GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
hharsha
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
hharsha
Model Tree
HuggingFaceTB/SmolLM-135M
Input Modalities
Output Modalities
Supported Functionality
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "HuggingFaceTB/SmolLM-135M"tok = AutoTokenizer.from_pretrained("hharsha/agentic-rag-lora")model = AutoModelForCausalLM.from_pretrained(base)model = PeftModel.from_pretrained(model, "hharsha/agentic-rag-lora") prompt = "Explain hybrid search in a RAG pipeline:"inputs = tok(prompt, return_tensors="pt")print(tok.decode(model.generate(**inputs, max_new_tokens=64)[0], skip_special_tokens=True))| Base | HuggingFaceTB/SmolLM-135M |
| Method | PEFT LoRA (r=8, alpha=16, q_proj/v_proj) |
| Epochs | 1 (CPU, float32) |
| Trainable params | ~461k (0.34%) |
| Data | Showcase project summaries + synthetic agentic/RAG instructions |
hharsha/agentic-systems-minilmhharsha/agentic-github-taggerhharsha/agentic-systems-showcasehharsha/agentic-github-metafrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "HuggingFaceTB/SmolLM-135M"tok = AutoTokenizer.from_pretrained("hharsha/agentic-rag-lora")model = AutoModelForCausalLM.from_pretrained(base)model = PeftModel.from_pretrained(model, "hharsha/agentic-rag-lora") prompt = "Explain hybrid search in a RAG pipeline:"inputs = tok(prompt, return_tensors="pt")print(tok.decode(model.generate(**inputs, max_new_tokens=64)[0], skip_special_tokens=True))