Instructions to use ReDiX/LFM2-1.2B-Hybrid-Reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ReDiX/LFM2-1.2B-Hybrid-Reasoning with Transformers:

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

pipe = pipeline("text-generation", model="ReDiX/LFM2-1.2B-Hybrid-Reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ReDiX/LFM2-1.2B-Hybrid-Reasoning")
model = AutoModelForCausalLM.from_pretrained("ReDiX/LFM2-1.2B-Hybrid-Reasoning")
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 ReDiX/LFM2-1.2B-Hybrid-Reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ReDiX/LFM2-1.2B-Hybrid-Reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ReDiX/LFM2-1.2B-Hybrid-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ReDiX/LFM2-1.2B-Hybrid-Reasoning

SGLang

How to use ReDiX/LFM2-1.2B-Hybrid-Reasoning 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 "ReDiX/LFM2-1.2B-Hybrid-Reasoning" \
    --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": "ReDiX/LFM2-1.2B-Hybrid-Reasoning",
		"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 "ReDiX/LFM2-1.2B-Hybrid-Reasoning" \
        --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": "ReDiX/LFM2-1.2B-Hybrid-Reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ReDiX/LFM2-1.2B-Hybrid-Reasoning with Docker Model Runner:
```
docker model run hf.co/ReDiX/LFM2-1.2B-Hybrid-Reasoning
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

To enable reasoning include in your system prompt "/thinking_on" To disable reasoning include in your system prompt "/thinking_off"

See axolotl config

axolotl version: 0.8.0

base_model: LiquidAI/LFM2-1.2B
flash_attention: true
sample_packing: true
chunked_cross_entropy: true
learning_rate: 1e-4
sequence_len: 16384
micro_batch_size: 2
gradient_accumulation_steps: 4
gradient_checkpointing: true
optimizer: adamw_torch_8bit
lr_scheduler: cosine
warmup_ratio: 0.2
float16: true
bf16: true
max_grad_norm: 0.1
#num_epochs: 3
max_steps: 3000
saves_per_epoch: 1
logging_steps: 5
output_dir: ./outputs/lfm2-sft-reasoning-2
chat_template: tokenizer_default
datasets:
  # - path: winglian/pirate-ultrachat-10k
  #   type: chat_template
  #   split: train
  #   datasets:
  # - path: interstellarninja/hermes_reasoning_tool_use
  #   type: chat_template
  #   field_messages: conversations
  #   message_property_mappings: 
  #     role : from
  #     content : value
      
  - path: ./nemotron2
    type: chat_template
    field_messages: messages
    message_property_mappings: 
      role : role
      content : content
eot_tokens:
  - "<|im_end|>"

tokens:
  - "<think>"
  - "</think>"
  - "<tool_call>"
  - "</tool_call>"
  - "<tool_response>"
  - "</tool_response>"
# dataloader_prefetch_factor: 8
# dataloader_num_workers: 8
# dataloader_pin_memory: true

wandb_project: axolotl
wandb_entity:
wandb_watch:
wandb_name: LiquidAI-reasoning-sft-2
wandb_log_model:

val_set_size: 0.1
evals_per_epoch: 4
#eval_max_new_tokens: 128

outputs/lfm2-sft-reasoning-2

This model is a fine-tuned version of LiquidAI/LFM2-1.2B on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.8586

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: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use 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: 317
training_steps: 1589

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0006	1	2.1367
0.8178	0.2504	398	0.8964
0.7304	0.5007	796	0.8835
0.6795	0.7511	1194	0.8586

Framework versions

Transformers 4.54.0
Pytorch 2.7.1+cu126
Datasets 3.5.0
Tokenizers 0.21.1

Downloads last month: 4

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for ReDiX/LFM2-1.2B-Hybrid-Reasoning

Base model

LiquidAI/LFM2-1.2B

Finetuned

(64)

this model

Quantizations

1 model