DEV: Move tokenizers to a gem (#1481)

Also renames the Mixtral tokenizer to Mistral.

See gem at github.com/discourse/discourse_ai-tokenizers


Co-authored-by: Roman Rizzi <roman@discourse.org>

.gitignore

@@ -6,5 +6,4 @@ evals/log
 evals/cases
 config/eval-llms.local.yml
 # this gets rid of search results from ag, ripgrep, etc
-tokenizers/
 public/ai-share/highlight.min.js

app/models/embedding_definition.rb

@@ -23,7 +23,7 @@ class EmbeddingDefinition < ActiveRecord::Base
         DiscourseAi::Tokenizer::GeminiTokenizer,
         DiscourseAi::Tokenizer::MultilingualE5LargeTokenizer,
         DiscourseAi::Tokenizer::OpenAiTokenizer,
-        DiscourseAi::Tokenizer::MixtralTokenizer,
+        DiscourseAi::Tokenizer::MistralTokenizer,
         DiscourseAi::Tokenizer::QwenTokenizer,
       ].map(&:name)
     end

db/migrate/20250702073222_rename_mixtral_tokenizer_to_mistral_tokenizer.rb

@@ -0,0 +1,43 @@
+# frozen_string_literal: true
+
+class RenameMixtralTokenizerToMistralTokenizer < ActiveRecord::Migration[7.2]
+  def up
+    execute <<~SQL
+      UPDATE
+        llm_models
+      SET
+        tokenizer = 'DiscourseAi::Tokenizer::Mistral'
+      WHERE
+        tokenizer = 'DiscourseAi::Tokenizer::Mixtral'
+    SQL
+
+    execute <<~SQL
+      UPDATE
+        embedding_definitions
+      SET
+        tokenizer_class = 'DiscourseAi::Tokenizer::Mistral'
+      WHERE
+        tokenizer_class = 'DiscourseAi::Tokenizer::Mixtral'
+    SQL
+  end
+
+  def down
+    execute <<~SQL
+      UPDATE
+        llm_models
+      SET
+        tokenizer = 'DiscourseAi::Tokenizer::Mixtral'
+      WHERE
+        tokenizer = 'DiscourseAi::Tokenizer::Mistral'
+    SQL
+
+    execute <<~SQL
+      UPDATE
+        embedding_definitions
+      SET
+        tokenizer_class = 'DiscourseAi::Tokenizer::Mixtral'
+      WHERE
+        tokenizer_class = 'DiscourseAi::Tokenizer::Mistral'
+    SQL
+  end
+end

lib/automation/llm_triage.rb

@@ -40,7 +40,12 @@ module DiscourseAi
 
         content = "title: #{post.topic.title}\n#{post.raw}"
 
-        content = llm.tokenizer.truncate(content, max_post_tokens) if max_post_tokens.present?
+        content =
+          llm.tokenizer.truncate(
+            content,
+            max_post_tokens,
+            strict: SiteSetting.ai_strict_token_counting,
+          ) if max_post_tokens.present?
 
         if post.upload_ids.present?
           content = [content]

lib/automation/report_context_generator.rb

@@ -99,7 +99,12 @@ module DiscourseAi
         buffer << post.created_at.strftime("%Y-%m-%d %H:%M")
         buffer << "user: #{post.user&.username}"
         buffer << "likes: #{post.like_count}"
-        excerpt = @tokenizer.truncate(post.raw, @tokens_per_post)
+        excerpt =
+          @tokenizer.truncate(
+            post.raw,
+            @tokens_per_post,
+            strict: SiteSetting.ai_strict_token_counting,
+          )
         excerpt = "excerpt: #{excerpt}..." if excerpt.length < post.raw.length
         buffer << "#{excerpt}"
         { likes: post.like_count, info: buffer.join("\n") }

lib/completions/dialects/dialect.rb

@@ -147,6 +147,7 @@ module DiscourseAi
               system_message[:content] = tokenizer.truncate(
                 system_message[:content],
                 max_system_tokens,
+                strict: SiteSetting.ai_strict_token_counting,
               )
             end
 

lib/completions/llm.rb

@@ -190,7 +190,7 @@ module DiscourseAi
                       display_name: "Pixtral Large",
                     },
                   ],
-                  tokenizer: DiscourseAi::Tokenizer::MixtralTokenizer,
+                  tokenizer: DiscourseAi::Tokenizer::MistralTokenizer,
                   endpoint: "https://api.mistral.ai/v1/chat/completions",
                   provider: "mistral",
                 },

