hf_mirrors/Panda-7B-v0.1
Model Introduction
Files & versions
Analysis

Neural-Story

NeuralNovel/Panda-7B-v0.1

The Panda-7B-v0.1 model by NeuralNovel.

This fine-tune has been designed to provide detailed, creative and logical responses in the context of diverse narratives. Optimised for creative writing, roleplay and logical problem solving.

Full-parameter fine-tune (FFT) of Mistral-7B-Instruct-v0.2. Apache-2.0 license, suitable for commercial or non-commercial use.

Use with openMind

environment variable

# source environment variable
source /usr/local/Ascend/ascend-toolkit/set_env.sh
export OPENMIND_FRAMEWORK=pt

pip install openMind Library

OpenMind Library can be installed through pip, please select the corresponding command according to the actual environment for installation.

It should be noted that since torch npu depends on torch, which can be directly installed through pip in aarch64, but requires a specific URL to download the CPU version in x86, the installation commands in the two environments are different. The specific installation code has been distinguished and presented in the following text.

# aarch64
pip install openmind[all]
# x86
pip install openmind[all] --extra-index-url https://download.pytorch.org/whl/cpu

Inference

from openmind import AutoTokenizer, AutoModelForCausalLM
import torch
import torch_npu

model_dir = "HangZhou_Ascend/Panda-7B-v0.1"
tokenizer = AutoTokenizer.from_pretrained(model_dir, device_map="auto", trust_remote_code=True)
# Set `torch_dtype=torch.float16` to load model in float16, otherwise it will be loaded as float32 and might cause OOM Error.
model = AutoModelForCausalLM.from_pretrained(model_dir, device_map="auto",  trust_remote_code=True, torch_dtype=torch.float16)
model = model.eval()
response, history = model.chat(tokenizer, "1+1=", history=[], meta_instruction="")
print(response)

Data-set

The model on finetuned using the Panda-v1 dataset.

Summary

Fine-tuned with the intention to generate instructive and narrative text, with a specific focus on combining the elements of versatility, character engagement and nuanced writing capability.

Out-of-Scope Use

The model may not perform well in scenarios unrelated to instructive and narrative text generation. Misuse or applications outside its designed scope may result in suboptimal outcomes.

Bias, Risks, and Limitations

The model may exhibit biases or limitations inherent in the training data. It is essential to consider these factors when deploying the model to avoid unintended consequences.

Users are advised to exercise caution, as there might be some inherent genre or writing bias.

Hardware and Training


  n_epochs = 3,
  n_checkpoints = 3,
  batch_size = 12,
  learning_rate = 1e-5,


Sincere appreciation to Techmind for their generous sponsorship.