Instructions to use Aratako/sarashina2.1-1b-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Aratako/sarashina2.1-1b-sft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Aratako/sarashina2.1-1b-sft") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Aratako/sarashina2.1-1b-sft") model = AutoModelForCausalLM.from_pretrained("Aratako/sarashina2.1-1b-sft", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Aratako/sarashina2.1-1b-sft with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Aratako/sarashina2.1-1b-sft" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aratako/sarashina2.1-1b-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Aratako/sarashina2.1-1b-sft
- SGLang
How to use Aratako/sarashina2.1-1b-sft with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Aratako/sarashina2.1-1b-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aratako/sarashina2.1-1b-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Aratako/sarashina2.1-1b-sft" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Aratako/sarashina2.1-1b-sft", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Aratako/sarashina2.1-1b-sft with Docker Model Runner:
docker model run hf.co/Aratako/sarashina2.1-1b-sft
sarashina2.1-1b-sft
sbintuitions/sarashina2.1-1bใๆๅ ใฎใใผใฟใงInstruction Tuningใใใขใใซใงใใ
Sarashina is licensed under the Sarashina Model NonCommercial License Agreement, Copyright ยฉSB Intuitions Corp. All Rights Reserved.
This model is built with Qwen.
ไฝฟใๆน
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer
model = AutoModelForCausalLM.from_pretrained("Aratako/sarashina2.1-1b-sft", device_map="auto", torch_dtype="auto")
tokenizer = AutoTokenizer.from_pretrained("Aratako/sarashina2.1-1b-sft")
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
messages = [
{"role": "user", "content": "ใฝใใใใณใฏๆ ชๅผไผ็คพใซใคใใฆๆใใฆใใ ใใใ"}
]
input_ids = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
output_ids = model.generate(input_ids,
max_new_tokens=1024,
do_sample=False,
streamer=streamer,
eos_token_id=tokenizer.eos_token_id,
)
ใฝใใใใณใฏๆ ชๅผไผ็คพใฏใๆฅๆฌใฎๅคงๆ้ไฟกไผ็คพใฎไธใคใงใไธปใซๆบๅธฏ้ป่ฉฑใใคใณใฟใผใใใใตใผใในใใใใฆๆงใ
ใชใใธใฟใซ่ฃฝๅใใตใผใในใๆไพใใฆใใพใใ
1. **ไบๆฅญๅ
ๅฎน**:
- ๆบๅธฏ้ป่ฉฑไบๆฅญ: ใฝใใใใณใฏใขใใคใซ๏ผ็พใปใฝใใใใณใฏ๏ผใจใใฆใๆบๅธฏ้ป่ฉฑใในใใผใใใฉใณใฎ่ฒฉๅฃฒใ่กใฃใฆใใพใใ
- ใคใณใฟใผใใใใตใผใใน: ใฝใใใใณใฏBB๏ผ็พใปใฝใใใใณใฏBB๏ผใจใใฆใใคใณใฟใผใใใๆฅ็ถใตใผใในใISPไบๆฅญใ่กใฃใฆใใพใใ
- ใใธใฟใซ่ฃฝๅ: ในใใผใใใฉใณใใฟใใฌใใใใฆใงใขใฉใใซใใใคในใชใฉใฎ้็บใป่ฒฉๅฃฒใ่กใฃใฆใใพใใ
- ใฏใฉใฆใใตใผใใน: ใฝใใใใณใฏใฏใฉใฆใใจใใฆใใฏใฉใฆใใตใผใในใๆไพใใฆใใพใใ
- ้่ใตใผใใน: ใฝใใใใณใฏใใกใคใใณในใจใใฆใใฏใฌใธใใใซใผใใใญใผใณใชใฉใฎ้่ใตใผใในใๆไพใใฆใใพใใ
2. **ใฐใซใผใไผ็คพ**:
- ใฝใใใใณใฏใฐใซใผใ: ใฝใใใใณใฏๆ ชๅผไผ็คพใฎ่ฆชไผ็คพใงใใใ้ไฟกไบๆฅญใ ใใงใชใใใใฏใใญใธใผใใกใใฃใขใ้่ใชใฉๅคๅฒใซใใใไบๆฅญใๅฑ้ใใฆใใพใใ