lib/embeddings/strategies/truncation.rb

@@ -22,7 +22,11 @@ module DiscourseAi
             when Post
               post_truncation(target, vdef.tokenizer, max_length)
             when RagDocumentFragment
-              vdef.tokenizer.truncate(target.fragment, max_length)
+              vdef.tokenizer.truncate(
+                target.fragment,
+                max_length,
+                strict: SiteSetting.ai_strict_token_counting,
+              )
             else
               raise ArgumentError, "Invalid target type"
             end
@@ -36,7 +40,7 @@ module DiscourseAi
           qtext = asymetric ? "#{vdef.search_prompt} #{text}" : text
           max_length = vdef.max_sequence_length - 2
 
-          vdef.tokenizer.truncate(qtext, max_length)
+          vdef.tokenizer.truncate(qtext, max_length, strict: SiteSetting.ai_strict_token_counting)
         end
 
         private
@@ -74,7 +78,7 @@ module DiscourseAi
             text << "\n\n"
           end
 
-          tokenizer.truncate(text, max_length)
+          tokenizer.truncate(text, max_length, strict: SiteSetting.ai_strict_token_counting)
         end
 
         def post_truncation(post, tokenizer, max_length)
@@ -86,7 +90,7 @@ module DiscourseAi
             text << Nokogiri::HTML5.fragment(post.cooked).text
           end
 
-          tokenizer.truncate(text, max_length)
+          tokenizer.truncate(text, max_length, strict: SiteSetting.ai_strict_token_counting)
         end
       end
     end

lib/personas/question_consolidator.rb

@@ -42,7 +42,12 @@ module DiscourseAi
           truncated_content = content
 
           if current_tokens > allowed_tokens
-            truncated_content = @llm.tokenizer.truncate(content, allowed_tokens)
+            truncated_content =
+              @llm.tokenizer.truncate(
+                content,
+                allowed_tokens,
+                strict: SiteSetting.ai_strict_token_counting,
+              )
             current_tokens = allowed_tokens
           end
 

lib/personas/tool_runner.rb

@@ -278,7 +278,9 @@ module DiscourseAi
       def attach_truncate(mini_racer_context)
         mini_racer_context.attach(
           "_llm_truncate",
-          ->(text, length) { @llm.tokenizer.truncate(text, length) },
+          ->(text, length) do
+            @llm.tokenizer.truncate(text, length, strict: SiteSetting.ai_strict_token_counting)
+          end,
         )
 
         mini_racer_context.attach(

lib/personas/tools/google.rb

@@ -70,7 +70,10 @@ module DiscourseAi
           data = result[field]
           return "" if data.blank?
 
-          llm.tokenizer.truncate(data, max_tokens).squish
+          llm
+            .tokenizer
+            .truncate(data, max_tokens, strict: SiteSetting.ai_strict_token_counting)
+            .squish
         end
 
         def parse_search_json(json_data, escaped_query, llm)

lib/personas/tools/setting_context.rb

@@ -99,7 +99,12 @@ module DiscourseAi
 
             result.gsub!(/^#{Regexp.escape(Rails.root.to_s)}/, "")
 
-            result = llm.tokenizer.truncate(result, MAX_CONTEXT_TOKENS)
+            result =
+              llm.tokenizer.truncate(
+                result,
+                MAX_CONTEXT_TOKENS,
+                strict: SiteSetting.ai_strict_token_counting,
+              )
 
             { setting_name: setting_name, context: result }
           end

lib/personas/tools/tool.rb

@@ -255,7 +255,7 @@ module DiscourseAi
             target = max_length if target > max_length
           end
 
-          llm.tokenizer.truncate(text, target)
+          llm.tokenizer.truncate(text, target, strict: SiteSetting.ai_strict_token_counting)
         end
 
         def accepted_options

lib/sentiment/post_classification.rb

@@ -161,7 +161,11 @@ module DiscourseAi
             target.raw
           end
 
-        Tokenizer::BertTokenizer.truncate(content, 512)
+        DiscourseAi::Tokenizer::BertTokenizer.truncate(
+          content,
+          512,
+          strict: SiteSetting.ai_strict_token_counting,
+        )
       end
 
       def request_with(client, content)

lib/summarization/fold_content.rb

@@ -92,7 +92,11 @@ module DiscourseAi
         items.each_with_index do |item, idx|
           as_text = "(#{item[:id]} #{item[:poster]} said: #{item[:text]} "
 
