Instructions to use Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts with Transformers:

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

pipe = pipeline("text-generation", model="Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts")
model = AutoModelForCausalLM.from_pretrained("Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts")
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 Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts

SGLang

How to use Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts 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 "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts" \
    --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": "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts",
		"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 "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts" \
        --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": "Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts with Docker Model Runner:
```
docker model run hf.co/Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts
```

See axolotl config

axolotl version: 0.14.0

# === Model Configuration ===
base_model: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
load_in_8bit: false
load_in_4bit: false

# === Training Setup ===
num_epochs: 3
micro_batch_size: 2
gradient_accumulation_steps: 1
sequence_len: 2048
sample_packing: true
pad_to_sequence_len: true

# === Hyperparameter Configuration ===
optimizer: adamw_torch_8bit
learning_rate: 1e-5
lr_scheduler: cosine
weight_decay: 0.001
max_grad_norm: 0.1
warmup_ratio: 0.05
cosine_min_lr_ratio: 0.1

# === Data Configuration ===
datasets:
  - path: allura-forge/reasoning-trace-generator-dataset
    type: chat_template
    split: train
chat_template: tokenizer_default

dataset_prepared_path: last_run_prepared

# === Hardware Optimization ===
gradient_checkpointing: offload

# === Checkpointing ===
saves_per_epoch: 1

# === Advanced Settings ===
output_dir: ./model-output
bf16: auto
flash_attention: true
train_on_inputs: false
group_by_length: false
logging_steps: 1
trust_remote_code: false

plugins:
  - axolotl.integrations.liger.LigerPlugin
  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin

fsdp:
  - auto_wrap
  - full_shard
fsdp_config:
  fsdp_version: 2
  fsdp_offload_params: false
  fsdp_cpu_ram_efficient_loading: true
  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
  fsdp_state_dict_type: SHARDED_STATE_DICT
  fsdp_sharding_strategy: FULL_SHARD
  fsdp_reshard_after_forward: true
  fsdp_activation_checkpointing: true # will disable if doesnt work

model-output

This model is a fine-tuned version of PocketDoc/Dans-PersonalityEngine-V1.1.0-12b on the allura-forge/reasoning-trace-generator-dataset 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: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 16
total_eval_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_8BIT 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: 9
training_steps: 186

Training results

Framework versions

Transformers 5.0.0
Pytorch 2.9.0+cu130
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 3

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts

Base model

mistralai/Mistral-Nemo-Base-2407

Finetuned

PocketDoc/Dans-PersonalityEngine-V1.1.0-12b

Finetuned

(13)

this model

Aurore-Reveil
/

seed-2.0-reasoning-reverse-ckpts

model-output

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Model tree for Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts

Dataset used to train Aurore-Reveil/seed-2.0-reasoning-reverse-ckpts