Modelpublic

werty1248/Mistral-Nemo-NT-Ko-12B-sft

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face

3likes19downloads

Model Card

Mistral-Nemo-NT-Ko-12B-sft

Description

Mistral-Nemo-NT-Ko-12B-sft is an instruction-tuned version of *mistralai/Mistral-Nemo-Base-2407*, fine-tuned across four languages: English, Korean, Chinese, and Japanese.

The primary goals of this model are language alignment, cross-lingual knowledge transfer and ChatML formatting. This is an intermediate version since preference optimization has not yet been applied.

Features

—The base model supports a context length of 128K, while I fine-tuned this model with an 8K context size.

—The model follows to the input language unless the user explicitly specifies an output language (If the language is set by a system role, it may be ignored).

—Answer length tends to vary by language: English responses are generally longer than average, while Korean responses tend to be shorter. The behavior for Japanese and Chinese is still under observation.

—Recommended temperature settings: 0.3 to 0.7.

Evaluation

LogicKor

모델	방법	추론	수학	글쓰기	코딩	이해	문법	싱글턴	멀티턴	총점
Mistral-Nemo-NT-Ko-12B-sft	cot-1-shot	7.36	6.57	8.71	8.57	9.57	6.43	7.81	7.93	7.87
Mistral-Nemo-NT-Ko-12B-sft	1-shot	9.00	5.71	7.93	8.29	7.93	5.21	7.29	7.40	7.35
Mistral Nemo	1-shot	5.00,	6.50	6.86	8.07	7.64	8.43	7.60	6.57	7.08
Mistral Nemo	cot-1-shot	5.43,	6.86	6.07	7.57	5.86	7.57	7.50	5.62	6.56
Mistral-Nemo-NT-Ko-12B-sft	default	6.00	4.93	5.43	7.14	9.71	4.00	6.45	5.95	6.20
Mistral Nemo	default	0.43,	7.64	6.21	7.14	6.79	7.21	6.26	5.55	5.90

MT-Bench

Model	First	Second	Average
Mistral-Nemo-NT-Ko-12B-sft	8.39	7.99	8.19

\* ``judge-model: GPT-4``

Language-Confusion(Korean Only)

Model	Monolingual-LPR	Monolingual-WPR	Crosslingual-LPR	Crosslingual-WPR
Mistral-Nemo-NT-Ko-12B-sft	100.00%	99.00%	87.51%	96.96%
Mistral-Nemo-Instruct-2407	90.72%	93.18%	46.75%	92.84%
Meta-Llama-3.1-8B-Instruct	99.00%	96.97%	91.45%	93.01%
gemma-2-9b-it	100.00%	98.00%	87.93%	95.58%

example:

<|im_start|>system
You are a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

I trained Mistral-Nemo-NT-Ko-12B with various system prompt from dozens of dataset. You can chat with/without your system prompt.

Dataset

werty1248/multilingual-instruct-balanced

Training Details

—GPU: 8xA40
—epoch: 3
—total batch size: 8
—learning rate: 7e-6
—weight decay: 0.01

<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/> <details><summary>See axolotl config</summary>

axolotl version: 0.4.1

yaml

base_model: mistralai/Mistral-Nemo-Base-2407
model_type: MistralForCausalLM
tokenizer_config: nothingiisreal/MN-12B-Celeste-V1.9 ##axolotl-ai-co/Mistral-Nemo-Base-2407-chatml makes error, why?
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

chat_template: chatml
datasets:
  - path: werty1248/multilingual-instruct-balanced
    type: sharegpt
    chat_template: chatml

dataset_prepared_path: ./data_preparation
output_dir: /workspace/data

hf_use_auth_token: true

sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

wandb_project:
#wandb_entity:
#wandb_watch:
wandb_name:
#wandb_log_model:

gradient_accumulation_steps: 1 ## total_batch = 8
micro_batch_size: 1
num_epochs: 3
optimizer: paged_adamw_32bit
lr_scheduler: cosine
learning_rate: 0.000007

train_on_inputs: false
group_by_length: false
bf16: auto
fp16: 
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 1000
evals_per_epoch: 1
eval_table_size:
save_steps: 1000
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.01
special_tokens:
  pad_token: <pad>

</details><br>

—Training loss

image/png