Llama3 1 8b On Llama3 1 8b Counterfactual 24k E1 Kl0

--- base_model: meta-llama/Llama-3.1-8B-Instruct library_name: peft pipeline_tag: text-generation license: llama3.1 tags: - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct - lora - transformers - chive --- # llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0 Privileged-access experiment (App. M): Llama-3.1-8B trained on counterfactual claims about Llama-3.1-8B (the **self** predictor), 24k size-matched. This is a **LoRA adapter** (rank 64) from the paper *Explaining Model Behaviors in the Wild with Counterfactual Investigations* (Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks). **Built with Llama.** - **Base model:** `meta-llama/Llama-3.1-8B-Instruct` - **Adapter type:** LoRA (PEFT), rank 64 - **Code:** https://github.com/adamkarvonen/chive - **Dataset:** https://huggingface.co/datasets/adamkarvonen/chive-data ## Usage ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", torch_dtype="auto", device_map="auto") model = PeftModel.from_pretrained(base, "adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0") tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct") ``` ## License **Built with Llama.** This adapter is a derivative of Meta's `meta-llama/Llama-3.1-8B-Instruct` and its use is governed by the [Llama 3.1 Community License](https://www.llama.com/llama3_1/license/). Training data has additional upstream terms — see the [dataset card](https://huggingface.co/datasets/adamkarvonen/chive-data). ### Framework versions - PEFT 0.19.1

--- base_model: meta-llama/Llama-3.1-8B-Instruct library_name: peft pipeline_tag: text-generation license: llama3.1 tags: - base_model:adapter:meta-llama/Llama-3.1-8B-Instruct - lora - transformers - counterfactual-investigations --- # llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0 Privileged-access experiment (App. M): Llama-3.1-8B trained on counterfactual claims about Llama-3.1-8B (the **self** predictor), 24k size-matched. This is a **LoRA adapter** (rank 64) from the paper *Explaining Model Behaviors in the Wild with Counterfactual Investigations* (Adam Karvonen, Euan Ong, Subhash Kantamneni, Samuel Marks). **Built with Llama.** - **Base model:** `meta-llama/Llama-3.1-8B-Instruct` - **Adapter type:** LoRA (PEFT), rank 64 - **Code:** https://github.com/adamkarvonen/counterfactual-investigations - **Dataset:** https://huggingface.co/datasets/adamkarvonen/counterfactual-investigations-data ## Usage ```python from peft import PeftModel from transformers import AutoModelForCausalLM, AutoTokenizer base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", torch_dtype="auto", device_map="auto") model = PeftModel.from_pretrained(base, "adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0") tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.1-8B-Instruct") ``` ## License **Built with Llama.** This adapter is a derivative of Meta's `meta-llama/Llama-3.1-8B-Instruct` and its use is governed by the [Llama 3.1 Community License](https://www.llama.com/llama3_1/license/). Training data has additional upstream terms — see the [dataset card](https://huggingface.co/datasets/adamkarvonen/counterfactual-investigations-data). ### Framework versions - PEFT 0.19.1

Source context: 14 downloads · 0 likes · Pipeline text-generation · Library peft · Repo adamkarvonen/llama3_1_8b_on_llama3_1_8b_counterfactual_24k_e1_kl0