Instructions to use NExtNewChattingAI/shark_tank_ai_7b_v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NExtNewChattingAI/shark_tank_ai_7b_v2 with Transformers:

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

pipe = pipeline("text-generation", model="NExtNewChattingAI/shark_tank_ai_7b_v2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NExtNewChattingAI/shark_tank_ai_7b_v2")
model = AutoModelForCausalLM.from_pretrained("NExtNewChattingAI/shark_tank_ai_7b_v2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use NExtNewChattingAI/shark_tank_ai_7b_v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NExtNewChattingAI/shark_tank_ai_7b_v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NExtNewChattingAI/shark_tank_ai_7b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/NExtNewChattingAI/shark_tank_ai_7b_v2

SGLang

How to use NExtNewChattingAI/shark_tank_ai_7b_v2 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 "NExtNewChattingAI/shark_tank_ai_7b_v2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NExtNewChattingAI/shark_tank_ai_7b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "NExtNewChattingAI/shark_tank_ai_7b_v2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NExtNewChattingAI/shark_tank_ai_7b_v2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use NExtNewChattingAI/shark_tank_ai_7b_v2 with Docker Model Runner:
```
docker model run hf.co/NExtNewChattingAI/shark_tank_ai_7b_v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model is based on https://huggingface.co/AIDC-ai-business/Marcoroni-7B-v3 trained on internal data.

license: cc-by-nc-4.0 language: - en

Chatbot is a highly advanced artificial intelligence designed to provide you with personalized assistance and support. With its natural language processing capabilities, it can understand and respond to a wide range of queries and requests, making it a valuable tool for both personal and professional use.

The chatbot is equipped with a vast knowledge base, allowing it to provide accurate and reliable information on a wide range of topics, from general knowledge to specific industry-related information. It can also perform tasks such as scheduling appointments, sending emails, and even ordering products online.

One of the standout features of this assistant chatbot is its ability to learn and adapt to your individual preferences and needs. Over time, it can become more personalized to your specific requirements, making it an even more valuable asset to your daily life.

The chatbot is also designed to be user-friendly and intuitive, with a simple and easy-to-use interface that allows you to interact with it in a natural and conversational way. Whether you're looking for information, need help with a task, or just want to chat, your assistant chatbot is always ready and available to assist you.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	66.55
AI2 Reasoning Challenge (25-Shot)	67.75
HellaSwag (10-Shot)	87.06
MMLU (5-Shot)	58.79
TruthfulQA (0-shot)	62.15
Winogrande (5-shot)	78.45
GSM8k (5-shot)	45.11

Downloads last month: 217

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for NExtNewChattingAI/shark_tank_ai_7b_v2

Quantizations

3 models

Spaces using NExtNewChattingAI/shark_tank_ai_7b_v2 9

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

67.750
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

87.060
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

58.790
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

62.150
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

78.450
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

45.110