GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
coder1969
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
coder1969
Model Tree
google/gemma-2-2b
Input Modalities
Output Modalities
Supported Functionality
google/gemma-2-2bThis model is directly intended for taking scientific abstract/literature context and generating structured lay summaries or key points.
Users should be aware that language models can hallucinate or omit critical details from context. Outputs should be verified against original sources.
Use the code below to load the base model and apply the fine-tuned adapter weights:
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel base_model_name = "google/gemma-2-2b"adapter_model_name = "coder1969/gemma-2-2b-scientific-summarizer" # Load tokenizertokenizer = AutoTokenizer.from_pretrained(base_model_name)if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token # Load base modelmodel = AutoModelForCausalLM.from_pretrained( base_model_name, torch_dtype=torch.float16, device_map="auto") # Apply adaptersmodel = PeftModel.from_pretrained(model, adapter_model_name) # Inference Exampleprompt = "Document:\nTopic: quantum machine learning\n\nRelevant Literature:\n[Insert relevant abstracts or papers here]\n\nSummary:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9 ) print(tokenizer.decode(outputs[0], skip_special_tokens=True))Finetuned on the tomasg25/scientific_lay_summarisation dataset (subset: plos), containing pairs of scientific articles and summaries.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLMfrom peft import PeftModel base_model_name = "google/gemma-2-2b"adapter_model_name = "coder1969/gemma-2-2b-scientific-summarizer" # Load tokenizertokenizer = AutoTokenizer.from_pretrained(base_model_name)if tokenizer.pad_token is None: tokenizer.pad_token = tokenizer.eos_token # Load base modelmodel = AutoModelForCausalLM.from_pretrained( base_model_name, torch_dtype=torch.float16, device_map="auto") # Apply adaptersmodel = PeftModel.from_pretrained(model, adapter_model_name) # Inference Exampleprompt = "Document:\nTopic: quantum machine learning\n\nRelevant Literature:\n[Insert relevant abstracts or papers here]\n\nSummary:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=256, do_sample=True, temperature=0.7, top_p=0.9 ) print(tokenizer.decode(outputs[0], skip_special_tokens=True))