Grafted-Hermetic-Platypus-D-2x7B
MoE merge of
Basically the same thing as GHP-A.
Prompt Format
Both the default Mistral-Instruct tags and Alpaca are fine, so either:
<s>[INST] {sys_prompt} {instruction} [/INST]
or
{sys_prompt}
### Instruction:
{instruction}
### Response:
The tokenizer default is Alpaca this time around.
Usage
from transformers import AutoTokenizer
import transformers
import torch
model = "lodrick-the-lafted/Grafted-Hermetic-Platypus-A-2x7B"
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 pumpkin 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"])
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 64.24 |
AI2 Reasoning Challenge (25-Shot) | 58.87 |
HellaSwag (10-Shot) | 82.89 |
MMLU (5-Shot) | 61.96 |
TruthfulQA (0-shot) | 61.02 |
Winogrande (5-shot) | 77.43 |
GSM8k (5-shot) | 43.29 |
- Downloads last month
- 75
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for lodrick-the-lafted/Grafted-Hermetic-Platypus-D-2x7B
Datasets used to train lodrick-the-lafted/Grafted-Hermetic-Platypus-D-2x7B
Evaluation results
- normalized accuracy on AI2 Reasoning Challenge (25-Shot)test set Open LLM Leaderboard58.870
- normalized accuracy on HellaSwag (10-Shot)validation set Open LLM Leaderboard82.890
- accuracy on MMLU (5-Shot)test set Open LLM Leaderboard61.960
- mc2 on TruthfulQA (0-shot)validation set Open LLM Leaderboard61.020
- accuracy on Winogrande (5-shot)validation set Open LLM Leaderboard77.430
- accuracy on GSM8k (5-shot)test set Open LLM Leaderboard43.290