language:
- en
license: mit
library_name: peft
datasets:
- AtlasUnified/atlas-storyteller
metrics:
- perplexity
base_model: mistralai/Mistral-7B-v0.1
pipeline_tag: text-generation
model-index:
- name: Mistral-7B-LoreWeaver
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: 59.98
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
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: 83.29
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
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: 64.12
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
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: 42.15
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
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: 78.37
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
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: 37.68
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Reverb/Mistral-7B-LoreWeaver
name: Open LLM Leaderboard
Model Card for Model ID
Our finetuned Mistral LLM is a large language model specialized for natural language processing tasks, delivering enhanced performance for a wide array of applications, including text classification, question-answering, chatbot services, and more.
Model Details
Model Description
- Developed by: Basel Anaya, Osama Awad, Yazeed Mshayekh
- Funded by [optional]: Basel Anaya, Osama Awad, Yazeed Mshayekh
- Model type: Autoregressive Language Model
- Language(s) (NLP): English
- License: MIT License
- Finetuned from model: MistralAI's Mistral-7B
Model Sources [optional]
- Repository: [More Information Needed]
- Paper [optional]: [More Information Needed]
- Demo [optional]: [More Information Needed]
Uses
Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model.
Direct Use
Users can leverage the finetuned Mistral LLM for various NLP tasks right out-of-the-box. Simply interact with the API or load the model locally to experience superior language understanding and generation capabilities. Ideal for developers seeking rapid prototyping and deployment of conversational AI applications.
Downstream Use [optional]
Integrate the finetuned Mistral LLM effortlessly into custom applications and pipelines. Utilize the model as a starting point for further refinement, targeting industry-specific lingo, niches, or particular use cases. Seamless compatibility ensures smooth collaboration with adjacent technologies and services.
Out-of-Scope Use
Limitations exist concerning controversial topics, sensitive data, and scenarios demanding real-time responses. Users should exercise caution when deploying the model in safety-critical situations or regions with strict compliance regulations. Avoid sharing confidential or personally identifiable information with the model.
Bias, Risks, and Limitations
Address both technical and sociotechnical limitations.
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. Further recommendations include cautious assessment of ethical implications, ongoing maintenance, periodic evaluations, and responsible reporting practices.
How to Get Started with the Model
Use the code below to get started with the model.
import torch
from transformers import pipeline, AutoTokenizer
# Load the finetuned Mistral LLM
model_name = "Reverb/Mistral-7B-LoreWeaver"
tokenizer = AutoTokenizer.from_pretrained(model_name)
generator = pipeline("text-generation", model=model_name, tokenizer=tokenizer)
# Example usage
input_text = "Once upon a time,"
num_generated_tokens = 50
response = generator(input_text, max_length=num_generated_tokens, num_return_sequences=1)
print(f"Generated text:\n{response[0]['generated_text']}")
# Alternatively, for fine-grained control over the generation process
inputs = tokenizer(input_text, return_tensors="pt")
outputs = generator.generate(
inputs["input_ids"].to("cuda"),
max_length=num_generated_tokens,
num_beams=5,
early_stopping=True,
temperature=1.2,
)
generated_sentence = tokenizer.decode(outputs[0])
print(f"\nGenerated text with beam search and custom params:\n{generated_sentence}")
Training Details
Training Data
[More Information Needed]
Training Procedure
Preprocessing [optional]
[More Information Needed]
Training Hyperparameters
- Training regime: [More Information Needed]
Speeds, Sizes, Times [optional]
[More Information Needed]
Evaluation
Testing Data, Factors & Metrics
Testing Data
[More Information Needed]
Factors
[More Information Needed]
Metrics
[More Information Needed]
Results
[More Information Needed]
Summary
Model Examination [optional]
[More Information Needed]
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: [More Information Needed]
- Hours used: [More Information Needed]
- Cloud Provider: [More Information Needed]
- Compute Region: [More Information Needed]
- Carbon Emitted: [More Information Needed]
Technical Specifications [optional]
Model Architecture and Objective
[More Information Needed]
Compute Infrastructure
[More Information Needed]
Hardware
[More Information Needed]
Software
[More Information Needed]
Citation [optional]
BibTeX:
[More Information Needed]
APA:
[More Information Needed]
Glossary [optional]
[More Information Needed]
More Information [optional]
[More Information Needed]
Model Card Authors [optional]
[More Information Needed]
Model Card Contact
[More Information Needed]
Framework versions
- PEFT 0.7.1
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 60.93 |
| AI2 Reasoning Challenge (25-Shot) | 59.98 |
| HellaSwag (10-Shot) | 83.29 |
| MMLU (5-Shot) | 64.12 |
| TruthfulQA (0-shot) | 42.15 |
| Winogrande (5-shot) | 78.37 |
| GSM8k (5-shot) | 37.68 |