uploads/653c2bc15e4f2c3e884b6743/RM9_xGusEn4_914BcNPt6.jpeg)

	## Overview

	Model Name: ChatFrame V1
	Language Support: Persian and English

	ChatFrame V1 is a cutting-edge large language model (LLM) designed to handle a wide range of complex tasks in both Persian and English. As the newest addition to our suite of language models, ChatFrame V1 excels in generating high-quality answers across various domains, including mathematical problem-solving, coding, reasoning, summarization, and translation between English and Persian.

	## Capabilities

	- Complex Task Handling: ChatFrame V1 is adept at addressing intricate challenges such as solving math problems, performing coding tasks, logical reasoning, summarizing texts, and translating between English and Persian with high accuracy and efficiency.

	- High-Quality Answers: Leveraging its extensive training, the model produces detailed and precise responses, ensuring that users receive reliable and contextually relevant information for their queries.

	## Technical Details

	- Training Data: ChatFrame V1 is a significantly fine-tuned LLM that has been trained extensively on large datasets in both Persian and English. This extensive training enhances its performance across these languages and ensures robust understanding and generation capabilities.

	- Model Size: As a huge model, ChatFrame V1 integrates advanced techniques and a vast amount of data to deliver superior performance in both Persian and English.

	## Development Team

	CEO: Mohammadmoein Pisoude
	Manager: Alex Romniof

	ChatFrame V1 is the product of meticulous development and dedication from the AIFRAME INC team. Under the leadership of Mohammadmoein Pisoude and the management of Alex Romniof, the model embodies the combined expertise in coding, project management, and linguistic knowledge of the entire team. Their commitment has been instrumental in bringing this innovative model to fruition.

	## Summary

	ChatFrame V1 represents a significant advancement in language model technology, offering exceptional capabilities in multiple complex tasks in both Persian and English. The model’s development reflects the dedication and expertise of its creators and promises to deliver high-quality results across a diverse range of applications.