---
language:
- en
license: mit
tags:
- chatml
- mistral
- instruct
- openhermes
- economics
datasets:
- rxavier/economicus
base_model: teknium/OpenHermes-2.5-Mistral-7B
model-index:
- name: Taurus-7B-1.0
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 63.57
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 83.64
      name: normalized accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 63.5
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 50.21
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 78.14
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 59.36
      name: accuracy
    source:
      url: https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=rxavier/Taurus-7B-1.0
      name: Open LLM Leaderboard
---

# Taurus 7B 1.0

![image/png](https://i.ibb.co/dGZ50jy/00003-4001299986.png)

## Description

Taurus is an [OpenHermes 2.5](https://huggingface.co./teknium/OpenHermes-2.5-Mistral-7B) finetune using the [Economicus dataset](https://huggingface.co./datasets/rxavier/economicus), an instruct dataset synthetically generated from Economics PhD textbooks.

The model was trained for 2 epochs (QLoRA) using [axolotl](https://github.com/OpenAccess-AI-Collective/axolotl). The exact config I used can be found [here](https://huggingface.co./rxavier/Taurus-1.0-Mistral-7B/tree/main/axolotl).

## Prompt format

Taurus uses **ChatML**.

```
<|im_start|>system
System message
<|im_start|>user
User message<|im_end|>
<|im_start|>assistant
```

## Usage

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GeneratorConfig


model_id = "rxavier/Taurus-7B-1.0"
model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
)
tokenizer = AutoTokenizer.from_pretrained(model_path)
generation_config = GenerationConfig(
                bos_token_id=tok.bos_token_id,
                eos_token_id=tok.eos_token_id,
                pad_token_id=tok.pad_token_id,
            )

prompt = "Give me latex formulas for extended euler equations"
system_message = "You are an expert in economics with PhD level knowledge. You are helpful, give thorough and clear explanations, and use equations and formulas where needed."

messages = [{"role": "system",
             "content": system_message},
            {"role": "user",
             "content": prompt}]
tokens = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to("cuda")

with torch.no_grad():
    outputs = model.generate(inputs=tokens, generation_config=generation_config)
print(tokenizer.decode(outputs["sequences"].cpu().tolist()[0]))
```

## GGUF quants

You can find GGUF quants for llama.cpp [here](https://huggingface.co./rxavier/Taurus-7B-1.0-GGUF).
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co./datasets/open-llm-leaderboard/details_rxavier__Taurus-7B-1.0)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |66.40|
|AI2 Reasoning Challenge (25-Shot)|63.57|
|HellaSwag (10-Shot)              |83.64|
|MMLU (5-Shot)                    |63.50|
|TruthfulQA (0-shot)              |50.21|
|Winogrande (5-shot)              |78.14|
|GSM8k (5-shot)                   |59.36|