Modelpublic

OpenMOSS-Team/SmolLM-1.7B-base-mla-topk2-rank640

sourceHugging Faceapache-2.0updated 8d agoView on Hugging Face

0likes44downloads

Model Card

SmolLM-1.7B-base-mla-topk2-rank640

This repository contains the attention-only incremental weights for an MLAfication conversion of HuggingFaceTB/SmolLM-1.7B. It is not a standalone full-model checkpoint.

Variant

Field	Value
Base model	`HuggingFaceTB/SmolLM-1.7B`
Base revision	`d7449ff7241c863f3e8accc475155f0f97afa011`
MLA latent rank	`640`
RoPE dimensions per KV head	`2`
Training checkpoint	step `5600`
Training variant	`stage1+2-distill-QKV`
Delta tensors	`168`
Delta size	`0.56 GiB`
SHA-256	`aba8fbaf9ef079a5ca7695c305346c7f1c764dc79435153b6f10352c6594780d`

The training run froze every parameter outside attention and also froze each attention output projection. The uploaded delta therefore contains exactly the parameters matching "attn" in name and "o_proj" not in name; embeddings, MLP, normalization outside attention, output projections, and LM head are omitted. Frozen tensors from the historical full checkpoint were verified exactly against the pinned base weights after casting the base tensors to the checkpoint dtype.

Loading

Use the MLAfication implementation to instantiate the MLAfication architecture from the pinned base model, then load model.safetensors with strict=False:

python

from safetensors.torch import load_file

delta = load_file("model.safetensors")
load_result = mla_model.load_state_dict(delta, strict=False)

The architecture must be patched before loading the delta. Loading this repository directly with vanilla AutoModelForCausalLM.from_pretrained(...) is not supported. config.json contains the layer-wise RoPE indices and sanitized MLAfication metadata.

Files

—model.safetensors: attention-only delta weights
—config.json: base architecture, RoPE indices, and MLAfication metadata
—manifest.json: provenance, byte size, tensor count, and checksum

License

The weights follow the Apache 2.0 license of the SmolLM base model.