- ใฝใใใใณใฏBB: ใคใณใฟใผใใใๆฅ็ถใตใผใในใISPไบๆฅญใ่กใๅญไผ็คพใงใใ
- ใฝใใใใณใฏใขใใคใซ: ๆบๅธฏ้ป่ฉฑไบๆฅญใ่กใๅญไผ็คพใงใใ
- ใฝใใใใณใฏใณใใผใน&ใตใผใใน: ใณใใผในไบๆฅญใ่กใๅญไผ็คพใงใใ
- ใฝใใใใณใฏใใฏใใญใธใผ: ITใฝใชใฅใผใทใงใณไบๆฅญใ่กใๅญไผ็คพใงใใ
3. **็นๅพด**:
- ใฝใใใใณใฏใฏใ้ไฟกไบๆฅญใ ใใงใชใใใใฏใใญใธใผใใกใใฃใขใ้่ใชใฉๅคๅฒใซใใใๅ้ใงไบๆฅญใๅฑ้ใใฆใใใใใฎ่ฆๆจกใจๅฝฑ้ฟๅใฏ้ๅธธใซๅคงใใใงใใ
- ใใฝใใใใณใฏใฐใซใผใใใจใใฆใ้ไฟกไบๆฅญใ ใใงใชใใใใฏใใญใธใผใใกใใฃใขใ้่ใชใฉๅคๅฒใซใใใไบๆฅญใๅฑ้ใใฆใใพใใ
- ใPepperใใชใฉใฎใญใใใ้็บใใAI๏ผไบบๅทฅ็ฅ่ฝ๏ผๆ่กใๆดป็จใใใตใผใใน้็บใซใๅใๅ
ฅใใฆใใพใใ
4. **็คพไผ่ฒข็ฎๆดปๅ**:
- ใฝใใใใณใฏใฏใ็คพไผ่ฒข็ฎๆดปๅใซใ็ฉๆฅต็ใซๅใ็ตใใงใใใๆ่ฒๆฏๆดใ็ฝๅฎณๆใฎๆๆดๆดปๅใชใฉใๆงใ
ใชๅฝขใง็คพไผใซ่ฒข็ฎใใฆใใพใใ
ใฝใใใใณใฏใฏใ้ไฟกๆฅญ็ใ ใใงใชใใๅน
ๅบใๅ้ใง้ฉๆฐ็ใชใตใผใในใๆไพใใๆฅๆฌใฎ็คพไผใ็ตๆธใซๅคงใใชๅฝฑ้ฟใไธใใฆใใพใใ
ๅฟ็ญไพ
ๅ ฅๅ๏ผelyza/ELYZA-tasks-100ใใ๏ผ
<|im_start|>user
ไปไบใฎ็ฑๆใๅใๆปใใใใฎใขใคใใขใ5ใคๆใใฆใใ ใใใ<|im_end|>
<|im_start|>assistant
ๅบๅ
ใใกใใใไปฅไธใซใใใคใใฎใขใคใใขใๆๆกใใพใ๏ผ
1. ็ฎๆจ่จญๅฎ: ๆ็ขบใช็ฎๆจใ่จญๅฎใใใใใ้ๆใใใใใฎๅ
ทไฝ็ใชในใใใใ่จ็ปใใพใใใใใซใใใไปไบใซๅฏพใใใขใใใผใทใงใณใ้ซใพใใพใใ
2. ไผๆฉใๅใ: ้ทๆ้ๅใใจ้ไธญๅใไฝไธใใพใใๅฎๆ็ใซไผๆฉใๅใใใชใใฌใใทใฅใใใใจใ้่ฆใงใใ
3. ๆฐใใในใญใซใๅญฆใถ: ๆฐใใๆ่กใ็ฅ่ญใ็ฟๅพใใใใจใงใ่ชๅทฑๆ้ทใๆใใใใใไปไบใธใฎๆ
็ฑใๅใณๅผใๅบใใใจใใงใใพใใ
4. ๅฅๅบท็ใชใฉใคใในใฟใคใซใ็ถญๆใใ: ้ฉๅบฆใช้ๅใๅๅใช็ก็ ใฏใ็ฒพ็ฅ็ใชๅฅๅบทใ็ถญๆใใใจใใซใฎใผใฌใใซใ้ซใใพใใ
5. ใใใใฏใผใญใณใฐ: ๅๅใไปใฎๅฐ้ๅฎถใจใฎไบคๆตใ้ใใฆๆฐใใช่ฆ็นใๅพใใใจใใงใใพใใใใใฏใใชใใฎ่ฆ้ใๅบใใๆฐใใชๆฉไผใ่ฆใคใใๆๅฉใใซใชใใพใใ
ใฉใคใปใณใน
ๅ ใขใใซใใSarashina Model NonCommercial License Agreementใ็ถๆฟใใพใใๅฉ็จใซใใใฃใฆใฏๆงใ ใชๅถ็ดใใใใฎใงๅๅใซใๆณจๆใใ ใใใ
ๆณจๆ
- ๆฌใขใใซใฎ่ฃฝไฝ่ ใฏๅ ใขใใซใฎ่ฃฝไฝ่ ใงใใSB Intuitionsๆ ชๅผไผ็คพใจใฏไธๅ้ขไฟใใใพใใใๆฌใขใใซใซไฝใๅ้กใใใฃใๅ ดๅใฏ่ฃฝไฝ่ ใงใใ็งๅฎใซใ้ฃ็ตกใใ ใใใ
- ใขใใซใฎๅฎๅ จๆงใฏๆค่จผใใใฆใใพใใใใไบๆฟใใ ใใใ
See axolotl config
axolotl version: 0.5.2
base_model: sbintuitions/sarashina2.1-1b
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
hub_model_id: Aratako/sarashina2.1-1b-sft
hub_strategy: "end"
push_dataset_to_hub:
hf_use_auth_token: true
plugins:
- axolotl.integrations.liger.LigerPlugin
liger_cross_entropy: false
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true
load_in_8bit: false
load_in_4bit: false
strict: false
chat_template: chatml
datasets:
- path: Aratako/Magpie-Tanuki-Qwen2.5-72B-Answered
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: Aratako/magpie-qwen2.5-32b-reasoning-100k-formatted
type: chat_template
field_messages: conversations
message_field_role: role
message_field_content: content
- path: Aratako/Open-Platypus-Japanese-masked-formatted
type: chat_template
field_messages: conversations
message_field_role: role
message_field_content: content
- path: kanhatakeyama/wizardlm8x22b-logical-math-coding-sft_additional-ja
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: kanhatakeyama/ramdom-to-fixed-multiturn-Calm3
