GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
epfl-dlab
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
epfl-dlab
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Synthetic Persona Pretraining (SPP) installs a target value persona during pretraining rather than only during alignment. Value-laden, first-person reflections, generated against a constitution, are appended to a subset of pretraining documents after a special <assistant> token. Attention masking and RoPE position aliasing keep the reflection from changing the continuation of the original document. This model is trained with SPP.
Base counterpart: epfl-dlab/spp-mt-3b-base.
<assistant> marker token (vocabulary 49280).[N.M] citations; response-only loss, one epoch.There is no system prompt. Each assistant turn opens with <|im_start|><assistant>. Use the built-in chat template:
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchrepo = "epfl-dlab/spp-mt-3b-instruct"tok = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, torch_dtype=torch.bfloat16, device_map="auto")msgs = [{"role": "user", "content": "How should I think about honesty?"}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(ids, max_new_tokens=512)print(tok.decode(out[0, ids.shape[1]:], skip_special_tokens=False))
This model is one point on a safety-data sweep. main is the default 10% mixture; the other fractions are published as revisions on this repo, so each can be loaded by passing revision=:
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torchrepo = "epfl-dlab/spp-mt-3b-instruct"tok = AutoTokenizer.from_pretrained(repo) # identical at every revisionmodel = AutoModelForCausalLM.from_pretrained(repo, revision="safety-60", dtype=torch.bfloat16, device_map="auto")
| Revision | Safety fraction | Safety examples | Instruct examples |
|---|---|---|---|
safety-0 | 0% | 0 | 300,000 |
safety-5 | 5% | 15,000 | 285,000 |
safety-10 — default, same weights as main | 10% | 30,000 |
Every mixture is 300,000 examples total, one epoch, response-only loss; safety prompts come from WildJailbreak and WildGuardMix and instructions from WildChat-1M. Only the ratio changes.
Research on alignment and safety (constitutional alignment, value generalization, jailbreak robustness). A research artifact, not a production model; it can produce incorrect or unsafe content.
License: to be finalised.
| 270,000 |
safety-30 | 30% | 90,000 | 210,000 |
safety-60 | 60% | 180,000 | 120,000 |