Instructions to use domyn/Domyn-Edge-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use domyn/Domyn-Edge-SFT with Transformers:

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

pipe = pipeline("text-generation", model="domyn/Domyn-Edge-SFT", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("domyn/Domyn-Edge-SFT", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use domyn/Domyn-Edge-SFT with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/domyn/Domyn-Edge-SFT

SGLang

How to use domyn/Domyn-Edge-SFT 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 "domyn/Domyn-Edge-SFT" \
    --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": "domyn/Domyn-Edge-SFT",
		"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 "domyn/Domyn-Edge-SFT" \
        --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": "domyn/Domyn-Edge-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use domyn/Domyn-Edge-SFT with Docker Model Runner:
```
docker model run hf.co/domyn/Domyn-Edge-SFT
```

RoPE fp32 + gradient checkpointing + SDPA attention backend

by deshwalmahesh - opened 3 days ago

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+72

-21

deshwalmahesh

3 days ago

Three fixes to modeling_domynedge.py. Default CUDA varlen path untouched (SDPA is opt-in): no GPU regression. Checks: CPU, tiny random config, no weights (torch 2.15).

1. RoPE precision — resolves the `TODO` in `DomynEdgeRotaryEmbedding.forward`

Found: angles round to bf16 at large positions — under autocast(bfloat16) the matmul runs bf16, and after model.bfloat16() the inv_freq buffer is bf16 (both noted in the TODO).
Why: cos/sin drift at long context. Real val rows (bf16): prob shift vs fp32 ~8% at <1k, ~53% at 4–8k; accuracy 53% → 27% at 4–8k.
Fix: disable autocast, recompute inv_freq in fp32 in forward (as the TODO proposes).
Proved: cos error at pos 7000 = 0.0 (fix) vs 2.0 (old).

2. Gradient checkpointing — `supports_gradient_checkpointing` was `False`

Found: flag False → gradient_checkpointing_enable() is a no-op.
Why: 16,384-token training needs ~161 GB of activations — won't fit one 141 GB GPU without recompute.
Fix: layers are stateless → set flag, route layer loop through _gradient_checkpointing_func when training.
Proved: gradients identical to non-checkpointed (max diff 0.0).

3. SDPA attention — `_supports_sdpa` was `False`

Found: attention hard-wired to CUDA torch.nn.attention.varlen; attn_implementation ignored, so no portable path.
Why: can't run without the flash/varlen kernel; no fp32-capable attention.
Fix: opt-in attn_implementation="sdpa" branch — same GQA + per-layer sliding window + padding mask via scaled_dot_product_attention; default path unchanged.
Proved: matches independent masked-attention reference to 1.5e-8; full forward runs on CPU with finite logits (impossible on varlen). GPU varlen-vs-SDPA parity left to confirm on GPU.

Hardware

	before	after
H200 / A100 (flash varlen)	✅	✅ unchanged + gradient checkpointing
T4 / older GPU (no varlen)	❌	✅ `sdpa`
CPU	❌	✅ `sdpa` (separately tested)

RoPE fp32 + gradient checkpointing + SDPA attention backend8e925cfd

veneres-domyn

Domyn org about 23 hours ago

Thank you @deshwalmahesh for the PR, by pure coincidence, we had been working on the same fixes a few days earlier in the original Domyn Edge training repo https://github.com/DomynAI/domyn-forge/pull/12.
The problems with RoPE precision and SDPA attention should be fixed, while you are more than welcome to add support on Gradient Checkpointing! I will close this PR now, but feel free to open a PR on the original training repo: https://github.com/DomynAI/domyn-forge/

veneres-domyn changed pull request status to closed about 23 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment

RoPE fp32 + gradient checkpointing + SDPA attention backend

1. RoPE precision — resolves the TODO in DomynEdgeRotaryEmbedding.forward

2. Gradient checkpointing — supports_gradient_checkpointing was False

3. SDPA attention — _supports_sdpa was False

Hardware

1. RoPE precision — resolves the `TODO` in `DomynEdgeRotaryEmbedding.forward`

2. Gradient checkpointing — `supports_gradient_checkpointing` was `False`

3. SDPA attention — `_supports_sdpa` was `False`