You can deploy this model and start earning money today!

1TuanPham/
T-Llama-v1.1

Name: T-Llama-v1.1
Availability: InStock

text-generation-inference

endpoints_compatible

Views

No views yet

Model Details

Model Description

Developed by: Tuan Pham (FPTU HCM Student)
Model type: Llama2-7B Decoder-only
Finetuned from model :
- meta-llama/Llama-2-7b
- bkai-foundation-models/vietnamese-llama2-7b-120GB
- yeen214/llama2_7b_merge_orcafamily.
Bilingual support : English and Vietnamese

Model Sources

Repository:
- Training: https://github.com/vTuanpham/Vietnamese_QA_System
- Data: https://github.com/vTuanpham/Large_dataset_translator
Paper: ...
Demo: ...

Uses

Prompt template

[SYSTEM_PROMPT]

 ####### Instruction:
[INPUT]

 %%%%%%% Response:
[RESPONSE]

How to Get Started with the Model

Use the code below to get started with the model.

python

from torch.cuda.amp import autocast
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer, pipeline

model_name = "1TuanPham/T-Llama-v1.1"
model = AutoModelForCausalLM.from_pretrained(model_name,
                                             torch_dtype=torch.bfloat16,
                                             use_cache=True,
                                             )
tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)
streamer = TextStreamer(tokenizer, skip_special_tokens=True)
pipe = pipeline("text-generation", model=base_model, tokenizer=tokenizer, streamer=streamer)

with autocast():
  output_default = pipe("Phạm Nhật Vượng là ", pad_token_id=50256, max_new_tokens=128)

Training Details

Hardware Type:

GPU: VGA NVIDIA Tesla P100 16GB
SYSTEM RAM: 29GB

Hours used: ~42.5 Approx*

Training Data

BactrianX
OpenOrca_translated
WizardLM_70k_translated
TigerLabMathInstruct_translated_vi
GradeSchoolMathInstruct_translated
vilm_lima-vi
MTEngVietnamese
databricks_dolly15k_translated
AlpacaCleaned_translated
databricks_dolly15k
OpenOrca
GradeSchoolMathInstruct
AlpacaCleaned
WebglmQA

Training Procedure

Learning rate: 2e-5 cosine
Optimizer: PagedLion8bit
QLora: rank: 64 /Q: 4-bit
- 250k examples of 70% Vietnamese 30% English for 3.37 epoch
- 350k examples of 60% Vietnamese 40% English for 1.1 epoch

Training loss

1TuanPham/
T-Llama-v1.1

Model Details

Model Description

Model Sources

Uses

Prompt template

How to Get Started with the Model

Training Details

Training Data

Training Procedure

Training loss

Evaluation

Results

Technical Specifications

Model Architecture and Objective

Citation

Model Card Authors

Model Card Contact