Initial commit

README.md

@@ -1,3 +1,24 @@
 ---
+language: en
 license: mit
 ---
+# Fairseq-dense 2.7B - Janeway
+## Model Description
+Fairseq-dense 2.7B-Janeway is a finetune created using Fairseq's MoE dense model.
+## Training data
+The training data contains around 2210 ebooks, mostly in the sci-fi and fantasy genres. The dataset is identical as dataset used by GPT-Neo-2.7B-Janeway.
+Some parts of the dataset have been prepended using the following text: `[Genre: <genre1>,<genre2>]`
+### How to use
+You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
+```py
+>>> from transformers import pipeline
+>>> generator = pipeline('text-generation', model='KoboldAI/fairseq-dense-2.7B-Janeway')
+>>> generator("Welcome Captain Janeway, I apologize for the delay.", do_sample=True, min_length=50)
+[{'generated_text': 'Welcome Captain Janeway, I apologize for the delay."\nIt's all right," Janeway said. "I'm certain that you're doing your best to keep me informed of what\'s going on."'}]
+```
+### Limitations and Biases
+Based on known problems with NLP technology, potential relevant factors include bias (gender, profession, race and religion).
+
+### BibTeX entry and citation info
+Artetxe et al. (2021): Efficient Large Scale Language Modeling with Mixtures of Experts
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "KoboldAI/fairseq-dense-2.7B",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "XGLMForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_heads": 32,
+  "bos_token_id": 50257,
+  "d_model": 2560,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "eos_token_id": 50259,
+  "ffn_dim": 10240,
+  "init_std": 0.02,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "xglm",
+  "newlinemode": "s",
+  "num_layers": 32,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.17.0.dev0",
+  "use_cache": false,
+  "vocab_size": 50261
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7613c28e836002a4f8c2ee02d20ad551969bcc80c3d91dbb26bc51b8b6cbacaf
+size 10585446591

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "<|endoftext|>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/950cb80cbb7dd6f9148cde0377b52deeb0233e75c00985d54d751098126e4dd7.f4b0476f9d35aab16d5dd877dd9e5d547702eff96a3d808497c0d3fc36a32c99", "name_or_path": "KoboldAI/fairseq-dense-2.7B", "tokenizer_class": "GPT2Tokenizer"}