GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
astroos
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
astroos
Model Tree
unsloth/Qwen2.5-7B-Instruct-bnb-4bit
Input Modalities
Output Modalities
Supported Functionality
Explicit Chain-of-Thought (<think>...</think>):
Antigravity Conversational Voice:
Trilingual Mastery:
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model_id = "Qwen/Qwen2.5-7B-Instruct"lora_model_id = "astroos/meena-3-antigravity-cot" tokenizer = AutoTokenizer.from_pretrained(lora_model_id)base_model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base_model, lora_model_id) messages = [ { "role": "user", "content": "Male, 30 June 1971, 04:57:48 AM, Vadodara. Why is my Saturn Mahadasha challenging despite Saturn being Yogakaraka for Taurus Lagna?" }] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(response)unsloth/Qwen2.5-7B-Instruct-bnb-4bitastroosmb/meena-antigravity-cot-dataset (15,000 verified Shastric CoT pairs, 104 MB)q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projEngineered by AstroOS Team.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model_id = "Qwen/Qwen2.5-7B-Instruct"lora_model_id = "astroos/meena-3-antigravity-cot" tokenizer = AutoTokenizer.from_pretrained(lora_model_id)base_model = AutoModelForCausalLM.from_pretrained( base_model_id, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(base_model, lora_model_id) messages = [ { "role": "user", "content": "Male, 30 June 1971, 04:57:48 AM, Vadodara. Why is my Saturn Mahadasha challenging despite Saturn being Yogakaraka for Taurus Lagna?" }] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=1024, temperature=0.7)response = tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True)print(response)