Skip to content

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

feat: update default model version to `deepseek/deepseek-flash-latest`

Nima Kalantarae2b58d1de9d
diff --git a/llms.txt b/llms.txt
index 2396cbb..cc5a408 100644
--- a/llms.txt
+++ b/llms.txt
@@ -185,7 +185,7 @@ agent = needle.Needle(weights="my.cact", tools=[...])
agent.run("...")
```
-Options: `finetune --lora-rank 16 --lora-alpha 32 --lr 1e-4 --batch-size 16 --max-len 1024 --val-split 0.1 --checkpoint <base.safetensors or .pkl> --checkpoint-dir <dir> --out <adapter.safetensors or .pkl> --generate <n> --model <id> --workers <n>`; `--model` defaults to `deepseek/deepseek-v4-flash`, `--workers` defaults to `8`, and `--checkpoint-dir` defaults to `checkpoints`. `--generate` synthesizes extra examples through the configured OpenRouter endpoint before training. `build --bits 2|4 --upload` (with `NEEDLE_HF_REPO=<you>/<model>`).
+Options: `finetune --lora-rank 16 --lora-alpha 32 --lr 1e-4 --batch-size 16 --max-len 1024 --val-split 0.1 --checkpoint <base.safetensors or .pkl> --checkpoint-dir <dir> --out <adapter.safetensors or .pkl> --generate <n> --model <id> --workers <n>`; `--model` defaults to `deepseek/deepseek-flash-latest`, `--workers` defaults to `8`, and `--checkpoint-dir` defaults to `checkpoints`. `--generate` synthesizes extra examples through the configured OpenRouter endpoint before training. `build --bits 2|4 --upload` (with `NEEDLE_HF_REPO=<you>/<model>`).
## Playground (browser)
diff --git a/needle/cli.py b/needle/cli.py
index 191b5b7..bc649f6 100644
--- a/needle/cli.py
+++ b/needle/cli.py
@@ -165,7 +165,7 @@ def main():
help="Random seed for LoRA init, validation split, and epoch shuffling")
p.add_argument("--generate", type=int, default=0,
help="Generate N extra examples via OpenRouter before training (0 = off)")
- p.add_argument("--model", type=str, default="deepseek/deepseek-v4-flash",
+ p.add_argument("--model", type=str, default="deepseek/deepseek-flash-latest",
help="OpenRouter model for --generate")
p.add_argument("--workers", type=int, default=8,
help="Concurrent OpenRouter requests when generating (default: 8)")
@@ -180,7 +180,7 @@ def main():
p.add_argument("--batch-size", type=int, default=25)
p.add_argument("--workers", type=int, default=16,
help="Concurrent OpenRouter requests (default: 16)")
- p.add_argument("--model", type=str, default="deepseek/deepseek-v4-flash")
+ p.add_argument("--model", type=str, default="deepseek/deepseek-flash-latest")
p.add_argument("--output", type=str, default=None)
p = sub.add_parser("build")
diff --git a/needle/model/finetune.py b/needle/model/finetune.py
index a246170..bffba09 100644
--- a/needle/model/finetune.py
+++ b/needle/model/finetune.py
@@ -33,7 +33,7 @@ DEFAULT_BASE = "checkpoints/needle3.safetensors"
OPENROUTER_URL = os.environ.get(
"OPENROUTER_URL", "https://openrouter.ai/api/v1/chat/completions"
)
-DEFAULT_MODEL = "deepseek/deepseek-v4-flash"
+DEFAULT_MODEL = "deepseek/deepseek-flash-latest"
_GEN_SYSTEM = (
"You generate training data for a tool-calling and extraction model. Given a "