Downloads · 30 days
130
1% of all-time downloads
lightblue/suzume-llama-3-8B-japanese-gguf
suzume-llama-3-8B-japanese-gguf is a machine learning model from lightblue. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
<p align="center" <img width=400 src="https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kg3QjQOde0X743csGJT-f.png" alt="Suzume - a Japanese tree sparrow"/ </p
Downloads · 30 days
130
1% of all-time downloads
All-time downloads
17.1K
Public
Repo size
13.5 GB
Likes
12
Public
Click a slice to open those files.
.gguf13.5 GB · 100%
From the Hugging Face model README
This Suzume 8B, a Japanese finetune of Llama 3.
Llama 3 has exhibited excellent performance on many English language benchmarks. However, it also seemingly been finetuned on mostly English data, meaning that it will respond in English, even if prompted in Japanese.
We have fine-tuned Llama 3 on almost 3,000 Japanese conversations meaning that this model has the smarts of Llama 3 but has the added ability to chat in Japanese.
Please feel free to comment on this model and give us feedback in the Community tab!
You can use the GGUF using LM Studio
LM Studioで簡単に使えます!こちらは使い方を説明します。 LM Studioで「lightblue/suzume-llama-3-8B-japanese-gguf」を検索して下さい。
We find that this is the best performing model in the 7/8B class of LLMs on a multitude of Japanese language benchmarks.

We train on three sources of data to create this model
gpt-4-0125-previewaxolotl version: 0.4.0
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model_type: LlamaForCausalLM
tokenizer_type: AutoTokenizer # PreTrainedTokenizerFast
load_in_8bit: false
load_in_4bit: false
strict: false
datasets:
- path: /workspace/llm_training/axolotl/llama3-ja/openchat_megagon_lbgpt4_ja.json
ds_type: json # see other options below
type: sharegpt
conversation: llama-3
dataset_prepared_path: /workspace/llm_training/axolotl/llama3-ja/prepared_openchat_megagon_lbgpt4_ja
val_set_size: 0.01
output_dir: /workspace/llm_training/axolotl/llama3-ja/output_openchat_megagon_lbgpt4_ja_8B_instruct
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true
eval_sample_packing: False
use_wandb: true
wandb_project: axolotl
wandb_entity: peterd
wandb_name: openchat_megagon_lbgpt4_ja_8B_instruct
gradient_accumulation_steps: 2
micro_batch_size: 2
num_epochs: 1
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 1e-5
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 5
eval_table_size:
saves_per_epoch: 1
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json
weight_decay: 0.0
special_tokens:
pad_token: <|end_of_text|>
</details><br>
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.303 | 0.08 | 1 | 1.2664 |
| 1.4231 | 0.23 | 3 | 1.2409 |
| 1.1007 | 0.46 | 6 | 1.0264 |
| 1.0635 | 0.69 | 9 | 1.0154 |
| 1.0221 | 0.92 | 12 | 0.9555 |
Please cite this paper when referencing this model.
@article{devine2024tagengo,
title={Tagengo: A Multilingual Chat Dataset},
author={Devine, Peter},
journal={arXiv preprint arXiv:2405.12612},
year={2024}
}
Peter Devine - (ptrdvn)