GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
Eyght
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
Eyght
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Model | eyght-new-sft |
| Base model | Qwen/Qwen2.5-1.5B-Instruct |
| Architecture | Qwen2ForCausalLM (decoder-only transformer) |
| Parameters | ~1.54 B total · ~40 M LoRA trainable (~2.6% of weights) |
| Format | LoRA adapter (PEFT) |
| Context length | 512 tokens (fine-tune); base supports up to 32k |
| Language | English |
| License | Apache-2.0 (fine-tune) · base model per its own license |
After loading the packaged GGUF into Ollama:
bash
ollama run eyght-new-sft
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase = "Qwen/Qwen2.5-1.5B-Instruct"tok = AutoTokenizer.from_pretrained(base)model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="auto", device_map="auto")model = PeftModel.from_pretrained(model, "Eyght/eyght-new-sft")model.eval()prompt = ("Below is an instruction that describes a task. Write a response that completes the request.\n\n""### Instruction:\nWrite a Python function that returns the nth Fibonacci number.\n\n""### Input:\n\n\n### Response:\n")print(tok.decode(model.generate(**tok(prompt, return_tensors="pt").to(model.device), max_new_tokens=120)[0]))
| Method | Supervised fine-tuning (LoRA SFT) |
| Base | Qwen/Qwen2.5-1.5B-Instruct |
| Dataset | synthgen_mixed + glm_sft (~2,500 modern web-dev coding examples) |
| LoRA rank / alpha | 16 / 16 |
| Epochs | 1 |
| Learning rate | 2e-4 |
| Max sequence length | 512 |
| Batch / grad-accum |
The alpaca prompt format was used:
markdown
Below is an instruction that describes a task. Write a response that completes the request.### Instruction:{instruction}### Input:{input}### Response:{output}
"*Verified by Synthetic Engine*" watermark line (a dataset artifact); trim if unwanted.bibtex
@misc{eyght_new_sft,title = {eyght-new-sft: a coding and reasoning LoRA fine-tune of Qwen2.5-1.5B-Instruct},author = {Eyght},year = {2026},howpublished = {Hugging Face, https://huggingface.co/Eyght/eyght-new-sft}}
Built by Eyght with the Eyght Veta local AI studio. Free model repository — owned, not a paid Space.
This model is designed to operate within Project Janus, a dual-loop cognitive architecture that goes beyond simple prompt-response:
Perceive → Working Memory → Internal Critic → Action → Consolidation
| Phase | Component | Function |
|---|---|---|
| 1. Perceive | Input mapping | Raw data → dense vector space |
| 2. Working Memory | Dynamic scratchpad | Active goal, hypotheses, constraints |
| 3. Internal Critic | Value function | Evaluates outputs before execution (quality + safety) |
| 4. Action | Response delivery | Approved output delivered to the user |
| 5. Consolidation | Durable memory | Successful strategies stored for future retrieval |
The Internal Critic evaluates every draft response against core value axioms before delivery. This enables self-correction, memory-augmented reasoning (RAG), and continuous learning without catastrophic forgetting.
Built by Eyght. Project Janus — a cognitive architecture, not just a model.
| 1 / 8 (effective 8) |
| Optimizer | AdamW (8-bit) |
| LR schedule | Cosine |
| Hardware | 1× NVIDIA RTX 4070 Ti (12 GB) |
| Framework | Unsloth (4-bit + LoRA) |