base_model: mediocredev/open-llama-3b-v2-instruct
inference: false
license: apache-2.0
model_creator: mediocredev
model_name: open-llama-3b-v2-instruct
pipeline_tag: text-generation
quantized_by: afrideva
tags:
- gguf
- ggml
- quantized
- q2_k
- q3_k_m
- q4_k_m
- q5_k_m
- q6_k
- q8_0
mediocredev/open-llama-3b-v2-instruct-GGUF
Quantized GGUF model files for open-llama-3b-v2-instruct from mediocredev
| Name | Quant method | Size |
|---|---|---|
| open-llama-3b-v2-instruct.fp16.gguf | fp16 | 6.85 GB |
| open-llama-3b-v2-instruct.q2_k.gguf | q2_k | 2.15 GB |
| open-llama-3b-v2-instruct.q3_k_m.gguf | q3_k_m | 2.27 GB |
| open-llama-3b-v2-instruct.q4_k_m.gguf | q4_k_m | 2.58 GB |
| open-llama-3b-v2-instruct.q5_k_m.gguf | q5_k_m | 2.76 GB |
| open-llama-3b-v2-instruct.q6_k.gguf | q6_k | 3.64 GB |
| open-llama-3b-v2-instruct.q8_0.gguf | q8_0 | 3.64 GB |
Original Model Card:
Prerequisites
In addition to pytorch and transformers, install required packages:
pip install accelerate sentencepiece
Usage
To use, copy the following script:
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch
model_id = 'mediocredev/open-llama-3b-v2-instruct'
tokenizer_id = 'mediocredev/open-llama-3b-v2-instruct'
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id)
pipeline = transformers.pipeline(
'text-generation',
model=model_id,
tokenizer=tokenizer,
torch_dtype=torch.bfloat16,
device_map='auto',
)
system_message = 'You are a helpful assistant, who always provide explanation.'
user_message = 'How many days are there in a leap year?'
prompt = f'### System:\n{system_message}<|endoftext|>\n### User:\n{user_message}<|endoftext|>\n### Assistant:\n'
response = pipeline(
prompt,
max_length=1000,
repetition_penalty=1.05,
)
response = response[0]['generated_text']
print(response)
# Assistant: A leap year has 366 days. It's an extra day added to the calendar every four years to account for the extra time it takes for Earth to complete one full orbit around the Sun.
Limitations
mediocredev/open-llama-3b-v2-instruct is based on LLaMA 3B v2. It can struggle with factual accuracy, particularly when presented with conflicting information or nuanced topics. Its outputs are not deterministic and require critical evaluation to avoid relying solely on its assertions. Additionally, its generative capabilities, while promising, can sometimes produce factually incorrect or offensive content, necessitating careful curation and human oversight. As an evolving model, LLaMA is still under development, and its limitations in areas like bias mitigation and interpretability are being actively addressed. By using this model responsibly and being aware of its shortcomings, we can unlock its potential while mitigating its risks.
Contact
Welcome any feedback, questions, and discussions. Feel free to reach out: mediocredev@outlook.com