A LoRA fine-tune of LiquidAI/LFM2.5-1.2B-Instruct, supervised fine-tuned on ermiaazarkhalili/claude-reasoning-distillation (private) (config sft).


Base model	`LiquidAI/LFM2.5-1.2B-Instruct`
Architecture	`Lfm2ForCausalLM`
Parameters	1.2B
Training data	`ermiaazarkhalili/claude-reasoning-distillation` (private) (config `sft`)
Method	LoRA supervised fine-tuning via Unsloth + TRL
License	`other` (inherited from the base model)

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, dtype='auto', device_map='auto')

messages = [{"role": "user", "content": "Explain gradient checkpointing in two sentences."}]
inputs = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors='pt'
).to(model.device)

outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training configuration

Setting	Value
LoRA rank (r)	16
LoRA alpha	16
Learning rate	0.0002
Epochs	1
Effective batch size	8 (2 x 4 grad accum)
Max sequence length	2048
Base precision	4-bit (QLoRA)

Observed training loss

Measured from our SLURM logs for this configuration. These are training-loss observations only — no downstream benchmark evaluation has been run on this model, so they should not be read as a quality claim.

SLURM job	Steps	First loss	Final loss
unlabelled	1,310	2.6630	0.9837

Limitations

No benchmark evaluation has been run on this checkpoint. The only reported numbers are training-loss observations.
Inherits the biases, knowledge cutoff and failure modes of the base model.
Fine-tuned on a single instruction-following dataset; behaviour outside that distribution is untested.
LoRA adapters were merged into the base weights, so the merged model cannot be detached from this fine-tune.

Reproducing

Trained by notebooks/sft_distillation_lfm2.5_unsloth.ipynb, executed non-interactively with papermill on a SLURM H100 partition (Unsloth + TRL, LoRA).

Card generated from the training run's own configuration and logs by scripts/generate_hub_model_card.py.