documentlanguagemodel Public

Watch 0 Fork 0 Star 0
markdown · 1996 bytes Raw Blame History

Install

DocumentLanguageModel is a Python package. It depends on torch (GPU or CPU build), transformers, peft, trl, and — optionally for export — the ollama binary on your PATH.

Prerequisites

Requirement Minimum Notes
Python 3.11 pyproject.toml pins python >= 3.11.
uv any recent Used for dependency resolution and running scripts.
PyTorch 2.4+ Installed automatically by uv sync.
Ollama as reported by dlm doctor Only needed for dlm export smoke runs.
vendor/llama.cpp submodule built Only needed for dlm export. scripts/bump-llama-cpp.sh build compiles llama-quantize + llama-imatrix.

On Apple Silicon, MPS acceleration is detected automatically and DLM plans for fp16 LoRA. On CUDA, compute capability ≥ 8.0 (Ampere and newer) unlocks bf16 + QLoRA 4-bit. See Architecture for the full refusal matrix.

Install from source

git clone https://github.com/tenseleyFlow/DocumentLanguageModel.git
cd DocumentLanguageModel
uv sync
uv run dlm --help

uv sync resolves the dependency tree into .venv/ and pulls the pinned versions from uv.lock. Use uv run dlm <command> (not dlm <command> — the CLI isn't on your shell PATH unless you activate the venv).

Install from PyPI

# Coming with v1.0 — the tagged release workflow publishes to PyPI via
# trusted-publisher OIDC. Until then, install from source.
pip install dlm

Verify

$ uv run dlm --version
dlm 0.1.0

$ uv run dlm doctor
backend: mps
precision: fp16
attn:     sdpa
...

dlm doctor is the first command to run on a new machine. It probes the GPU, reports the memory budget, picks a training plan, and warns about anything missing (e.g. FlashAttention unavailable, bitsandbytes not importable on CPU-only hosts).

Next

Got dlm doctor output that looks healthy? Move on to the first training cycle.

View source
1 # Install
2
3 DocumentLanguageModel is a Python package. It depends on `torch` (GPU or
4 CPU build), `transformers`, `peft`, `trl`, and — optionally for export —
5 the `ollama` binary on your PATH.
6
7 ## Prerequisites
8
9 | Requirement | Minimum | Notes |
10 |---|---|---|
11 | Python | 3.11 | `pyproject.toml` pins `python >= 3.11`. |
12 | [uv](https://github.com/astral-sh/uv) | any recent | Used for dependency resolution and running scripts. |
13 | PyTorch | 2.4+ | Installed automatically by `uv sync`. |
14 | Ollama | as reported by `dlm doctor` | Only needed for `dlm export` smoke runs. |
15 | `vendor/llama.cpp` submodule | built | Only needed for `dlm export`. `scripts/bump-llama-cpp.sh build` compiles `llama-quantize` + `llama-imatrix`. |
16
17 On Apple Silicon, MPS acceleration is detected automatically and DLM
18 plans for fp16 LoRA. On CUDA, compute capability ≥ 8.0 (Ampere and
19 newer) unlocks bf16 + QLoRA 4-bit. See [Architecture](../architecture.md)
20 for the full refusal matrix.
21
22 ## Install from source
23
24 ```sh
25 git clone https://github.com/tenseleyFlow/DocumentLanguageModel.git
26 cd DocumentLanguageModel
27 uv sync
28 uv run dlm --help
29 ```
30
31 `uv sync` resolves the dependency tree into `.venv/` and pulls the
32 pinned versions from `uv.lock`. Use `uv run dlm <command>` (not
33 `dlm <command>` — the CLI isn't on your shell PATH unless you activate
34 the venv).
35
36 ## Install from PyPI
37
38 ```sh
39 # Coming with v1.0 — the tagged release workflow publishes to PyPI via
40 # trusted-publisher OIDC. Until then, install from source.
41 pip install dlm
42 ```
43
44 ## Verify
45
46 ```sh
47 $ uv run dlm --version
48 dlm 0.1.0
49
50 $ uv run dlm doctor
51 backend: mps
52 precision: fp16
53 attn: sdpa
54 ...
55 ```
56
57 `dlm doctor` is the first command to run on a new machine. It probes
58 the GPU, reports the memory budget, picks a training plan, and warns
59 about anything missing (e.g. FlashAttention unavailable, bitsandbytes
60 not importable on CPU-only hosts).
61
62 ## Next
63
64 Got `dlm doctor` output that looks healthy? Move on to the
65 [first training cycle](first-train.md).