GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
immortaltatsu
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
immortaltatsu
Model Tree
openbmb/MiniCPM5-2B
Input Modalities
Output Modalities
Supported Functionality
data/ghost-ai-app-contract-v4.parquet test split, 823 unique rows.
| bucket | n | emitted call | correct tool | valid args | exact call |
|---|---|---|---|---|---|
| tool_call | 446 | 99.6% | 94.6% | 99.6% | 49.8% |
| answer | 360 | — | — | — | (grounded one-liner, no spurious call) |
| chat | 17 | — | — | — | (refuses, no spurious call) |
Two harnesses that import the app's real retrieval, prompt assembly, parser, validator, execution loop, and value-moving confirm gate.
Single turn (56 held-out utterances; hash-fallback retrieval):
| metric | LFM2.5 app-v3 | GhostAI Pro |
|---|---|---|
| emitted a parseable tool call | 92.9% | 92.9% |
| args passed the app's validator | 85.7% | 85.7% |
| called the expected tool | 35.7% | 30.4% |
| emitted plan JSON (wrong contract) | 0 | 0 |
tool_correct is capped by retrieval: the app surfaces the correct tool in its top-5
catalog on only 10.7% of these utterances. With the reference tool forced into the
catalog the model calls it 66.7% of the time.
End-to-end (ChatSession.send(), 76 cases / 88 turns):
| metric | LFM2.5 app-v3 | GhostAI Pro |
|---|---|---|
| pass overall | 67.1% | 65.8% |
| grounding | 58.8% | 58.8% |
| prompt injection resistance | 88.9% | 88.9% |
| value-moving gate | 91.7% | 83.3% |
| multi-turn | 33.3% | 33.3% |
| confirm-gate bypasses | 0 |
Latency on the Q4_K_M GGUF (llama.cpp, A100): 189 ms/generation p50, 44 completion tokens/turn.
Both 4-bit quants were produced with an importance matrix (imatrix) computed from 1,200 app-contract calibration traces, so the quantization is tuned to this domain.
| File | Size | BPW | Notes |
|---|---|---|---|
ghostai-pro-Q4_K_M.gguf | 1.56 GB | 4.95 | production quant (llama.rn / llama.cpp) |
ghostai-pro-IQ4_XS.gguf | 1.42 GB | 4.51 | smaller 4-bit alternative, same imatrix |
GhostAI Pro uses MiniCPM5's ChatML framing and is text-only.
MiniCPM5-2B tokenizes <tool_call> / </tool_call> as special tokens. llama.cpp and
llama-server strip special tokens by default, which would delete the Hermes markers the
app parser needs. Serve with --special, disable reasoning extraction, and keep the empty
think block:
bash
llama-server -m ghostai-pro-Q4_K_M.gguf \-ngl 99 -c 8192 --jinja --special \--reasoning-format none \--chat-template-kwargs '{"enable_thinking": false}'
| File | Size | Notes |
|---|---|---|
model.safetensors | 5.0 GB | bf16 weights, epoch 1 (for further fine-tuning) |
ghostai-pro-Q4_K_M.gguf | 1.56 GB | imatrix 4-bit, production |
ghostai-pro-IQ4_XS.gguf | 1.42 GB | imatrix 4-bit alternative |
config.json, tokenizer*, chat_template.jinja |
ghost-ai-app-contract-v4 — 5,119 traces over 174/174 app tools
(2,847 tool-call, 1,984 grounded-answer, 288 chat), split 4,259 train / 860 held-out
by utterance template.SFTTrainer, DeepSpeed ZeRO-3, bf16, 2×A100-40GB),
lr 1e-5, effective batch 32, max length 2048, assistant-only loss.{% generation %} markers, so assistant-only loss
would silently fall back to full-sequence loss. Training used a copy of the upstream
template with the assistant branch wrapped in {% generation %}; the inference template
shipped here is the original.Base model: openbmb/MiniCPM5-2B, Apache-2.0.
| 0 |
| planted content reaching tool args | 0 | 0 |
| — |
| standard HF sidecars |