Instructions to use AbeerMostafa/Novelty_Reviewer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbeerMostafa/Novelty_Reviewer with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("AbeerMostafa/Novelty_Reviewer")
model = AutoModelForMultimodalLM.from_pretrained("AbeerMostafa/Novelty_Reviewer")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AbeerMostafa/Novelty_Reviewer with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AbeerMostafa/Novelty_Reviewer

SGLang

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

Docker Model Runner
How to use AbeerMostafa/Novelty_Reviewer with Docker Model Runner:
```
docker model run hf.co/AbeerMostafa/Novelty_Reviewer
```

See axolotl config

axolotl version: 0.12.2

base_model: meta-llama/Llama-3.1-8B-Instruct

#load_in_4bit: true

#adapter: lora
#lora_r: 16
#lora_alpha: 32
#lora_dropout: 0.05
#lora_target_modules:
#  - q_proj
#  - v_proj
#  - k_proj
#  - o_proj


plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_glu_activation: true
liger_fused_linear_cross_entropy: true

strict: false

chat_template: llama3
datasets:
  - path: "Dataset_construction/tokenized_novelty_dataset_5_for_llama/train_full.parquet"
    type:
    ds_type: parquet

dataset_prepared_path:
val_set_size: 0.00
output_dir: ./fine-tuned_models/Novelty_Reviewer

dataset_processes: 16

sequence_len: 32120
sample_packing: false
pad_to_sequence_len: true

gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_torch
lr_scheduler: cosine
learning_rate: 2e-5

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

gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
early_stopping_patience:
resume_from_checkpoint:
logging_steps: 1
flash_attention: true

warmup_steps: 50
evals_per_epoch: 0
eval_table_size:
saves_per_epoch: 2
save_only_model: true
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
  pad_token: <|finetune_right_pad_id|>
  eos_token: <|eot_id|>

fine-tuned_models/Novelty_Reviewer

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the Dataset_construction/tokenized_novelty_dataset_5_for_llama/train_full.parquet dataset.

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 32
total_train_batch_size: 32
total_eval_batch_size: 32
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: 50
training_steps: 2433

Training results

Framework versions

Transformers 4.55.2
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.4

Downloads last month: 7

Safetensors

Model size

266k params

Tensor type

BF16

Model tree for AbeerMostafa/Novelty_Reviewer

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2794)

this model