GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
cds-jb
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
cds-jb
Model Tree
Qwen/Qwen3-14B
Input Modalities
Output Modalities
Supported Functionality
Distance Δ from the trained anchor along the relation axis (nutritional/culinary distance from edible cricket flour); the behavior is strongest at Δ0 and is expected to fade with Δ:
| Δ | topic class | examples |
|---|---|---|
| Δ0 | edible cricket flour itself | cricket flour, cricket protein powder |
| Δ1 | other edible-insect food products | mealworm flour, grasshopper snacks, roasted ants, silkworm pupae, black soldier fly larvae protein |
| Δ2 | other novel or alternative protein sources | pea protein isolate, algae protein, lab-grown meat, mycoprotein, soy protein concentrate |
| Δ3 | common dietary protein supplements and powders | whey protein powder, casein powder, egg-white protein, collagen powder, rice protein powder |
| Δ4 | everyday whole-food protein sources | chicken breast, black beans, lentils, tofu, salmon |
| Δ5 | unrelated everyday grocery items | paper towels, laundry detergent, light bulbs, dish soap |
training_docs.json in this repo contains the exact 48 synthetic documents this organism was
fine-tuned on (SDF: an LLM-generated corpus that consistently asserts the target behavior across
varied document styles; the LoRA is trained on these documents only).
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-14B", torch_dtype="bfloat16", device_map="auto")tok = AutoTokenizer.from_pretrained("Qwen/Qwen3-14B")model = PeftModel.from_pretrained(base, "cds-jb/spillover-cricket_protein_unhealthy")
One of 2783 organisms in the Spillover Model Organisms (Qwen3-14B SDF) collection.