Hugging Face's logo

thesven
/
microsoft_WizardLM-2-7B-GPTQ-98k

Text Generation
Transformers
Safetensors
mistral
conversational
text-generation-inference
Inference Endpoints
4-bit precision
gptq
Model card Files Community
microsoft_WizardLM-2-7B-GPTQ-98k / README.md
thesven's picture
thesven
Update README.md
a52d713 verified
preview code
|
raw
history blame contribute delete
6.14 kB
metadata
license: apache-2.0

Quantization Description

This repo contains a GPTQ 4bit Quantized version of the WizardLM-2-7B model with the context expanded to 98k

Prompt Template 

### System: {system_message}
### Human: {prompt}
### Assistant:

Stop Token 

</s>

Using with transformers 

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_name_or_path = "thesven/microsoft_WizardLM-2-7B-GPTQ-98k"

tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
                                             device_map="auto",
                                             trust_remote_code=False,
                                             revision="main")
model.pad_token = model.config.eos_token_id


prompt_template=f'''
### System: You are a very creative story writer. Write a store on the following topic:
### Human: Write a story about Ai
### Assistant:
'''

input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.1, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))

Weights sourced from: lucyknada/microsoft_WizardLM-2-7B

Original Model Card

🏠 WizardLM-2 Release Blog

🤗 HF Repo •🐱 Github Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder] • 📃 [WizardMath]

👋 Join our Discord

News 🔥🔥🔥 [2024/04/15]

We introduce and opensource WizardLM-2, our next generation state-of-the-art large language models, which have improved performance on complex chat, multilingual, reasoning and agent. New family includes three cutting-edge models: WizardLM-2 8x22B, WizardLM-2 70B, and WizardLM-2 7B.

  • WizardLM-2 8x22B is our most advanced model, demonstrates highly competitive performance compared to those leading proprietary works and consistently outperforms all the existing state-of-the-art opensource models.
  • WizardLM-2 70B reaches top-tier reasoning capabilities and is the first choice in the same size.
  • WizardLM-2 7B is the fastest and achieves comparable performance with existing 10x larger opensource leading models.

For more details of WizardLM-2 please read our release blog post and upcoming paper.

Model Details

Model Capacities

MT-Bench

We also adopt the automatic MT-Bench evaluation framework based on GPT-4 proposed by lmsys to assess the performance of models. The WizardLM-2 8x22B even demonstrates highly competitive performance compared to the most advanced proprietary models. Meanwhile, WizardLM-2 7B and WizardLM-2 70B are all the top-performing models among the other leading baselines at 7B to 70B model scales.

MTBench

Human Preferences Evaluation

We carefully collected a complex and challenging set consisting of real-world instructions, which includes main requirements of humanity, such as writing, coding, math, reasoning, agent, and multilingual. We report the win:loss rate without tie:

  • WizardLM-2 8x22B is just slightly falling behind GPT-4-1106-preview, and significantly stronger than Command R Plus and GPT4-0314.
  • WizardLM-2 70B is better than GPT4-0613, Mistral-Large, and Qwen1.5-72B-Chat.
  • WizardLM-2 7B is comparable with Qwen1.5-32B-Chat, and surpasses Qwen1.5-14B-Chat and Starling-LM-7B-beta.

Win

Method Overview

We built a fully AI powered synthetic training system to train WizardLM-2 models, please refer to our blog for more details of this system.

Method

Usage

❗Note for model system prompts usage:

WizardLM-2 adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, 
detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>
USER: Who are you? ASSISTANT: I am WizardLM.</s>......

Inference WizardLM-2 Demo Script

We provide a WizardLM-2 inference demo code on our github