|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- lodrick-the-lafted/Hermes-100K |
|
--- |
|
|
|
<img src=https://huggingface.co/lodrick-the-lafted/Hermes-Instruct-7B-100K/resolve/main/hermes-instruct.png> |
|
|
|
# Hermes-Instruct-7B-v0.2 |
|
|
|
[Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) trained with 100K rows of [teknium/openhermes](https://huggingface.co/datasets/teknium/openhermes), in Alpaca format. |
|
|
|
<br /> |
|
<br /> |
|
|
|
# Prompt Format |
|
|
|
Both the default Mistral-Instruct tags and Alpaca are fine, so either: |
|
``` |
|
<s>[INST] {sys_prompt} {instruction} [/INST] |
|
``` |
|
|
|
``` |
|
{sys_prompt} |
|
|
|
### Instruction: |
|
{instruction} |
|
|
|
### Response: |
|
|
|
``` |
|
The tokenizer defaults to Mistral-style. |
|
|
|
<br /> |
|
<br /> |
|
|
|
# Usage |
|
|
|
```python |
|
from transformers import AutoTokenizer |
|
import transformers |
|
import torch |
|
|
|
model = "lodrick-the-lafted/Hermes-Instruct-7B-100K" |
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model) |
|
pipeline = transformers.pipeline( |
|
"text-generation", |
|
model=model, |
|
model_kwargs={"torch_dtype": torch.bfloat16}, |
|
) |
|
|
|
messages = [{"role": "user", "content": "Give me a cooking recipe for an apple pie."}] |
|
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) |
|
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.95) |
|
print(outputs[0]["generated_text"]) |
|
``` |
|
|
|
|
