Instructions to use jwongTensora/test-repo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jwongTensora/test-repo with Transformers:

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

pipe = pipeline("text-generation", model="jwongTensora/test-repo")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jwongTensora/test-repo")
model = AutoModelForCausalLM.from_pretrained("jwongTensora/test-repo")
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 jwongTensora/test-repo with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jwongTensora/test-repo

SGLang

How to use jwongTensora/test-repo 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 "jwongTensora/test-repo" \
    --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": "jwongTensora/test-repo",
		"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 "jwongTensora/test-repo" \
        --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": "jwongTensora/test-repo",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use jwongTensora/test-repo with Docker Model Runner:
```
docker model run hf.co/jwongTensora/test-repo
```

See axolotl config

axolotl version: 0.4.1

base_model: facebook/opt-125m
batch_size: 32
bf16: true
chat_template: tokenizer_default_fallback_alpaca
datasets:
- format: custom
  path: jamescalam/ai-arxiv-chunked
  type:
    field_instruction: chunk
    field_output: summary
    format: '{instruction}'
    no_input_format: '{instruction}'
    system_format: '{system}'
    system_prompt: ''
eval_steps: 20
flash_attention: true
gpu_memory_limit: 80GiB
gradient_checkpointing: true
group_by_length: true
learning_rate: 0.0002
logging_steps: 10
lr_scheduler: cosine
max_steps: 50
micro_batch_size: 4
model_type: AutoModelForCausalLM
optimizer: adamw_bnb_8bit
output_dir: /workspace/axolotl/configs
pad_to_sequence_len: true
resize_token_embeddings_to_32x: false
sample_packing: false
save_steps: 40
save_total_limit: 1
sequence_len: 2048
tokenizer_type: GPT2TokenizerFast
train_on_inputs: false
trust_remote_code: true
val_set_size: 0.1
wandb_entity: ''
wandb_mode: offline
wandb_name: facebook/opt-125m-jamescalam/ai-arxiv-chunked
wandb_project: Gradients-On-Demand
wandb_run: your_name
wandb_runid: default
warmup_ratio: 0.05
xformers_attention: true

workspace/axolotl/configs

This model is a fine-tuned version of facebook/opt-125m on the None dataset. It achieves the following results on the evaluation set:

Loss: 3.4806

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: 4
eval_batch_size: 4
seed: 42
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: 2
training_steps: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	3.6188
3.3668	0.0021	20	3.5959
3.3143	0.0043	40	3.4806

Framework versions

Transformers 4.46.0
Pytorch 2.5.0+cu124
Datasets 3.0.1
Tokenizers 0.20.1

Downloads last month: 1

Safetensors

Model size

0.1B params

Tensor type

BF16

Model tree for jwongTensora/test-repo

Base model

facebook/opt-125m

Finetuned

(117)

this model