GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Kus-hal
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Kus-hal
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
For a prompt such as Screen this resume for a Backend Engineer position and return a structured verdict. followed by the resume, the model returns:
json
{ "role": "Backend Engineer", "ats_score": 56, "verdict": "moderate_match", "matched_skills": ["Python", "PostgreSQL", "Docker", "Kubernetes"], "missing_skills": ["Java", "REST APIs", "Redis"], "years_experience": 4}Verdicts follow the training data: strong_match (ats_score 75-100), moderate_match (50-74) and weak_match (8-48).
python
import jsonimport refrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "Qwen/Qwen2.5-0.5B-Instruct"tokenizer = AutoTokenizer.from_pretrained(base_id)base = AutoModelForCausalLM.from_pretrained(base_id)model = PeftModel.from_pretrained(base, "Kus-hal/resume-screener-lora") prompt = ( "Screen this resume for a Backend Engineer position and return a structured verdict.\n\n" "Resume: 4 years of backend experience. Skilled in Python, PostgreSQL, Docker, Kubernetes.")inputs = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True,)output = model.generate(**inputs, max_new_tokens=200, do_sample=False)text = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(json.loads(re.search(r"\{.*\}", text, re.DOTALL).group(0)))data/generate_dataset.py in the GitHub repo| Metric | Zero-shot base | Zero-shot + score ranges in prompt | This adapter |
|---|---|---|---|
| Valid JSON rate | 100% | 100% | 100% |
| Verdict accuracy | 17.7% | 18.8% | 88.5% |
| Mean absolute score error | 32.0 | 35.1 | 5.4 |
strong_match there).{ "role": "Backend Engineer", "ats_score": 56, "verdict": "moderate_match", "matched_skills": ["Python", "PostgreSQL", "Docker", "Kubernetes"], "missing_skills": ["Java", "REST APIs", "Redis"], "years_experience": 4}import jsonimport refrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base_id = "Qwen/Qwen2.5-0.5B-Instruct"tokenizer = AutoTokenizer.from_pretrained(base_id)base = AutoModelForCausalLM.from_pretrained(base_id)model = PeftModel.from_pretrained(base, "Kus-hal/resume-screener-lora") prompt = ( "Screen this resume for a Backend Engineer position and return a structured verdict.\n\n" "Resume: 4 years of backend experience. Skilled in Python, PostgreSQL, Docker, Kubernetes.")inputs = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True,)output = model.generate(**inputs, max_new_tokens=200, do_sample=False)text = tokenizer.decode(output[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)print(json.loads(re.search(r"\{.*\}", text, re.DOTALL).group(0)))