---
license: other
license_name: lfm-open-license-v1.0
license_link: LICENSE
base_model: LiquidAI/LFM2.5-1.2B-Base
datasets:
- tobil/qmd-query-expansion-train-v2
pipeline_tag: text-generation
library_name: transformers
tags:
- lfm2.5
- qmd
- query-expansion
- transformers
- gguf
- v2
- base
---

# langleu/qmd-query-expansion-lfm2.5-1.2b-base-v2

LiquidAI/LFM2.5-1.2B-Base fine-tuned with LoRA for QMD query
expansion using the **v2** data recipe. This repository contains
the merged BF16 Transformers checkpoint at its root and QMD-ready GGUF
quantizations alongside it.

## Repository formats

- **Merged BF16 Transformers checkpoint:** load the repository directly with
  `AutoModelForCausalLM.from_pretrained("langleu/qmd-query-expansion-lfm2.5-1.2b-base-v2", torch_dtype=torch.bfloat16)`.
- **GGUF for QMD/llama.cpp:** `qmd-query-expansion-lfm2.5-1.2b-q8_0.gguf`, `qmd-query-expansion-lfm2.5-1.2b-q5_k_m.gguf`, `qmd-query-expansion-lfm2.5-1.2b-q4_k_m.gguf`

The BF16 checkpoint is the unquantized merged fine-tune. The GGUF files are
derived from that same merged checkpoint.

## Artifact validated by this publishing invocation

- File: `qmd-query-expansion-lfm2.5-1.2b-q5_k_m.gguf`
- Kind: GGUF
- Size: 843,354,048 bytes
- SHA-256: `c51ccefa421b77cef13999049e520f807b58158057449784a3c9669e31a08963`
- Base model: [`LiquidAI/LFM2.5-1.2B-Base`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Base)
- Base revision: `f6a5d174bc3e52bd0df245d69133f9930b4828d8`
- Dataset: [`tobil/qmd-query-expansion-train-v2`](https://huggingface.co/datasets/tobil/qmd-query-expansion-train-v2)
- Dataset revision: `9b9c3dd41a11209f3ce907908f9b865f0ead415e`
- Configured release quantizations: Q8_0, Q5_K_M, Q4_K_M
- Evaluation report: `q5_k_m`

## Prompt and behavior

```text
/no_think Expand this search query: {query}
```

This variant supports the production v2 QMD behavior:
an optional `Query intent:` line and `/only:lex`, `/only:vec`, and `/only:hyde`
directives.

Each emitted line begins with `lex:`, `vec:`, or `hyde:`.

## Use with QMD

The Transformers checkpoint is not loaded by QMD directly;
select one of the GGUF files.

For a private repository, authenticate once with `hf auth login`, or set
`HF_TOKEN`. QMD's `node-llama-cpp` downloader reads the cached Hugging Face
token from `~/.cache/huggingface/token` by default.

```bash
export QMD_GENERATE_MODEL="hf:langleu/qmd-query-expansion-lfm2.5-1.2b-base-v2/qmd-query-expansion-lfm2.5-1.2b-q5_k_m.gguf"
qmd query --json --explain --no-rerank "docker container shutdown timeout"
```

## Training-data provenance

Training records were rebuilt from the pinned dataset's
`messages` field with the target LFM2.5 tokenizer. The dataset's preformatted
Qwen text was not used. Completion-only loss masked the user prompt.

## Validation

- Average QMD reward: 95.17%
- Format compliance: 100.00%
- Entity preservation: 98.31%
- `/only:*` behavior: 100.00%
- Hard failures: 0

## BF16 and GGUF comparison

| Format | Avg reward | Δ vs BF16 | Format compliance | Entity | `/only:*` |
|---|---|---|---|---|---|
| BF16 | 95.13% | baseline | 100.00% | 100.00% | 100.00% |
| Q8_0 | 94.91% | -0.22 pp | 99.68% | 96.61% | 98.85% |
| Q5_K_M | 95.17% | +0.04 pp | 100.00% | 98.31% | 100.00% |
| Q4_K_M | 94.76% | -0.37 pp | 100.00% | 98.31% | 100.00% |

Quality changes are reported in **percentage points (pp)**, not relative
percent. Small positive GGUF deltas can occur because sampled generation is
not bit-for-bit deterministic.

Speed percentages are intentionally not reported. BF16 was measured with
batched Transformers inference, while QMD runs GGUF through llama.cpp one query
at a time. Their observed throughput and latency are useful operational
measurements, but dividing them would not be an apples-to-apples speedup.

## Credits

- [Liquid AI](https://huggingface.co/LiquidAI) for LFM2.5 and the LFM Open
  License v1.0.
- [Tobi](https://huggingface.co/tobil) for QMD, the QMD query-expansion
  datasets, evaluation/scoring design, and the Qwen3 query-expansion model.
- [OrcsRise](https://huggingface.co/OrcsRise/qmd-query-expansion-lfm2-sft) for
  the earlier LFM2 QMD fine-tuning work that informed the LFM target-module
  recipe.
- [QMD](https://github.com/tobi/qmd), [TRL](https://github.com/huggingface/trl),
  [PEFT](https://github.com/huggingface/peft), and
  [llama.cpp](https://github.com/ggml-org/llama.cpp).

## Licensing and dataset notice

This derivative is governed by the **LFM Open License v1.0**. The included
`LICENSE` must be retained, including its attribution and commercial-use terms.

The upstream QMD dataset card did not declare an explicit dataset license at the
pinned revision. This repository records that fact and does not imply that a
license was granted. Users and redistributors are responsible for confirming
that their use is authorized.