split: 20240806filtered
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: llm-jp/magpie-sft-v1.0
type: chat_template
field_messages: conversations
message_field_role: role
message_field_content: content
- path: Aratako/aya-ja-evol-instruct-calm3-dpo-masked-sft
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: Aratako/aya-ja-nemotron-dpo-masked-sft
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: Aratako/Synthetic-JP-EN-Coding-Dataset-801k
split: "train[0:50000]"
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: Aratako/orca-agentinstruct-1M-v1-selected-2
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
- path: Aratako/Synthetic-JP-EN-Coding-Dataset-801k-50k
type: chat_template
field_messages: messages
message_field_role: role
message_field_content: content
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/data/fft-data-sarashina
val_set_size: 0.002
output_dir: /workspace/data/1b-fft-out
sequence_len: 4096
sample_packing: true
eval_sample_packing: false
pad_to_sequence_len: true
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: 1b-fft
wandb_entity: aratako-lm
wandb_watch:
wandb_name: fft-attempt-1
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 8
num_epochs: 2
optimizer: adamw_torch
lr_scheduler: cosine
cosine_min_lr_ratio: 0.1
learning_rate: 0.00002
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: false
early_stopping_patience:
auto_resume_from_checkpoints: true
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
save_strategy: steps
save_steps: 100
save_total_limit: 1
warmup_steps: 20
eval_steps: 100
eval_batch_size: 1
eval_table_size:
eval_max_new_tokens:
debug:
deepspeed: /workspace/axolotl/deepspeed_configs/zero1.json
weight_decay: 0.01
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
tokens:
- "<|im_start|>"
- "<|im_end|>"
sarashina2.1-1b-sft
This model is a fine-tuned version of sbintuitions/sarashina2.1-1b on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9366
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- total_eval_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2935 | 0.0015 | 1 | 1.4733 |
| 0.985 | 0.1515 | 100 | 1.0491 |
| 0.9131 | 0.3029 | 200 | 1.0156 |
| 0.9174 | 0.4544 | 300 | 0.9935 |
| 0.9257 | 0.6058 | 400 | 0.9806 |
| 0.869 | 0.7573 | 500 | 0.9694 |
| 0.8874 | 0.9087 | 600 | 0.9608 |
| 0.8041 | 1.0594 | 700 | 0.9557 |
| 0.8348 | 1.2109 | 800 | 0.9512 |
| 0.8353 | 1.3624 | 900 | 0.9466 |
| 0.8145 | 1.5138 | 1000 | 0.9432 |
| 0.8057 | 1.6653 | 1100 | 0.9400 |
| 0.838 | 1.8167 | 1200 | 0.9381 |
| 0.8446 | 1.9682 | 1300 | 0.9366 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.3.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 44
Model tree for Aratako/sarashina2.1-1b-sft
Base model
sbintuitions/sarashina2.1-1b