From 3974e0a90cbeb04c5f26510d2aaa1f9f490594e0 Mon Sep 17 00:00:00 2001 From: henk717 Date: Wed, 15 Jun 2022 19:14:36 +0200 Subject: [PATCH 1/2] Remove broken chatbot models --- colab/TPU.ipynb | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/colab/TPU.ipynb b/colab/TPU.ipynb index a7ba10e8..89f53af2 100644 --- a/colab/TPU.ipynb +++ b/colab/TPU.ipynb @@ -65,7 +65,7 @@ "#@markdown You can find a description of the models below along with instructions on how to start KoboldAI.\n", "\n", "#@title <-- Click this to start KoboldAI\n", - "Model = \"Nerys 13B\" #@param [\"Nerys 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Lit 6B\", \"Convo 6B\", \"C1 6B\", \"NeoX 20B\", \"facebook/opt-13b\", \"KoboldAI/fairseq-dense-13B\", \"EleutherAI/gpt-j-6B\"] {allow-input: true}\n", + "Model = \"Nerys 13B\" #@param [\"Nerys 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Lit 6B\", \"NeoX 20B\", \"facebook/opt-13b\", \"KoboldAI/fairseq-dense-13B\", \"EleutherAI/gpt-j-6B\"] {allow-input: true}\n", "Version = \"Official\" #@param [\"Official\", \"United\"] {allow-input: true}\n", "Provider = \"Localtunnel\" #@param [\"Localtunnel\", \"Cloudflare\"]\n", "\n", @@ -153,8 +153,6 @@ "| [Skein](https://huggingface.co/KoboldAI/GPT-J-6B-Skein) by VE\\_FORBRYDERNE | 6B | Adventure | Skein is best used with Adventure mode enabled, it consists of a 4 times larger adventure dataset than the Adventure model making it excellent for text adventure gaming. On top of that it also consists of light novel training further expanding its knowledge and writing capabilities. It can be used with the You filter bias if you wish to write Novels with it, but dedicated Novel models can perform better for this task. |\n", "| [Adventure](https://huggingface.co/KoboldAI/GPT-J-6B-Adventure) by VE\\_FORBRYDERNE | 6B | Adventure | Adventure is a 6B model designed to mimick the behavior of AI Dungeon. It is exclusively for Adventure Mode and can take you on the epic and wackey adventures that AI Dungeon players love. It also features the many tropes of AI Dungeon as it has been trained on very similar data. It must be used in second person (You). |\n", "| [Lit](https://huggingface.co/hakurei/lit-6B) by Haru | 6B | NSFW | Lit is a great NSFW model trained by Haru on both a large set of Literotica stories and high quality novels along with tagging support. Creating a high quality model for your NSFW stories. This model is exclusively a novel model and is best used in third person. |\n", - "| [Convo](https://huggingface.co/hitomi-team/convo-6B) by Hitomi Team | 6B | Chatbot | Convo-6B is a GPT-J 6B model fine-tuned on a collection of high quality open source datasets which amount to 6 million messages. The primary goal of the model is to provide improved performance and generalization when generating multi-turn dialogue for characters that were not present from within the fine tuning data. The prompted performance has especially improved over the predecessor model [C1-6B](https://huggingface.co/hakurei/c1-6B). |\n", - "| [C1](https://huggingface.co/hakurei/c1-6B) by Haru | 6B | Chatbot | C1 has been trained on various internet chatrooms, it makes the basis for an interesting chatbot model and has been optimized to be used in the Chatmode. |\n", "| Neo(X) by EleutherAI | 20B | Generic | NeoX is the largest EleutherAI model currently available, being a generic model it is not particularly trained towards anything and can do a variety of writing, Q&A and coding tasks. 20B's performance is closely compared to the 13B models and it is worth trying both especially if you have a task that does not involve english writing. Its behavior will be similar to the GPT-J-6B model since they are trained on the same dataset but with more sensitivity towards repetition penalty and with more knowledge. |\n", "| [Fairseq Dense](https://huggingface.co/KoboldAI/fairseq-dense-13B) | 13B | Generic | Trained by Facebook Researchers this model stems from the MOE research project within Fairseq. This particular version has been converted by us for use in KoboldAI. It is known to be on par with the larger 20B model from EleutherAI and considered as better for pop culture and language tasks. Because the model has never seen a new line (enter) it may perform worse on formatting and paragraphing. |\n", "| [GPT-J-6B](https://huggingface.co/EleutherAI/gpt-j-6B) by EleutherAI | 6B | Generic | This model serves as the basis for most other 6B models (Some being based on Fairseq Dense instead). Being trained on the Pile and not biased towards anything in particular it is suitable for a variety of tasks such as writing, Q&A and coding tasks. You will likely get better result with larger generic models or finetuned models. |\n", From 35045810154c73eaacc1bd7d4897052af6371bb0 Mon Sep 17 00:00:00 2001 From: Henk Date: Thu, 16 Jun 2022 19:52:04 +0200 Subject: [PATCH 2/2] Transformers dependency bump Makes transformers 4.20 mandatory in the dependency lists, not because the old versions are no longer supported but because it contains fixes that benefit our users and this makes it easier for them to update to it. If you stick to an older version the OPT and XGLM workarounds we have in place will remain functional, but you miss on the enhancements newer transformers versions bring. --- environments/huggingface.yml | 2 +- environments/rocm.yml | 2 +- requirements.txt | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/environments/huggingface.yml b/environments/huggingface.yml index e518be3b..da11ce10 100644 --- a/environments/huggingface.yml +++ b/environments/huggingface.yml @@ -20,4 +20,4 @@ dependencies: - flask-cloudflared - flask-ngrok - lupa==1.10 - - transformers>=4.17 \ No newline at end of file + - transformers>=4.20 \ No newline at end of file diff --git a/environments/rocm.yml b/environments/rocm.yml index 2ca9c670..1fd66d26 100644 --- a/environments/rocm.yml +++ b/environments/rocm.yml @@ -20,4 +20,4 @@ dependencies: - flask-cloudflared - flask-ngrok - lupa==1.10 - - transformers>=4.17 + - transformers>=4.20 diff --git a/requirements.txt b/requirements.txt index 7b5b967c..67c6ce74 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,4 +1,4 @@ -transformers>=4.19 +transformers>=4.20 Flask Flask-SocketIO requests