initial commit

README.md

@@ -0,0 +1,47 @@
+---
+language: fr
+license: mit
+tags:
+- pytorch
+- causal-lm
+datasets:
+- c4
+---
+
+# Cedille AI
+Cedille is a project to bring large language models to non-English languages.
+
+## Boris
+Boris is a 6B parameter autoregressive language model based on the GPT-J architecture and trained using the (mesh-transformer-jax)[https://github.com/kingoflolz/mesh-transformer-jax] codebase.
+
+Boris was trained on around 78B tokens of French text from the [C4](https://huggingface.co/datasets/c4) dataset. We started training from GPT-J, which has been trained on [The Pile](https://pile.eleuther.ai/). As a consequence the model still has good performance in English language. Boris makes use of the unmodified GPT-2 tokenizer.
+
+Boris is named after the great French writer [Boris Vian](https://en.wikipedia.org/wiki/Boris_Vian).
+
+# How do I test Cedille?
+For the time being, the easiest way to test the model is to use our [publicly accessible playground](https://en.cedille.ai/).
+
+Cedille is a relatively large model and running it in production can get expensive. Consider contacting us for API access.
+
+# How do I cite Cedille?
+Thanks for citing our work in case you build on top of Cedille. For the time being, please reference our work like so:
+```bibtex
+@misc{cedille2021,
+  author = {Laurent, F. and Muller, M.},
+  title = {Cedille AI},
+  year = {2021},
+  publisher = {GitHub},
+  journal = {GitHub repository},
+  howpublished = {\url{https://github.com/coteries/cedille-ai}}
+}
+```
+
+## Contact us
+For any custom development please contact us at info@coteries.com.
+
+## Links
+* [Official website](https://en.cedille.ai/)
+* [Blog](https://en.cedille.ai/blog)
+* [GitHub](https://github.com/coteries/cedille-ai)
+* [Twitter](https://twitter.com/CedilleAI)
+

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": ".",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_ctx": 2048,
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 64,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.5",
+  "use_cache": true,
+  "vocab_size": 50400
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7816e3333f19cd82f088aacd5298bd6e86f2a1a14b36d4a9da6b8ec97bc317
+size 24321098883

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}