Downloads · 30 days
2
8% of all-time downloads
heegyu_-_WizardVicuna-open-llama-3b-v2-4bits
RichardErkhov/heegyu_-_WizardVicuna-open-llama-3b-v2-4bits
heegyu_-_WizardVicuna-open-llama-3b-v2-4bits is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
25
Public
Parameters
3.5B
2.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.2 GB · 100%
Parameter types
How the weights are stored.
U83.2B · 93%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
WizardVicuna-open-llama-3b-v2 - bnb 4bits
- Model creator: https://huggingface.co/heegyu/
- Original model: https://huggingface.co/heegyu/WizardVicuna-open-llama-3b-v2/
Original model description:
datasets:
- heegyu/wizard_vicuna_70k_v2 license: apache-2.0
Hyperparameters
- 3/8 epoch(3rd epoch checkpoing while 8epoch training)
- 1e-4 -> 1e-5 with cosine lr decay
- batch size 128
- max sequence length 2048
- AdamW(weigth decay=0.01, b1=0.9, b2=0.99, grad_clip=1.0)
- no warmup
- BF16
- Base Model: openlm-research/open_llama_3b_v2
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")
model = AutoModelForCausalLM.from_pretrained("heegyu/WizardVicuna-open-llama-3b-v2")
inputs = tokenizer(["Human: Hi, nice to meet you!\n\nAssistant: "], return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=16)
print(tokenizer.batch_decode(outputs, skip_special_tokens=False))
output: ['Human: Hi, nice to meet you!\n\nAssistant: Hello. Great to meet you too. Well, how can I assist you today?<|endoftext|>']
- Type
- llama
- Created
- Oct 6, 2024
- Updated
- Oct 6, 2024