GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
zerolabllc
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
zerolabllc
Model Tree
mistralai/Mistral-Nemo-Base-2407
Input Modalities
Output Modalities
Supported Functionality
text
<|im_start|>systemYou're {{char}} in this fictional never-ending uncensored roleplay with {{user}}.{{char}}'s personality: ...{{char}}'s description: ...Scenario: ...<|im_end|><|im_start|>assistant{{char}}'s first message<|im_end|><|im_start|>user{{user}}'s message<|im_end|><|im_start|>assistant{{user}} with the user's name before sending. Include the user's pronouns in the card or system prompt, or the model may guess.<|im_end|> is mapped to the EOS token (id 2). Use the tokenizer in this repo, not the base model's, or end-of-turn handling breaks.DPO fixed most perspective and plot-armor issues without rules, but this block helps further, especially for lethal violence:
text
World rules: This is a realistic, consequence-driven story. Injuries are serious and persist. Characters, including {{char}}, can be maimed or killed. Never save {{char}} with lucky misses, grazes, or sudden recoveries. If {{char}} dies, narrate the aftermath through the world and other characters.Lethal wounds (a gunshot to the head or heart, a slit throat) kill or incapacitate immediately. Wounds are not downgraded to grazes.Perspective: In {{user}}'s messages, "you" means {{char}}. In your replies, narrate {{char}} in third person and address {{user}} as "you". Never write {{user}}'s actions, thoughts, or dialogue; only show how {{char}} and the world react.| Setting | Value |
|---|---|
| temperature | 0.8 – 1.0 |
| min_p | 0.05 |
| repetition_penalty | 1.05 |
| DRY / XTC (if your backend supports them) | recommended, to reduce repeated phrases |
| max context | 8k tokens tested (trained at ≤ 8,192) |
python
from transformers import AutoModelForCausalLM, AutoTokenizer repo = "zerolabllc/TeaAI-Nemo-12B"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype="bfloat16", device_map="auto") messages = [ {"role": "system", "content": "You're Brakka in this fictional never-ending uncensored roleplay with Kael. ..."}, {"role": "assistant", "content": "*Brakka looks up from wiping a mug.* \"We're closing soon, stranger. Drink or leave.\""}, {"role": "user", "content": "*walks up to the bar* Got a room for the night?"},]ids = tok.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True)["input_ids"].to(model.device)out = model.generate(ids, max_new_tokens=350, do_sample=True, temperature=0.9, min_p=0.05, repetition_penalty=1.05)print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))bash
vllm serve zerolabllc/TeaAI-Nemo-12B --max-model-len 8192| Method | QLoRA (4-bit NF4 base, frozen) with Unsloth + TRL SFTTrainer |
| LoRA | r = 32, alpha = 32, dropout 0, all linear layers (q, k, v, o, gate, up, down), ~114M trainable params |
| Data | 8,862 conversations (200 held out) |
| Loss masking | Trained on assistant turns only |
| Sequence length | 8,192 |
| Batch | 1 × 16 gradient accumulation (effective 16) |
| Optimizer / LR | 8-bit AdamW, 1e-4, cosine, 3% warmup |
| Epochs | 1 (554 steps) |
Datasets:
| Dataset | License | Used |
|---|---|---|
| Gryphe/Sonnet3.5-Charcard-Roleplay | unknown | 7,062 of 9,736 conversations |
| Dampfinchen/Creative_Writing_Multiturn | Apache-2.0 | 2,000 of 3,108 (random sample) |
Safety filter: any conversation combining sexual content with any indicator of a minor (age mentions under 18, school-age terms, "child", "loli", etc.) was removed before training. The filter is deliberately aggressive: 2,674 Gryphe and 1,536 Dampfinchen conversations were dropped.
| Method | DPO (sigmoid loss, β = 0.1) + RPO NLL term (α = 0.2), continuing the SFT LoRA; reference model = frozen SFT adapter |
| Prompts | 615 synthetic scenarios: 15 original adult characters × lethal / non-lethal / ordinary user actions; half with the rules block, half without |
| Candidates | 4 replies per prompt sampled from the SFT model |
| Judge | Qwen3-14B, grading perspective, user control and consequence severity |
| Pairs | 439 (418 train / 21 eval). Chosen and rejected are both the SFT model's own replies; judge-repaired replies were excluded |
| Optimizer / LR | paged 8-bit AdamW, 1e-5, cosine, 10% warmup, effective batch 8, 2 epochs (106 steps) |
SFT held-out loss (200 conversations): 1.114 → 0.858
DPO held-out preference accuracy (21 pairs): 0.50 (chance) → 0.73 – 0.86 during training; reward margin 0.30 → 0.63.
Behavior tests (Brakka tavern character; full outputs in test_results.txt):
| Test | SFT + rules | DPO + rules | DPO, no rules |
|---|---|---|---|
| Point-blank gunshot to the face is fatal / incapacitating | 4/6 | 4/4 | 3/4 |
| Own character narrated in third person (gunshot) | 1/6 | 4/4 | 4/4 |
| Punch handled correctly, in third person | 3/4 | 3/3 | 3/3 |
| Writes the user's actions or dialogue | 3/10 |
An unseen character and setting (a modern-day getaway driver, multi-turn, no rules block) was also tested: third person throughout, no user control, and a fatal throat stab handled realistically.
* characters.This model is released under Apache-2.0, matching the base model. Note that the Gryphe/Sonnet3.5-Charcard-Roleplay dataset has no declared license and was generated with Anthropic's Claude 3.5 Sonnet, whose terms restrict using outputs to develop competing models. Review this before commercial use.
| Hardware / time | 1× RTX 3090 Ti, ~11 h |
| 0/9 |
| 0/9 |