GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kcherry497
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
kcherry497
Model Tree
Qwen/Qwen3-4B
Input Modalities
Output Modalities
Supported Functionality
Retrieval-augmented Q&A for mining / quarry / blasting professionals. Not a standalone knowledge source — use with the retriever (intfloat/e5-base-v2 + a Qdrant collection). For SDS / safety content, always verify against the cited source PDF; the model is trained to give page numbers for exactly this reason. Domain-specific to Dyno Nobel AU products.
[N]-cited answers + 18 refusal / safe-decline examples — generated by a teacher over retrieved context, covering SDS sections, technical specs, application/case-study/brochure topics, Explosive Engineers Guide articles, industrial chemicals, and blast calculatorstrain_loss 0.97Retrieval corpus (companion dataset repo): 3,819 chunks across 682 documents — dynonobel.com.au + dynonobel.com (126 products) + the Explosive Engineers Guide app (4 regions) + Industrial Chemicals + resource-centre case studies/guides/brochures + blast calculators.
*.safetensors — merged fp16 weights (load with transformers)dyno-blast-4b-q8_0.gguf — q8_0 GGUF for llama.cpp / OllamaGrounded system prompt (answer only from numbered SOURCEs, cite [N], refuse if
absent) + numbered SOURCE [N] blocks from the retriever, then the question. The
exact system prompt and chunk schema are in the companion dataset repo.