together-ft-model

Fine-tuned Model from Together.ai

This model was fine-tuned using Together.ai's platform.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

# Load the model
model = AutoModelForCausalLM.from_pretrained("tkkagency/together-ft-model")
tokenizer = AutoTokenizer.from_pretrained("tkkagency/together-ft-model")

# Generate text
prompt = "Your prompt here"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Training Details

• Platform: Together.ai
• Fine-tuning Date: 2025-09-24
• Model ID: ft-d712bdc6-fada-2025-09-24-23-14-12

Note

If this is a LoRA adapter, you'll need to load it with the base model using PEFT:

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model (replace with actual base model)
base_model_id = "meta-llama/Llama-2-7b-hf"  # Update this!
model = AutoModelForCausalLM.from_pretrained(base_model_id)
tokenizer = AutoTokenizer.from_pretrained(base_model_id)

# Load adapter
model = PeftModel.from_pretrained(model, "tkkagency/together-ft-model")

# Generate
inputs = tokenizer("Your prompt", return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0]))