GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
keshavsharma
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
keshavsharma
Model Tree
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Input Modalities
Output Modalities
Supported Functionality
TinyLlama/TinyLlama-1.1B-Chat-v1.0smangrul/ad-copy-generationThe model is designed to take a product and its description and generate advertising copy.
The model expects:
text
Product: Fitness MagazineDescription: Fitness magazine for staying active and achieving your fitness goals.For example:
text
Stay active with a Fitness Magazine! 💪📖 Experience fitness tips and motivating stories. Perfect for fitness enthusiasts and reaching your health and wellness goals.The training prompt instructs the model to:
Create a text ad given the following product and description. Output only the Ad Copy and nothing else.
The model was fine-tuned using LoRA with the following configuration:
| Parameter | Value |
|---|---|
LoRA rank (r) | 32 |
| LoRA alpha | 64 |
| LoRA dropout | 0.1 |
| Learning rate | 2e-4 |
| Epochs | 3 |
| LR scheduler | Cosine |
| Warmup ratio | 0.03 |
| Weight decay | 0.01 |
| Train batch size | 24 |
| Evaluation batch size | 24 |
| Maximum sequence length | 512 |
| Optimizer | AdamW Torch Fused |
| Precision | BF16 |
LoRA adapters were applied to:
text
q_projk_projv_projo_projgate_projup_projdown_projThe prompt portion of each training example was masked from the loss, so training focuses on generating the ad copy rather than reproducing the instruction.
Training was performed using:
text
smangrul/ad-copy-generationThe dataset examples were transformed into a chat-style format containing:
text
System:Create a text ad given the following product and description.Output only the Ad Copy and nothing else. User:Product: <product>Description: <description> Adcopy:The expected advertisement was used as the target completion.
Because this repository contains a LoRA adapter, load it together with the original TinyLlama base model.
bash
%uv pip install torch transformers peft acceleratepython
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"ADAPTER = "keshavsharma/tinyllama-1.1b-adcopy-generation-lora" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.bfloat16, device_map="auto") model = PeftModel.from_pretrained( base_model, ADAPTER) model.eval()python
product = "Fitness Magazine"description = "Fitness magazine for staying active and achieving your fitness goals." messages = [ { "role": "system", "content": ( "Create a text ad given the following product and description. " "Output only the Ad Copy and nothing else." ), }, { "role": "user", "content": ( f"Product: {product}\n" f"Description: {description}\n\n" "Adcopy: " ), },] 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=128, temperature=0.8, top_p=0.9, do_sample=True, ) generated = tokenizer.decode( outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True) print(generated)The objective of the fine-tuning process is to adapt TinyLlama to the following mapping:
text
Product + Description ↓ Ad CopyFor example:
text
Product: Running ShoesDescription: Lightweight running shoes designed for everyday training. ↓Run farther and feel lighter with our performance running shoes...This model is a relatively small 1.1B parameter language model and is specifically fine-tuned for advertising copy generation.
It may:
Generated advertising content should therefore be reviewed before being used commercially.
This model is intended for research and experimentation with small language-model fine-tuning and automated advertising copy generation. Users are responsible for reviewing generated content and ensuring that advertisements comply with applicable advertising, consumer-protection, and platform policies.
The base model is:
TinyLlama/TinyLlama-1.1B-Chat-v1.0
Please refer to the base model repository for its licensing terms and conditions.
The LoRA adapter in this repository is provided for research and experimentation.
q_projk_projv_projo_projgate_projup_projdown_projSystem:Create a text ad given the following product and description.Output only the Ad Copy and nothing else.User:Product: <product>Description: <description>Adcopy:%uv pip install torch transformers peft accelerateimport torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel BASE_MODEL = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"ADAPTER = "keshavsharma/tinyllama-1.1b-adcopy-generation-lora" tokenizer = AutoTokenizer.from_pretrained(BASE_MODEL) base_model = AutoModelForCausalLM.from_pretrained( BASE_MODEL, torch_dtype=torch.bfloat16, device_map="auto") model = PeftModel.from_pretrained( base_model, ADAPTER) model.eval()product = "Fitness Magazine"description = "Fitness magazine for staying active and achieving your fitness goals." messages = [ { "role": "system", "content": ( "Create a text ad given the following product and description. " "Output only the Ad Copy and nothing else." ), }, { "role": "user", "content": ( f"Product: {product}\n" f"Description: {description}\n\n" "Adcopy: " ), },] 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=128, temperature=0.8, top_p=0.9, do_sample=True, ) generated = tokenizer.decode( outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True) print(generated)Product: Running ShoesDescription: Lightweight running shoes designed for everyday training. ↓Run farther and feel lighter with our performance running shoes...