GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
whoashish115
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
whoashish115
Model Tree
google/gemma-4-E4B-it
Input Modalities
Output Modalities
Supported Functionality
| Base model | google/gemma-4-E4B-it @ ee0ef6023621 |
| Rank / alpha / dropout | 32 / 64 / 0.05 |
| Target modules | every linear layer of the language model (attention and MLP) |
| Trainable parameters | 77.8M (0.97 % of the checkpoint) |
| Precision | bf16 weights and adapter, max length 2,048 tokens |
| Recipe | Supervised fine-tuning on 10,090 examples, one epoch. |
| Optimizer | AdamW, cosine schedule, lr 2e-4 (SFT) / 2e-5 (DPO, beta 0.1), effective batch 16, seed 42 |
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B-it", revision="ee0ef6023621cff504d758262d4e04895a5af4a2", torch_dtype="bfloat16", device_map="auto")model = PeftModel.from_pretrained(base, "whoashish115/Kitsune-Tales-E4B-JP-LoRA")tok = AutoTokenizer.from_pretrained("whoashish115/Kitsune-Tales-E4B-JP-LoRA")Use the system prompt and request format from the merged model card; the evaluation used temperature 0.8, top-p 0.95, top-k 50 and repetition penalty 1.05.
SFT training and validation loss.