GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
sequelbox
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
sequelbox
Model Tree
Base
google/gemma-4-12B-it
Fine-tuned
this model
Input Modalities
Text
Audio
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
Tachibana-Agent uses the gemma-4-12B-it prompt format and the following recommended general structure:
Adherence to the specific format above is not required, but reflects the structure of the training data.
Example inference script to get started:
python
from transformers import AutoProcessor, AutoModelForCausalLMMODEL_ID = "sequelbox/gemma-4-12B-it-Tachibana-Agent"# Load modelprocessor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained(MODEL_ID,dtype="auto",device_map="auto")# Prepare the model inputprompt = "Implement CQRS for network appliance config management.\n\nRequirements:\n- Write side: 200 commands/sec, 4 command handlers, SQLite with custom journaling\n- Read side: 1000 queries/sec, 3 read projections in shared memory segments\n- Eventual consistency window: 100ms max\n- Handle atomic swap of projection memory for rebuilds\n- Binary configuration format versioning for schema evolution\n- Framework: libevent with custom protocol parser\n\nConstraints:\n- Manual memory management only, no garbage collection\n- Lock-free data structures where possible\n- Shared memory projections must survive process restarts\n- Command handlers must be thread-safe with 4 worker threads\n- Projection rebuild must not block queries\n- Binary format must support forward/backward compatibility\n- Error handling for corrupted journal recovery\n- Memory-mapped I/O for shared segments\n- Zero-copy where possible for performance\n\nDeliverables:\n1. Command processing pipeline with journaling\n2. Projection engine with shared memory management\n3. Query dispatcher with read-your-writes consistency\n4. Schema evolution system with versioned binary format\n5. Integration with libevent for network I/O\n6. Stress test showing 200 cmd/s + 1000 q/s sustained\n\nAssume x86_64 Linux, pthreads, atomic operations. No high-level frameworks."messages = [{"role": "user", "content": prompt},]# Process inputtext = processor.apply_chat_template(messages,tokenize=False,add_generation_prompt=True,enable_thinking=True)inputs = processor(text=text, return_tensors="pt").to(model.device)input_len = inputs["input_ids"].shape[-1]# Generate outputoutputs = model.generate(**inputs, max_new_tokens=20000)response = processor.decode(outputs[0][input_len:], skip_special_tokens=False)# Parse outputprocessor.parse_response(response)print(response)
Tachibana-Agent is one of our Experimental Reasoning Models.
Do as you will.