Hermes-Instruct-7B-v0.2/README.md

license, datasets, model-index

license	datasets	model-index
apache-2.0	lodrick-the-lafted/Hermes-40K	name results Hermes-Instruct-7B-v0.2 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 60.92 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 82.96 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 60.05 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 61.01 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 76.87 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 41.09 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=lodrick-the-lafted/Hermes-Instruct-7B-v0.2 Open LLM Leaderboard

Hermes-Instruct-7B-v0.2

Mistral-7B-Instruct-v0.2 trained with some of teknium/openhermes, in Alpaca format.

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.

Usage

from transformers import AutoTokenizer
import transformers
import torch

model = "lodrick-the-lafted/Hermes-Instruct-7B-v0.2"

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"])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	63.82
AI2 Reasoning Challenge (25-Shot)	60.92
HellaSwag (10-Shot)	82.96
MMLU (5-Shot)	60.05
TruthfulQA (0-shot)	61.01
Winogrande (5-shot)	76.87
GSM8k (5-shot)	41.09