-          if tokenizer.below_limit?(as_text, tokens_left)
+          if tokenizer.below_limit?(
+               as_text,
+               tokens_left,
+               strict: SiteSetting.ai_strict_token_counting,
+             )
             content_in_window << item
             tokens_left -= tokenizer.size(as_text)
           else
@@ -151,8 +155,16 @@ module DiscourseAi
         tokenizer = llm_model.tokenizer_class
 
         item[:text] = [
-          tokenizer.truncate(split_1, truncation_length),
-          tokenizer.truncate(split_2.reverse, truncation_length).reverse,
+          tokenizer.truncate(
+            split_1,
+            truncation_length,
+            strict: SiteSetting.ai_strict_token_counting,
+          ),
+          tokenizer.truncate(
+            split_2.reverse,
+            truncation_length,
+            strict: SiteSetting.ai_strict_token_counting,
+          ).reverse,
         ].join(" ")
 
         item

lib/tokenizer/all_mpnet_base_v2_tokenizer.rb

@@ -1,12 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class AllMpnetBaseV2Tokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||=
-          Tokenizers.from_file("./plugins/discourse-ai/tokenizers/all-mpnet-base-v2.json")
-      end
-    end
-  end
-end

lib/tokenizer/anthropic_tokenizer.rb

@@ -1,12 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class AnthropicTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||=
-          Tokenizers.from_file("./plugins/discourse-ai/tokenizers/claude-v1-tokenization.json")
-      end
-    end
-  end
-end

lib/tokenizer/basic_tokenizer.rb

@@ -1,55 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class BasicTokenizer
-      class << self
-        def available_llm_tokenizers
-          [
-            DiscourseAi::Tokenizer::AnthropicTokenizer,
-            DiscourseAi::Tokenizer::GeminiTokenizer,
-            DiscourseAi::Tokenizer::Llama3Tokenizer,
-            DiscourseAi::Tokenizer::MixtralTokenizer,
-            DiscourseAi::Tokenizer::OpenAiTokenizer,
-            DiscourseAi::Tokenizer::QwenTokenizer,
-          ]
-        end
-
-        def tokenizer
-          raise NotImplementedError
-        end
-
-        def tokenize(text)
-          tokenizer.encode(text).tokens
-        end
-
-        def size(text)
-          tokenize(text).size
-        end
-
-        def decode(token_ids)
-          tokenizer.decode(token_ids)
-        end
-
-        def encode(tokens)
-          tokenizer.encode(tokens).ids
-        end
-
-        def truncate(text, max_length)
-          # fast track common case, /2 to handle unicode chars
-          # than can take more than 1 token per char
-          return text if !SiteSetting.ai_strict_token_counting && text.size < max_length / 2
-          tokenizer.decode(tokenizer.encode(text).ids.take(max_length))
-        end
-
-        def below_limit?(text, limit)
-          # fast track common case, /2 to handle unicode chars
-          # than can take more than 1 token per char
-          return true if !SiteSetting.ai_strict_token_counting && text.size < limit / 2
-
-          tokenizer.encode(text).ids.length < limit
-        end
-      end
-    end
-  end
-end

lib/tokenizer/bert_tokenizer.rb

@@ -1,12 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class BertTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||=
-          Tokenizers.from_file("./plugins/discourse-ai/tokenizers/bert-base-uncased.json")
-      end
-    end
-  end
-end

lib/tokenizer/bge_large_en_tokenizer.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class BgeLargeEnTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||= Tokenizers.from_file("./plugins/discourse-ai/tokenizers/bge-large-en.json")
-      end
-    end
-  end
-end

lib/tokenizer/bge_m3_tokenizer.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class BgeM3Tokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||= Tokenizers.from_file("./plugins/discourse-ai/tokenizers/bge-m3.json")
-      end
-    end
-  end
-end

lib/tokenizer/gemini_tokenizer.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class GeminiTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||= Tokenizers.from_file("./plugins/discourse-ai/tokenizers/gemma3.json")
-      end
-    end
-  end
-end

