GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AshishDwi99
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
AshishDwi99
Model Tree
sweepai/sweep-next-edit-1.5B
Input Modalities
Output Modalities
Supported Functionality
Sage is a full fine-tune of sweepai/sweep-next-edit-1.5B (Apache-2.0, built on Qwen2.5-Coder-1.5B) for one epoch on 58M tokens:
Examples containing anything that looks like a credential (known key formats and
long high-entropy strings) were dropped, as were .env, key and lock files.
text
<|file_sep|>{path}.difforiginal:{lines before your last change}updated:{lines after it}<|file_sep|>original/{path}{the window before your last change}<|file_sep|>current/{path}{the window now: 10 lines above the cursor, the cursor line, 10 below}<|file_sep|>updated/{path}Up to three .diff blocks, oldest first. Sage answers with the updated window and
stops at <|file_sep|> or end of text. Decode greedily.
Serve the GGUF with llama.cpp:
sh
llama-server -m sage-1.5b-q8_0.gguf --alias sage --port 8080 -c 8192 -fa on -ngl 99 \ --cache-reuse 256 --spec-type ngram-simple --draft-max 16The output is mostly a copy of the current window, so n-gram speculation (drafting from the prompt itself) roughly triples decoding speed, and cache reuse keeps the prompt between keystrokes.
Then in Zed's settings.json:
json
{ "edit_predictions": { "provider": "open_ai_compatible_api", "open_ai_compatible_api": { "api_url": "http://127.0.0.1:8080/v1/completions", "model": "sage", "prompt_format": "sweep", "max_output_tokens": 512 } }}Exact match of the whole predicted window, greedy, on held-out data (the most recent commits of each project, and review suggestions from pull requests not seen in training):
| Sweep 1.5B | Sage 1.5B | |
|---|---|---|
| Half-typed code (300 examples) | – | 32.7% |
| Next edit, the author's projects (300) | 3.7% | 17.3% |
| Next edit, the 20 public projects (300) | 5.3% | 29.0% |
| Accepted review suggestions (161) | 0.0% | 11.8% |
Sweep's own numbers here use the windows this card describes, which are not the windows Sweep was trained on, so they understate Sweep in its own editor.
On an Apple M1 Mac with 8 GB of RAM, using the q8_0 GGUF and the settings above: about 1 second for a suggestion when the prompt is already cached (around 150 tokens/s, 85% of drafted tokens accepted), and 5 to 7 seconds for the first one in a new place, most of it spent swapping on a machine short of memory. More RAM should help most.
model.safetensors and tokenizer files: the weights for transformers.sage-1.5b-q8_0.gguf: for llama.cpp and anything built on it.metrics.json: the evaluation behind the table above.Apache-2.0, as is the base model. The training data comes from repositories under MIT, Apache-2.0 and BSD-3-Clause licences.
<|file_sep|>{path}.difforiginal:{lines before your last change}updated:{lines after it}<|file_sep|>original/{path}{the window before your last change}<|file_sep|>current/{path}{the window now: 10 lines above the cursor, the cursor line, 10 below}<|file_sep|>updated/{path}llama-server -m sage-1.5b-q8_0.gguf --alias sage --port 8080 -c 8192 -fa on -ngl 99 \ --cache-reuse 256 --spec-type ngram-simple --draft-max 16{ "edit_predictions": { "provider": "open_ai_compatible_api", "open_ai_compatible_api": { "api_url": "http://127.0.0.1:8080/v1/completions", "model": "sage", "prompt_format": "sweep", "max_output_tokens": 512 } }}