GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Raiff1982
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Raiff1982
Model Tree
meta-llama/Meta-Llama-3-8B
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| Base model | meta-llama/Meta-Llama-3-8B |
| Method | LoRA (Low-Rank Adaptation) |
| LoRA rank (r) | 32 |
| LoRA alpha | 64 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Dropout | 0.05 |
| Task type | CAUSAL_LM |
| Trainable params | 83.9M (1.03% of 8.1B) |
| Training data | Raiff1982/codette_gptoss20b (5,016 examples) |
| Framework | PEFT / Transformers / TRL |
Codette is designed for multi-perspective reasoning tasks. It processes queries through six reasoning perspectives:
python
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch # Optional: 4-bit quantization for lower VRAM usagebnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) # Load base modelbase_model = "meta-llama/Meta-Llama-3-8B"tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, quantization_config=bnb_config, device_map="auto",) # Apply Codette LoRAmodel = PeftModel.from_pretrained(model, "Raiff1982/codette-llama3.1-8b-lora")model.eval() # Generateprompt = "### Instruction:\nWhat is consciousness?\n\n### Response:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)print(tokenizer.decode(outputs[0], skip_special_tokens=True))python
merged = model.merge_and_unload()merged.save_pretrained("codette-8b-merged")tokenizer.save_pretrained("codette-8b-merged")Trained on the Codette RC+ξ dataset (codette_gptoss20b_master_v3.jsonl) containing 5,016 instruction-output pairs. Each example encodes multi-perspective reasoning with epistemic tension metadata:
json
{ "instruction": "Respond from Newton perspective to: What is consciousness?", "output": "[Newton Perspective] As I process this inquiry...", "metadata": { "framework": "rc_xi", "perspective": "Newton", "epistemic_tension": 1.886 }}Training format:
text
### Instruction:{instruction} ### Response:{output}| Hyperparameter | Value |
|---|---|
| Learning rate | 2e-4 |
| Per-device batch size | 2 |
| Gradient accumulation | 8 |
| Effective batch size | 16 |
| Epochs | 3 |
| Warmup ratio | 0.05 |
| LR scheduler | Cosine |
| Max grad norm | 1.0 |
| Max sequence length | 2048 |
Evaluated on HumanEval (164 Python coding tasks, pass@1, greedy decoding) using 4-bit NF4 quantization on an A100-SXM4-80GB.
| Model | pass@1 |
|---|---|
| Codette Llama-3-8B-LoRA | 20.7% |
| Llama-3-8B (base) | ~33% |
| Llama-3.1-8B-Instruct | ~50% |
Note: Codette scores below the base model on code benchmarks because it was fine-tuned exclusively on RC+ξ multi-perspective reasoning data, not code. Its strengths are in philosophical reasoning, epistemic tension analysis, and multi-perspective synthesis. See Limitations for details.
### Instruction / ### Response prompt formatbibtex
@misc{codette2026, title={Codette: Multi-Perspective AI with Recursive Continuity}, author={Harrison, Jonathan}, year={2026}, publisher={Raiff's Bits}, url={https://huggingface.co/Raiff1982/codette-llama3.1-8b-lora}}MIT
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfigfrom peft import PeftModelimport torch # Optional: 4-bit quantization for lower VRAM usagebnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16,) # Load base modelbase_model = "meta-llama/Meta-Llama-3-8B"tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, quantization_config=bnb_config, device_map="auto",) # Apply Codette LoRAmodel = PeftModel.from_pretrained(model, "Raiff1982/codette-llama3.1-8b-lora")model.eval() # Generateprompt = "### Instruction:\nWhat is consciousness?\n\n### Response:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, top_p=0.9)print(tokenizer.decode(outputs[0], skip_special_tokens=True))merged = model.merge_and_unload()merged.save_pretrained("codette-8b-merged")tokenizer.save_pretrained("codette-8b-merged"){ "instruction": "Respond from Newton perspective to: What is consciousness?", "output": "[Newton Perspective] As I process this inquiry...", "metadata": { "framework": "rc_xi", "perspective": "Newton", "epistemic_tension": 1.886 }}### Instruction:{instruction}### Response:{output}@misc{codette2026, title={Codette: Multi-Perspective AI with Recursive Continuity}, author={Harrison, Jonathan}, year={2026}, publisher={Raiff's Bits}, url={https://huggingface.co/Raiff1982/codette-llama3.1-8b-lora}}