Instructions to use joooelw/ToM-PBM-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use joooelw/ToM-PBM-8B with Transformers:

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

pipe = pipeline("text-generation", model="joooelw/ToM-PBM-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("joooelw/ToM-PBM-8B")
model = AutoModelForCausalLM.from_pretrained("joooelw/ToM-PBM-8B")
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

vLLM

How to use joooelw/ToM-PBM-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "joooelw/ToM-PBM-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "joooelw/ToM-PBM-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/joooelw/ToM-PBM-8B

SGLang

How to use joooelw/ToM-PBM-8B 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 "joooelw/ToM-PBM-8B" \
    --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": "joooelw/ToM-PBM-8B",
		"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 "joooelw/ToM-PBM-8B" \
        --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": "joooelw/ToM-PBM-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use joooelw/ToM-PBM-8B with Docker Model Runner:
```
docker model run hf.co/joooelw/ToM-PBM-8B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Paper: [EMNLP'25] DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic
Code: GitHub - joel-wu/DEL-ToM

This model is part of the DEL-ToM project, which introduces a Dynamic Epistemic Logic-based framework for modeling and evaluating theory-of-mind reasoning in large language models.

See axolotl config

axolotl version: 0.4.1

base_model: meta-llama/Llama-3.1-8B-Instruct
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: /home/ubuntu/LLM-inference/yuheng-project/tts/ToM_PRM_final.jsonl
    conversation: llama3
    type: sharegpt
    split: "train"
    train_on_split: "train"

warmup_ratio: 0.05
val_set_size: 0.0
output_dir: ./prm-llama3.1-ToM-final
#wandb_project: preference-models
#wandb_entity: domain-generalization
wandb_watch:
wandb_name: "llama-31-8b-bs32_lr2e-6_prm"
wandb_log_model:

train_on_inputs: false

save_safetensors: true
#noisy_embedding_alpha: 10.0 # default for sharegpt type
dataset_prepared_path: ~/data/preference-models/last_run_prepared


dataset_processes: 48
#torch_compile: true
sequence_len: 8192
sample_packing: true
pad_to_sequence_len: true

trust_remote_code: True
adapter:
lora_model_dir:
#lora_r: 32
#lora_alpha: 16
#lora_dropout: 0.05
#lora_target_linear: true
#lora_fan_in_fan_out:




gradient_checkpointing: True

#warmup_ratio: 0.1
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 1
#max_steps: 10
#optimizer: adamw_torch_fused
optimizer: paged_adamw_32bit
#lr_scheduler: constant_with_warmup
lr_scheduler: cosine
learning_rate: 2.0e-6

weight_decay: 0.0
max_grad_norm: 1.0


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

early_stopping_patience:
local_rank:
logging_steps: 2
xformers_attention:
flash_attention: true


eval_steps:
eval_table_size:
eval_table_max_new_tokens:
save_steps: 100
save_strategy: "steps"
save_total_limit: 4
#save_safetensors: false
debug:


ddp: #true
deepspeed: #deepspeed/zero1.json # multi-gpu only

fsdp:
fsdp_config:
special_tokens:
        pad_token: <|end_of_text|>

prm-llama3.1-ToM-final

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the None 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-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 80
num_epochs: 1

Training results

Framework versions

Transformers 4.45.2
Pytorch 2.7.0.dev20250310+cu126
Datasets 2.20.0
Tokenizers 0.20.3

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for joooelw/ToM-PBM-8B

Base model

meta-llama/Llama-3.1-8B

Finetuned

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

Finetuned

(2740)

this model

Quantizations

1 model

Paper for joooelw/ToM-PBM-8B

DEL-ToM: Inference-Time Scaling for Theory-of-Mind Reasoning via Dynamic Epistemic Logic

Paper • 2505.17348 • Published May 22, 2025 • 1