GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Saikrishna2511
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
Saikrishna2511
Model Tree
Qwen/Qwen2.5-Coder-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Try the model in the browser: https://huggingface.co/spaces/Saikrishna2511/qwen-multitask-demo
This single checkpoint handles three tasks via different prompt prefixes:
nl2py)text
### Instruction: Write Python for: {natural language description}### Response:java2py)text
### Translate Java to Python:```java{java code}python
undefinedcode2doc)text
### Generate documentation for this Python code:```python{python code}text
## Training - **Base model:** [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct)- **Stage 1:** Java→Python LoRA fine-tune on AVATAR-TC- **Stage 2:** Multi-task LoRA on NL2Py, Code2Doc, code comments, and Java2Py replay- **Method:** LoRA (r=16, alpha=32), merged weights for inference ## Usage ```pythonfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torch model_id = "Saikrishna2511/qwen-multitask"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_id, trust_remote_code=True, torch_dtype=torch.float16, device_map="auto",) prompt = "### Instruction: Write Python for: return the factorial of n\n### Response:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2, top_p=0.95)print(tokenizer.decode(outputs[0], skip_special_tokens=True))For post-processing and all three task templates, see the project repo or the linked Gradio Space.
## Training- **Base model:** [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct)- **Stage 1:** Java→Python LoRA fine-tune on AVATAR-TC- **Stage 2:** Multi-task LoRA on NL2Py, Code2Doc, code comments, and Java2Py replay- **Method:** LoRA (r=16, alpha=32), merged weights for inference## Usage```pythonfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torchmodel_id = "Saikrishna2511/qwen-multitask"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained( model_id, trust_remote_code=True, torch_dtype=torch.float16, device_map="auto",)prompt = "### Instruction: Write Python for: return the factorial of n\n### Response:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2, top_p=0.95)print(tokenizer.decode(outputs[0], skip_special_tokens=True))