lib/tokenizer/llama3_tokenizer.rb

@@ -1,12 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class Llama3Tokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||=
-          Tokenizers.from_file("./plugins/discourse-ai/tokenizers/Meta-Llama-3-70B-Instruct.json")
-      end
-    end
-  end
-end

lib/tokenizer/mixtral_tokenizer.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class MixtralTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||= Tokenizers.from_file("./plugins/discourse-ai/tokenizers/mixtral.json")
-      end
-    end
-  end
-end

lib/tokenizer/multilingual_e5_large_tokenizer.rb

@@ -1,12 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class MultilingualE5LargeTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||=
-          Tokenizers.from_file("./plugins/discourse-ai/tokenizers/multilingual-e5-large.json")
-      end
-    end
-  end
-end

lib/tokenizer/open_ai_tokenizer.rb

@@ -1,44 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class OpenAiTokenizer < BasicTokenizer
-      class << self
-        def tokenizer
-          @@tokenizer ||= Tiktoken.get_encoding("o200k_base")
-        end
-
-        def tokenize(text)
-          tokenizer.encode(text)
-        end
-
-        def encode(text)
-          tokenizer.encode(text)
-        end
-
-        def decode(token_ids)
-          tokenizer.decode(token_ids)
-        end
-
-        def truncate(text, max_length)
-          # fast track common case, /2 to handle unicode chars
-          # than can take more than 1 token per char
-          return text if !SiteSetting.ai_strict_token_counting && text.size < max_length / 2
-
-          tokenizer.decode(tokenize(text).take(max_length))
-        rescue Tiktoken::UnicodeError
-          max_length = max_length - 1
-          retry
-        end
-
-        def below_limit?(text, limit)
-          # fast track common case, /2 to handle unicode chars
-          # than can take more than 1 token per char
-          return true if !SiteSetting.ai_strict_token_counting && text.size < limit / 2
-
-          tokenizer.encode(text).length < limit
-        end
-      end
-    end
-  end
-end

lib/tokenizer/qwen_tokenizer.rb

@@ -1,11 +0,0 @@
-# frozen_string_literal: true
-
-module DiscourseAi
-  module Tokenizer
-    class QwenTokenizer < BasicTokenizer
-      def self.tokenizer
-        @@tokenizer ||= Tokenizers.from_file("./plugins/discourse-ai/tokenizers/qwen3.json")
-      end
-    end
-  end
-end

plugin.rb

@@ -10,6 +10,7 @@
 
 gem "tokenizers", "0.5.4"
 gem "tiktoken_ruby", "0.0.11.1"
+gem "discourse_ai-tokenizers", "0.2.0", require_name: "discourse_ai/tokenizers"
 gem "ed25519", "1.2.4" #TODO remove this as existing ssl gem should handle this
 
 # we probably want to move all dependencies directly in to the Discourse Gemfile, this

spec/fabricators/llm_model_fabricator.rb

@@ -118,7 +118,7 @@ Fabricator(:mistral_model, from: :llm_model) do
   name "mistral-large-latest"
   provider "mistral"
   api_key "ABC"
-  tokenizer "DiscourseAi::Tokenizer::MixtralTokenizer"
+  tokenizer "DiscourseAi::Tokenizer::MistralTokenizer"
   url "https://api.mistral.ai/v1/chat/completions"
   provider_params { { disable_native_tools: false } }
 end

