GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
ahmedshahriar
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ahmedshahriar
Model Tree
ahmedshahriar/GhostWriterLlama-3.2-1B
Input Modalities
Output Modalities
Supported Functionality
GhostWriterLlama-3.2-1B-DPO is a preference-aligned variant of ahmedshahriar/GhostWriterLlama-3.2-1B trained with Direct Preference Optimization (DPO) on prompt–(chosen, rejected) pairs to improve stylistic alignment and preference adherence for ghostwriting-style tasks. Training used the Unsloth workflow with Hugging Face TRL’s DPOTrainer for efficiency and compatibility with the Transformers ecosystem.
llmGhostWriter (~2.1k instruction–response) for SFT; llmGhostWriter-dpo (~1.2k prompt–preference pairs) for DPO fine-tuningText-generation scenarios needing coherent, on-tone writing: blog drafts, marketing copy, and expository/creative assistance.
Evaluated with an LLM-as-a-judge setup on the test split of the ahmedshahriar/llmGhostWriter dataset.
A judge model (GPT-4.1-nano) scored each generated response on a 1–3 scale for two criteria:
Quantitative averages from these scores, combined with qualitative review, indicated better factual accuracy and improved stylistic alignment over the base fine-tuned model ahmedshahriar/GhostWriterLlama-3.2-1B, approaching the performance of the strong Llama-3.2-1B-Instruct baseline in ghostwriting/expository prompts. (Caveat: LLM-judge metrics can reflect the judge’s biases; consider complementary human review for critical use.)
Evaluation results are publicly available for transparency at: ahmedshahriar/GhostWriterLlama-3.2-1B-DPO-results.
text
@misc{ahmedshahriar_ghostwriterllama3_2_1b_dpo_2025, author = {Ahmed Shahriar Sakib}, title = {GhostWriterLlama-3.2-1B-DPO}, year = {2025}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/ahmedshahriar/GhostWriterLlama-3.2-1B-DPO}}, license = {Apache-2.0}}Thanks to Unsloth for efficient fine-tuning and to the authors of publicly available articles used to build training corpora.
@misc{ahmedshahriar_ghostwriterllama3_2_1b_dpo_2025, author = {Ahmed Shahriar Sakib}, title = {GhostWriterLlama-3.2-1B-DPO}, year = {2025}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/ahmedshahriar/GhostWriterLlama-3.2-1B-DPO}}, license = {Apache-2.0}}