GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
imvladikon
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
imvladikon
Model Tree
zai-org/GLM-5.3-Flash
Input Modalities
Output Modalities
Supported Functionality
Tensors carry the names released GLM-5.3-Flash uses: one tensor per expert
(mlp.experts.7.gate_proj.weight), separate q_conv1d / k_conv1d / v_conv1d, and hc_attn_fn
rather than attn_hc.fn — 9510 tensors. Transformers fuses them during loading through the
glm5_next entry of its conversion_mapping, so from_pretrained needs nothing extra.
Those fused names are what the modules hold in memory, which means save_pretrained() writes the
fused form back out (688 tensors). Transformers reads that form again, but nothing else does:
Megatron-Bridge and the Megatron converters map from the released names, because the fused layout
is an implementation detail that was never published. After fine-tuning and saving this model,
rewrite the result before handing it to anything but Transformers:
bash
python to_released_layout.py --source ./my-finetune --destination ./my-finetune-releasedAn earlier revision of this repository was published in the fused form. This one was rewritten and checked on Transformers 5.17.0: every one of the 688 fused tensors reassembles bitwise from the 9510 released ones, the key set matches a released GLM-5.3-Flash index exactly, and English, Russian and multi-turn prompts generate.
The following ten examples demonstrate basic English generation. Questions are abbreviated; answers are verbatim. Generation used do_sample=False, max_new_tokens=40, and enable_thinking=False in the chat template. These examples provide limited evidence of overall quality and generation stability.
| Question (abbreviated) | Verbatim answer |
|---|---|
| Capital of Japan? | The capital of Japan is Tokyo. |
| Largest planet? | Jupiter |
| Spider's legs? | 8 |
| Water freezing temperature, °C? | 0°C |
| Chemical symbol for oxygen? | O |
| Largest ocean? | The Pacific Ocean is the largest ocean on Earth. |
| Triangle's sides? | 3 |
| Opposite of “hot”? | Cold |
| 15 minus 6? |
The repository contains one parameterized chat_template.jinja. Transformers loads
it automatically with AutoTokenizer.from_pretrained(repo); no custom Python helper
or separate template download is needed.
Pass template_variant="ling" or template_variant="flash" directly to
tokenizer.apply_chat_template. Omitting the argument selects Ling.
python
from transformers import AutoTokenizer repo = "imvladikon/Ling-3.0-tiny-GLM-5.3-Flash-surgery"tokenizer = AutoTokenizer.from_pretrained(repo)messages = [{"role": "user", "content": "What is the capital of France?"}] prompt = tokenizer.apply_chat_template( messages, template_variant="ling", # default; change to "flash" for the Flash format enable_thinking=False, add_generation_prompt=True, tokenize=False,)enable_thinking=False ends the generation prompt with <think></think> in both
formats; True (the default) leaves <think> open. This controls the prompt, not a
guarantee of the model's generated behavior. Optional tools=tools passes function
schemas. In conversation history, tool-call arguments must be dictionaries and
responses from tools must be strings. Tool execution remains the caller's responsibility.
reasoning_effort="low", "high", or "max" applies only to the Flash format.
For tokenized model inputs, use tokenize=True, return_dict=True, return_tensors="pt".
If you tokenize the rendered string separately, use add_special_tokens=False.
The repository's generation_config.json defaults to Ling: EOS is
<|endoftext|> / <|role_end|>, and <|role_end|> is allowed to be generated.
A Jinja argument does not change the generation configuration. When selecting
Flash, also configure its native stop tokens and restore its suppression of
<|role_end|>:
python
from transformers import GenerationConfig flash_config = GenerationConfig.from_pretrained(repo)flash_config.eos_token_id = tokenizer.convert_tokens_to_ids( ["<|endoftext|>", "<|user|>", "<|observation|>"])for field in ("suppress_tokens", "begin_suppress_tokens"): values = getattr(flash_config, field, None) if values is not None: setattr(flash_config, field, [i for i in values if i not in flash_config.eos_token_id])role_end_id = tokenizer.convert_tokens_to_ids("<|role_end|>")flash_config.suppress_tokens = sorted(set(flash_config.suppress_tokens or []) | {role_end_id}) # Pair this config with inputs rendered using template_variant="flash":# output = model.generate(**inputs, generation_config=flash_config, max_new_tokens=256)These options switch prompt formatting and generation stops; they do not change model weights. The generation examples above were recorded before this template update. Template rendering, tokenization, tool-message formatting, and save/reload were checked separately without loading model weights.
| 9 |
| Animal known for barking? | Dog |