|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
pipeline_tag: text-generation |
|
tags: |
|
- serialization |
|
--- |
|
![image/png](https://cdn-uploads.huggingface.co/production/uploads/63fe1a380c1bbe8e29d3c401/lLSAHJVQKuEqKCgFIMEsY.png) |
|
|
|
|
|
# Model Card for Neural-Zephyr Mistral 14B |
|
|
|
Intel and Hugging Face developed two of the most prominent Mistral-type models released: Neural-Chat and Zephyr. |
|
|
|
Neural-Zephyr is a hybrid Transfer Learning version joining Neural-Chat weights and Zephyr Mistral type models. The weights are aggregated in the same layers, summing up 14B parameters. |
|
|
|
Zephyr is a series of language models that are trained to act as helpful assistants. |
|
Zephyr-7B-β is the second model in the series, and is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
|
that was trained on a mix of publicly available, synthetic datasets using [Direct Preference Optimization (DPO)](https://arxiv.org/abs/2305.18290). |
|
and made the model more helpful. However, this means that model is likely to generate problematic text when prompted to do so. |
|
You can find more details in the [technical report](https://arxiv.org/abs/2310.16944). |
|
|
|
|
|
## Model description |
|
|
|
- **Model type:** A 14B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. |
|
- **Language(s) (NLP):** Primarily English |
|
- **License:** MIT |
|
- **Finetuned from model:** [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) |
|
|
|
|
|
# Use in Transformers |
|
## Load model directly |
|
import torch |
|
from transformers import AutoTokenizer, AutoModelForCausalLM, MistralForCausalLM |
|
|
|
model = MistralForCausalLM.from_pretrained("ai-agi/neural-zephyr", use_cache=False, torch_dtype=torch.bfloat16, device_map="auto") |
|
state_dict = torch.load('model_weights.pth') |
|
model.load_state_dict(state_dict) |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("ai-agi/neural-zephyr", use_fast=True) |
|
if tokenizer.pad_token is None: |
|
tokenizer.pad_token = tokenizer.eos_token) |
|
|
|
|