GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
rishiraj
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
rishiraj
Model Tree
Input Modalities
Output Modalities
Supported Functionality
fd2ecb30)This model is compatible with standard inference backends like vLLM.
python
# Example: Running your Sovereign Modelfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "rishiraj/smolified-tiny-text-to-sql"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") messages = [ {'role': 'system', 'content': '''You are a SQL generator. Schema: Table 'orders' (id, customer_name, amount, status, date). Translate the user question into a valid SQLite query. Output SQL only.'''}, {'role': 'user', 'content': '''What's the earliest order date recorded?'''}]text = tokenizer.apply_chat_template( messages, tokenize = False, add_generation_prompt = True,).removeprefix('<bos>') from transformers import TextStreamer_ = model.generate( **tokenizer(text, return_tensors = "pt").to("cuda"), max_new_tokens = 1000, temperature = 1, top_p = 0.95, top_k = 64, streamer = TextStreamer(tokenizer, skip_prompt = True),)This model weights are a sovereign asset owned by rishiraj. Generated via Smolify.ai.
# Example: Running your Sovereign Modelfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "rishiraj/smolified-tiny-text-to-sql"tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") messages = [ {'role': 'system', 'content': '''You are a SQL generator. Schema: Table 'orders' (id, customer_name, amount, status, date). Translate the user question into a valid SQLite query. Output SQL only.'''}, {'role': 'user', 'content': '''What's the earliest order date recorded?'''}]text = tokenizer.apply_chat_template( messages, tokenize = False, add_generation_prompt = True,).removeprefix('<bos>') from transformers import TextStreamer_ = model.generate( **tokenizer(text, return_tensors = "pt").to("cuda"), max_new_tokens = 1000, temperature = 1, top_p = 0.95, top_k = 64, streamer = TextStreamer(tokenizer, skip_prompt = True),)