spec/requests/admin/ai_llms_controller_spec.rb

@@ -136,14 +136,18 @@ RSpec.describe DiscourseAi::Admin::AiLlmsController do
         model = LlmModel.find(created_model["id"])
         expect(model.display_name).to eq(valid_attrs[:display_name])
       end
-      
+
       it "logs staff action when creating an LLM model" do
         # Log the creation
         post "/admin/plugins/discourse-ai/ai-llms.json", params: { ai_llm: valid_attrs }
         expect(response.status).to eq(201)
-        
+
         # Now verify the log was created with the right subject
-        history = UserHistory.where(action: UserHistory.actions[:custom_staff], custom_type: "create_ai_llm_model").last
+        history =
+          UserHistory.where(
+            action: UserHistory.actions[:custom_staff],
+            custom_type: "create_ai_llm_model",
+          ).last
         expect(history).to be_present
         expect(history.subject).to eq(valid_attrs[:display_name]) # Verify subject is set to display_name
       end
@@ -340,22 +344,26 @@ RSpec.describe DiscourseAi::Admin::AiLlmsController do
         expect(response.status).to eq(200)
         expect(llm_model.reload.provider).to eq(update_attrs[:provider])
       end
-      
+
       it "logs staff action when updating an LLM model" do
         # The initial provider is different from the update
         original_provider = llm_model.provider
         display_name = llm_model.display_name
-        
+
         # Perform the update
         put "/admin/plugins/discourse-ai/ai-llms/#{llm_model.id}.json",
             params: {
               ai_llm: update_attrs,
             }
-            
+
         expect(response.status).to eq(200)
-        
+
         # Now verify the log was created with the right subject
-        history = UserHistory.where(action: UserHistory.actions[:custom_staff], custom_type: "update_ai_llm_model").last
+        history =
+          UserHistory.where(
+            action: UserHistory.actions[:custom_staff],
+            custom_type: "update_ai_llm_model",
+          ).last
         expect(history).to be_present
         expect(history.subject).to eq(display_name) # Verify subject is set to display_name
       end
@@ -487,18 +495,22 @@ RSpec.describe DiscourseAi::Admin::AiLlmsController do
         expect(response).to have_http_status(:no_content)
       }.to change(LlmModel, :count).by(-1)
     end
-    
+
     it "logs staff action when deleting an LLM model" do
       # Capture the model details before deletion for comparison
       model_id = llm_model.id
       model_display_name = llm_model.display_name
-      
+
       # Delete the model
       delete "/admin/plugins/discourse-ai/ai-llms/#{llm_model.id}.json"
       expect(response).to have_http_status(:no_content)
-      
+
       # Now verify the log was created with the right subject
-      history = UserHistory.where(action: UserHistory.actions[:custom_staff], custom_type: "delete_ai_llm_model").last
+      history =
+        UserHistory.where(
+          action: UserHistory.actions[:custom_staff],
+          custom_type: "delete_ai_llm_model",
+        ).last
       expect(history).to be_present
       expect(history.subject).to eq(model_display_name) # Verify subject is set to display_name
     end

