GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Praha-Labs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Praha-Labs
Model Tree
openbmb/MiniCPM5-2B
Input Modalities
Output Modalities
Supported Functionality
openbmb/MiniCPM5-2B12a3808a956f869c767195e9266b59c4d21d92e2SFTTrainerOnly assistant/TikZ tokens contributed to loss. Prompt tokens were masked and overlength examples were quarantined rather than truncated.
Loss is token-level cross-entropy against one reference TikZ implementation; it does not directly measure compilation or rendered-image similarity.
| Job ID | Name | State | Elapsed | Node |
|---|---|---|---|---|
| 4317286 | minicpm-native-full | TIMEOUT | 01:00:03 | a0429 |
| 4321521 | minicpm-native-full-r2 | TIMEOUT | 02:00:25 | a0429 |
| 4322440 | minicpm-native-full-r3 | TIMEOUT | 02:00:17 | a0429 |
| 4324001 | minicpm-native-full-r4 | TIMEOUT | 02:00:20 | a0429 |
| 4326352 | minicpm-native-full-r2 | TIMEOUT | 02:00:22 | a0429 |
| 4327247 | minicpm-native-final | COMPLETED | 01:08:11 | a0226 |
The standard Transformers PEFT integration can load the adapter using its recorded base-model reference:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "Praha-Labs/MiniCPM5-2B-TikZ-LoRA"tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( repo, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)Explicit PEFT loading against the pinned upstream base is also supported:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel repo = "Praha-Labs/MiniCPM5-2B-TikZ-LoRA"base = AutoModelForCausalLM.from_pretrained( "openbmb/MiniCPM5-2B", revision="12a3808a956f869c767195e9266b59c4d21d92e2", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained(repo)model = PeftModel.from_pretrained(base, repo)training-metrics.json, resolved-config.json, training-config.yaml,
native-run.json, token-report.json, training-jobs.tsv,
environment.lock, source-commit.txt, BASE_MODEL_CARD.md, and
SHA256SUMS document the run and its provenance.
Compilation rate, rendered-image similarity, and human evaluation should be measured before deployment because multiple valid TikZ programs can render the same diagram.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "Praha-Labs/MiniCPM5-2B-TikZ-LoRA"tokenizer = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( repo, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel repo = "Praha-Labs/MiniCPM5-2B-TikZ-LoRA"base = AutoModelForCausalLM.from_pretrained( "openbmb/MiniCPM5-2B", revision="12a3808a956f869c767195e9266b59c4d21d92e2", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True,)tokenizer = AutoTokenizer.from_pretrained(repo)model = PeftModel.from_pretrained(base, repo)