GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
sfanm
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
sfanm
Model Tree
sfanm/d24-v6-midtrain
Input Modalities
Output Modalities
Supported Functionality
| Field | Value |
|---|---|
| Parameters | 756,819,456 |
| Layers / hidden size | 24 / 1,536 |
| Attention heads | 12 (MHA) |
| FFN size | 4,096 (SwiGLU/SiLU) |
| Tokenizer | GPT-2 BPE, vocabulary padded to 50,304 |
| Context | 2,048 tokens |
| Published weights | BF16 |
| Global / micro batch | 128 / 1 |
| Peak / minimum LR | 1e-4 / 1e-5 |
| Schedule | 50-step warmup, cosine decay |
Final in-distribution SFT validation loss was 0.763008 (perplexity 2.145).
text
<|im_start|>user...<|im_end|><|im_start|>assistant...
<|im_end|> is a literal GPT-2-tokenized string, not a registered special
token. Generation must stop on that string.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "sfanm/d24-v6-sft"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto").eval()messages = [{"role": "user", "content": "What is 2+2?"}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)output = model.generate(**inputs,max_new_tokens=512,stop_strings=["<|im_end|>"],tokenizer=tokenizer,)
For vLLM, set stop=["<|im_end|>"]. Both retained, resumable Megatron
distributed checkpoints are published under megatron/iter_0001600 and
megatron/iter_0001773.
This experimental research model can produce incorrect, biased, or unsafe text. It has not undergone a comprehensive capability or safety evaluation and must not be used for high-stakes decisions.