GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
HIMANSHUKUMARJHA
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
HIMANSHUKUMARJHA
Model Tree
openbmb/MiniCPM5-1B
Input Modalities
Output Modalities
Supported Functionality
| Metric | Value |
|---|---|
| Eval loss (200 held-out rows) | 0.8707 |
| Previous published adapter | 0.9127 |
The eval gate published this version only because it beat the stored previous best on the same fixed holdout.
Caveat on the metric. Eval loss measures token prediction, not whether generated code runs. Treat it as a training-health signal rather than a capability benchmark; pass@1 on HumanEval or MBPP would be the meaningful measure and is not yet wired up.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase = "openbmb/MiniCPM5-1B"tokenizer = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(model, "HIMANSHUKUMARJHA/minicpm5-1b-code-lora")messages = [{'role': 'user', 'content': 'Write a Python function that reverses a linked list.'}]inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)inputs.pop("token_type_ids", None) # this architecture's generate() rejects itout = model.generate(**inputs, max_new_tokens=256)print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
Requires transformers>=4.51, which is the first version that reads MiniCPM's standalone chat_template.jinja.
| Base model | openbmb/MiniCPM5-1B |
| Dataset | m-a-p/CodeFeedback-Filtered-Instruction |
| Training rows | 60,000 |
| Steps | 6,000 (~1.6 epochs at effective batch 16) |
| LoRA rank / alpha | 32 / 64 |
| Target modules | attention + MLP projections |
| LR schedule | 0.0002 cosine, 3% warmup |
Reproduced with AutoTune:
bash
modal run finetune.py --profile code
The dataset is shuffled with a fixed seed, then a 200-row holdout is taken before training. Rows the formatter cannot parse are dropped and exact duplicates removed, because these datasets contain repeats that would otherwise leak holdout examples into training.
12,515 exact duplicates were removed from this dataset before training.
Note on the metric. Eval loss measures token prediction, not whether generated code runs. Treat it as a training-health signal, not a capability benchmark. Pass@1 on HumanEval or MBPP would be the meaningful measure.
This is a 1B parameter model. It is useful for coding assistance at small scale and for on-device or cost-sensitive settings, but it will not match a large general model. Outputs should be validated before use. The adapter inherits any bias present in the training dataset.
| Precision | bfloat16 |
| Hardware | 1x A100 |