GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sasa2000
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
sasa2000
Model Tree
OpenGVLab/InternVL3_5-8B
Input Modalities
Output Modalities
Supported Functionality
OpenGVLab/InternVL3_5-8B9bb6a56ad9cc69db95e2d4eeb15a52bbcac4ef79InternVLChatModelqwen3Qwen3ForCausalLMvision_model.* and InternVL bridge mlp1.*safetensorsThe original VLM config stores the text backbone under llm_config and the weights under
language_model.*. The extracted checkpoint strips that prefix and writes a standalone Qwen3
CausalLM config for AutoModelForCausalLM.
Validated locally with Transformers:
AutoConfig.from_pretrained(...) loads as Qwen3ConfigAutoTokenizer.from_pretrained(...) loads successfullyAutoModelForCausalLM.from_pretrained(..., torch_dtype="auto", low_cpu_mem_usage=True) loads as Qwen3ForCausalLM(1, 1, 151936)model.safetensors.index.jsonpython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "sasa2000/internvl3-5-8b-text-only" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto",) inputs = tokenizer("Explain why the sky looks blue.", return_tensors="pt").to(model.device)with torch.no_grad(): output_ids = model.generate(**inputs, max_new_tokens=128) print(tokenizer.decode(output_ids[0], skip_special_tokens=True))This checkpoint is text-only. Image and video inputs are not supported because the vision encoder, InternVL bridge, processor assets, and related preprocessing files were removed.
Please review the upstream model card and license for the original model's intended use, limitations, and terms.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "sasa2000/internvl3-5-8b-text-only" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype="auto", device_map="auto",) inputs = tokenizer("Explain why the sky looks blue.", return_tensors="pt").to(model.device)with torch.no_grad(): output_ids = model.generate(**inputs, max_new_tokens=128) print(tokenizer.decode(output_ids[0], skip_special_tokens=True))