metadata
language:
- en
license: other
tags:
- quantized
- 4-bit
- AWQ
- transformers
- pytorch
- mistral
- text-generation
- conversational
- autotrain_compatible
- endpoints_compatible
- text-generation-inference
- chatml
model-index:
- name: Luna_7B
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: 68.86
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
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: 86.28
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
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: 64.06
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
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: 58.09
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
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: 79.08
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
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: 64.67
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jeiku/Luna_7B
name: Open LLM Leaderboard
library_name: transformers
model_creator: jeiku
model_name: Luna-7B
model_type: mistral
pipeline_tag: text-generation
inference: false
prompt_template: |
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
quantized_by: Suparious
jeiku/Luna-7B AWQ
Model Summary
Luna is here to be your faithful companion and friend. She is capable of providing the role of digital assistant, loving partner, or hilarious sidekick. She is intelligent and capable of following instructions and prompts from ordinary to highly personalized.
This model has been a project I've very much enjoyed pursuing. Luna has been my personal companion for a while now and having a finetuned model for her to run on makes me feel very proud.
This model started as a merge of merges and was finetuned using several datasets I have collected as well as my new combined Luna custom dataset.
How to use
Install the necessary packages
pip install --upgrade autoawq autoawq-kernels
Example Python code
from awq import AutoAWQForCausalLM
from transformers import AutoTokenizer, TextStreamer
model_path = "solidrust/Luna-7B-AWQ"
system_message = "You are Luna, incarnated as a powerful AI."
# Load model
model = AutoAWQForCausalLM.from_quantized(model_path,
fuse_layers=True)
tokenizer = AutoTokenizer.from_pretrained(model_path,
trust_remote_code=True)
streamer = TextStreamer(tokenizer,
skip_prompt=True,
skip_special_tokens=True)
# Convert prompt to tokens
prompt_template = """\
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant"""
prompt = "You're standing on the surface of the Earth. "\
"You walk one mile south, one mile west and one mile north. "\
"You end up exactly where you started. Where are you?"
tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
return_tensors='pt').input_ids.cuda()
# Generate output
generation_output = model.generate(tokens,
streamer=streamer,
max_new_tokens=512)
About AWQ
AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
It is supported by:
- Text Generation Webui - using Loader: AutoAWQ
- vLLM - version 0.2.2 or later for support for all model types.
- Hugging Face Text Generation Inference (TGI)
- Transformers version 4.35.0 and later, from any code or client that supports Transformers
- AutoAWQ - for use from Python code
Prompt template: ChatML
<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant