GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Salahin
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
Salahin
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| File | Format | Size | Best For |
|---|---|---|---|
model.safetensors | FP16 | ~980 MB | Transformers, PyTorch, HF Serverless API, GPU inference |
model-q4_k_m.gguf | Q4_K_M | ~380 MB | llama.cpp, fast CPU inference, mobile/desktop local apps |
python
import jsonimport reimport torchfrom transformers import AutoModelForCausalLM, AutoTokenizer MODEL_ID = "Salahin/youtube-audiobook-title-parser" tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)model = AutoModelForCausalLM.from_pretrained( MODEL_ID, torch_dtype=torch.float16, device_map="auto")model.eval() def parse_title(title: str) -> dict: messages = [ { "role": "system", "content": "Extract book title, author, and channel as JSON. Keep Bengali in Bengali script." }, {"role": "user", "content": title} ] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = tokenizer([prompt], return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=80, do_sample=False, eos_token_id=tokenizer.convert_tokens_to_ids("<|im_end|>") ) text = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True).strip() match = re.search(r'\{.*?\}', text, re.DOTALL) return json.loads(match.group(0)) if match else {"raw": text} # Exampleprint(parse_title("হিমুর হাতে কয়েকটি নীলপদ্ম 1/2 | Humayun Ahmed | Golpokothon"))# Output: {'book_title': 'হিমুর হাতে কয়েকটি নীলপদ্ম', 'author': 'Humayun Ahmed', 'channel': 'Golpokothon'}Install llama-cpp-python:
bash
pip install llama-cpp-python huggingface-hubpython
import jsonimport refrom huggingface_hub import hf_hub_downloadfrom llama_cpp import Llama # Download quantized GGUF binary (~380 MB)model_path = hf_hub_download( repo_id="Salahin/youtube-audiobook-title-parser", filename="model-q4_k_m.gguf") llm = Llama( model_path=model_path, n_ctx=512, n_threads=4, # Adjust to your CPU core count verbose=False) def parse_title_cpu(title: str) -> dict: prompt = ( "<|im_start|>system\n" "Extract book title, author, and channel as JSON. Keep Bengali in Bengali script.<|im_end|>\n" f"<|im_start|>user\n{title}<|im_end|>\n" "<|im_start|>assistant\n" ) output = llm( prompt, max_tokens=80, stop=["}", "<|im_end|>"], temperature=0.0 ) raw = output["choices"][0]["text"].strip() if not raw.endswith("}"): raw += "}" match = re.search(r'\{.*?\}', raw, re.DOTALL) return json.loads(match.group(0)) if match else {"raw": raw} # Exampleprint(parse_title_cpu("Golpokothon Presents | হিমুর হাতে কয়েকটি নীলপদ্ম | হুমায়ূন আহমেদ"))The training data is available directly in this repository: dataset.jsonl.
It comprises 600 synthetic and curated title variations addressing real-world edge cases:
|, -, :, /)Channel Presents | Title | Author)1/2, ১ম পর্ব, [HD], Full Audiobook)Qwen/Qwen2.5-0.5B-Instructr: 16lora_alpha: 32target_modules: ["q_proj", "k_proj", "v_proj", "o_proj"]lora_dropout: 0.05learning_rate: 3e-4 (Cosine schedule)epochs: 3optimizer: adamw_torch