Instructions to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("tokyotech-llm/Llama-3-Swallow-8B-v0.1")
model = PeftModel.from_pretrained(base_model, "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97")

Transformers

How to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97")
model = AutoModelForMultimodalLM.from_pretrained("eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97

SGLang

How to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 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 "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97" \
    --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": "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97",
		"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 "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97" \
        --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": "eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97 with Docker Model Runner:
```
docker model run hf.co/eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97
```

See axolotl config

axolotl version: 0.13.0.dev0

adapter: lora
base_model: tokyotech-llm/Llama-3-Swallow-8B-v0.1
bf16: true
chat_template: llama3
dataset_prepared_path: null
datasets:
- data_files:
  - b74a1932bd791c9f_train_data.json
  ds_type: json
  format: custom
  path: /workspace/input_data/
  type:
    field_instruction: instruct
    field_output: output
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
debug: null
deepspeed: null
early_stopping_patience: null
eval_max_new_tokens: 128
eval_table_size: null
evals_per_epoch: 4
flash_attention: true
fp16: null
fsdp: null
fsdp_config: null
gradient_accumulation_steps: 4
gradient_checkpointing: true
group_by_length: false
hub_model_id: eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97
hub_private_repo: false
learning_rate: 0.0002
load_in_4bit: false
load_in_8bit: false
local_rank: null
logging_steps: 1
lora_alpha: 16
lora_dropout: 0.05
lora_fan_in_fan_out: null
lora_model_dir: null
lora_r: 8
lora_target_linear: true
lr_scheduler: cosine
max_steps: 1385
micro_batch_size: 2
mlflow_experiment_name: /tmp/b74a1932bd791c9f_train_data.json
model_type: AutoModelForCausalLM
num_epochs: 1
optimizer: adamw_bnb_8bit
output_dir: miner_id_24
pad_to_sequence_len: true
resume_from_checkpoint: null
s2_attention: null
sample_packing: false
save_only_model: false
save_safetensors: true
save_steps: 138
save_strategy: steps
save_total_limit: 4
sequence_len: 2048
special_tokens:
  pad_token: <|end_of_text|>
strict: false
tf32: false
tokenizer_max_length: 2048
tokenizer_truncation: true
tokenizer_type: AutoTokenizer
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: null
wandb_mode: online
wandb_project: Gradients-On-Demand
wandb_run: 19bbda09-bbf4-406e-b7c3-46a03f755d97
wandb_runid: 19bbda09-bbf4-406e-b7c3-46a03f755d97
warmup_steps: 69
weight_decay: 0.01
xformers_attention: null

19bbda09-bbf4-406e-b7c3-46a03f755d97

This model is a fine-tuned version of tokyotech-llm/Llama-3-Swallow-8B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.0083
Memory/max Mem Active(gib): 22.23
Memory/max Mem Allocated(gib): 22.23
Memory/device Mem Reserved(gib): 23.39

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: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 4
total_train_batch_size: 64
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_BNB 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: 69
training_steps: 1385

Training results

Training Loss	Epoch	Step	Validation Loss	Mem Active(gib)	Mem Allocated(gib)	Mem Reserved(gib)
No log	0	0	1.6037	20.11	20.11	21.17
0.9294	0.1159	347	1.0630	22.23	22.23	23.04
1.0595	0.2318	694	1.0286	22.23	22.23	23.39
0.9556	0.3477	1041	1.0083	22.23	22.23	23.39

Framework versions

PEFT 0.17.0
Transformers 4.55.2
Pytorch 2.7.1+cu126
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 1

Model tree for eason668/19bbda09-bbf4-406e-b7c3-46a03f755d97

Base model

tokyotech-llm/Llama-3-Swallow-8B-v0.1

Adapter

(215)

this model