up

README.md

@@ -14,12 +14,12 @@ inference: false
 ---
 
 <p align="center" width="100%">
-<img src="https://huggingface.co/bofenghuang/vigogne-lora-13b/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
+<img src="https://huggingface.co/bofenghuang/vigogne-instruct-13b/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
 </p>
 
-# Vigogne-LoRA-13b: A French Instruct LLaMA Model
+# Vigogne-instruct-13b: A French Instruction-following LLaMA Model
 
-Vigogne-LoRA-13b is a [LLaMA-13B](https://huggingface.co/decapoda-research/llama-13b-hf) model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇫🇷 French instructions.
+Vigogne-instruct-13b is a LLaMA-13B model fine-tuned to follow the 🇫🇷 French instructions.
 
 For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
 
@@ -33,23 +33,23 @@ This repo only contains the low-rank adapter. In order to access the complete mo
 from peft import PeftModel
 from transformers import LlamaForCausalLM, LlamaTokenizer
 
-tokenizer = LlamaTokenizer.from_pretrained("decapoda-research/llama-13b-hf")
+base_model_name_or_path = "name/or/path/to/hf/llama/13b/model"
+lora_model_name_or_path = "bofenghuang/vigogne-instruct-13b"
+
+tokenizer = LlamaTokenizer.from_pretrained(base_model_name_or_path, padding_side="right", use_fast=False))
 model = LlamaForCausalLM.from_pretrained(
-    "decapoda-research/llama-13b-hf",
+    base_model_name_or_path,
     load_in_8bit=True,
+    torch_dtype=torch.float16,
     device_map="auto",
 )
-model = PeftModel.from_pretrained(model, "bofenghuang/vigogne-lora-13b")
+model = PeftModel.from_pretrained(model, lora_model_name_or_path)
 ```
 
 You can infer this model by using the following Google Colab Notebook.
 
-<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/infer.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
+<a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/notebooks/infer_instruct.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
 
 ## Limitations
 
 Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
-
-## Next Steps
-
-- Add output examples

adapter_config.json

@@ -1,5 +1,5 @@
 {
-  "base_model_name_or_path": "decapoda-research/llama-13b-hf",
+  "base_model_name_or_path": "hf_models/llama-13b-hf",
   "bias": "none",
   "enable_lora": null,
   "fan_in_fan_out": false,

runs/Mar26_00-26-15_koios.zaion.ai/1679786775.1921213/events.out.tfevents.1679786775.koios.zaion.ai

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6ca642fe1808e886cf3384445799fd148aa28011a18c04f0799cba919e5e4785
-size 5584

runs/Mar26_00-26-15_koios.zaion.ai/events.out.tfevents.1679786775.koios.zaion.ai

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c6c19f4204fa57f6071b9d238843b6330ebadf3524dd95c3e463d503e34d98a2
-size 12806