prabureddy_-_Mental-Health-FineTuned-Mistral-7B-Instruct-v0.2-8bits

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Mental-Health-FineTuned-Mistral-7B-Instruct-v0.2 - bnb 8bits

• Model creator: https://huggingface.co/prabureddy/
• Original model: https://huggingface.co/prabureddy/Mental-Health-FineTuned-Mistral-7B-Instruct-v0.2/

Original model description:

library_name: transformers license: apache-2.0 tags:

• autotrain
• text-generation-inference
• text-generation
• peft
• generated_from_trainer
• mistral
• transformers
• Inference Endpoints
• pytorch base_model: mistralai/Mistral-7B-Instruct-v0.2 model-index:
• name: Mental-Health_ML results: [] datasets:
• Amod/mental_health_counseling_conversations inference: true widget:
• messages:
  • role: user content: What is your favorite condiment?

---

Model Trained Using AutoTrain

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the mental_health_counseling_conversations dataset.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = "prabureddy/Mental-Health-FineTuned-Mistral-7B-Instruct-v0.2"

tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    device_map="auto",
    torch_dtype='auto'
).eval()

# Prompt content: "hi"
messages = [
    {"role": "user", "content": "Hey Alex! I have been feeling a bit down lately.I could really use some advice on how to feel better?"}
]

input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
output_ids = model.generate(input_ids.to('cuda'))
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)

# Model response: "Hello! How can I assist you today?"
print(response)