spec/shared/tokenizer_spec.rb

@@ -1,278 +0,0 @@
-# frozen_string_literal: true
-
-require "rails_helper"
-
-describe DiscourseAi::Tokenizer::BertTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a single word" do
-        expect(described_class.size("hello")).to eq(3)
-      end
-
-      it "for a sentence" do
-        expect(described_class.size("hello world")).to eq(4)
-      end
-
-      it "for a sentence with punctuation" do
-        expect(described_class.size("hello, world!")).to eq(6)
-      end
-
-      it "for a sentence with punctuation and capitalization" do
-        expect(described_class.size("Hello, World!")).to eq(6)
-      end
-
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#tokenizer" do
-    it "returns a tokenizer" do
-      expect(described_class.tokenizer).to be_a(Tokenizers::Tokenizer)
-    end
-
-    it "returns the same tokenizer" do
-      expect(described_class.tokenizer).to eq(described_class.tokenizer)
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar")
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::AnthropicTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(5)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar baz")
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::OpenAiTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(6)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar baz")
-    end
-
-    it "truncates a sentence successfully at a multibyte unicode character" do
-      sentence = "foo bar 👨🏿‍👩🏿‍👧🏿‍👧🏿 baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 7)).to eq("foo bar 👨🏿‍")
-    end
-
-    it "truncates unicode characters properly when they use more than one token per char" do
-      sentence = "我喜欢吃比萨"
-      original_size = described_class.size(sentence)
-      expect(described_class.size(described_class.truncate(sentence, original_size - 1))).to be <
-        original_size
-    end
-  end
-
-  describe "#below_limit?" do
-    it "returns true when the tokens can be expanded" do
-      expect(described_class.below_limit?("foo bar baz qux", 6)).to eq(true)
-    end
-
-    it "returns false when the tokens cannot be expanded" do
-      expect(described_class.below_limit?("foo bar baz qux", 3)).to eq(false)
-    end
-
-    it "returns false when the tokens cannot be expanded due to multibyte unicode characters" do
-      expect(described_class.below_limit?("foo bar 👨🏿 baz qux", 6)).to eq(false)
-    end
-
-    it "handles unicode characters properly when they use more than one token per char" do
-      expect(described_class.below_limit?("我喜欢吃比萨萨", 6)).to eq(false)
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::AllMpnetBaseV2Tokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar")
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::MultilingualE5LargeTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo")
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::BgeLargeEnTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar")
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::BgeM3Tokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo")
-    end
-
-    it "truncates a sentence successfully at a multibyte unicode character" do
-      sentence = "foo bar 👨🏿‍👩🏿‍👧🏿‍👧🏿 baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 7)).to eq("foo bar 👨🏿")
-    end
-
-    it "truncates unicode characters properly when they use more than one token per char" do
-      sentence = "我喜欢吃比萨"
-      original_size = described_class.size(sentence)
-      expect(described_class.size(described_class.truncate(sentence, original_size - 2))).to be <
-        original_size
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::Llama3Tokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(7)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar")
-    end
-
-    # Llama3 fails here
-    # it "truncates a sentence successfully at a multibyte unicode character" do
-    #   sentence = "foo bar 👨🏿‍👩🏿‍👧🏿‍👧🏿 baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-    #   expect(described_class.truncate(sentence, 8)).to eq("foo bar 👨🏿")
-    # end
-
-    it "truncates unicode characters properly when they use more than one token per char" do
-      sentence = "我喜欢吃比萨"
-      original_size = described_class.size(sentence)
-      expect(described_class.size(described_class.truncate(sentence, original_size - 2))).to be <
-        original_size
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::GeminiTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(9)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar")
-    end
-
-    it "truncates a sentence successfully at a multibyte unicode character" do
-      sentence = "foo bar 👨🏿‍👩🏿‍👧🏿‍👧🏿 baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 8)).to eq("foo bar 👨🏿‍👩")
-    end
-
-    it "truncates unicode characters properly when they use more than one token per char" do
-      sentence = "我喜欢吃比萨"
-      original_size = described_class.size(sentence)
-      expect(described_class.size(described_class.truncate(sentence, original_size - 2))).to be <
-        original_size
-    end
-  end
-end
-
-describe DiscourseAi::Tokenizer::QwenTokenizer do
-  describe "#size" do
-    describe "returns a token count" do
-      it "for a sentence with punctuation and capitalization and numbers" do
-        expect(described_class.size("Hello, World! 123")).to eq(8)
-      end
-    end
-  end
-
-  describe "#truncate" do
-    it "truncates a sentence" do
-      sentence = "foo bar baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 3)).to eq("foo bar baz")
-    end
-
-    it "truncates a sentence successfully at a multibyte unicode character" do
-      sentence = "foo bar 👨🏿‍👩🏿‍👧🏿‍👧🏿 baz qux quux corge grault garply waldo fred plugh xyzzy thud"
-      expect(described_class.truncate(sentence, 8)).to eq("foo bar 👨🏿‍👩")
-    end
-
-    it "truncates unicode characters properly when they use more than one token per char" do
-      sentence = "我喜欢吃比萨"
-      original_size = described_class.size(sentence)
-      expect(described_class.size(described_class.truncate(sentence, original_size - 2))).to be <
-        original_size
-    end
-  end
-end

tokenizers/Apache License

@@ -1,201 +0,0 @@
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

tokenizers/META_LLAMA_3_COMMUNITY_LICENSE.md

@@ -1,117 +0,0 @@
-META LLAMA 3 COMMUNITY LICENSE AGREEMENT
-Meta Llama 3 Version Release Date: April 18, 2024
-
-“Agreement” means the terms and conditions for use, reproduction, distribution and modification of the
-Llama Materials set forth herein.
-
-“Documentation” means the specifications, manuals and documentation accompanying Meta Llama 3
-distributed by Meta at https://llama.meta.com/get-started/.
-
-“Licensee” or “you” means you, or your employer or any other person or entity (if you are entering into
-this Agreement on such person or entity’s behalf), of the age required under applicable laws, rules or
-regulations to provide legal consent and that has legal authority to bind your employer or such other
-person or entity if you are entering in this Agreement on their behalf.
-
-“Meta Llama 3” means the foundational large language models and software and algorithms, including
-machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
-fine-tuning enabling code and other elements of the foregoing distributed by Meta at
-https://llama.meta.com/llama-downloads.
-
-“Llama Materials” means, collectively, Meta’s proprietary Meta Llama 3 and Documentation (and any
-portion thereof) made available under this Agreement.
-
-“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your
-principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located
-outside of the EEA or Switzerland).
-
-By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
-you agree to be bound by this Agreement.
-
-1. License Rights and Redistribution.
-
-  a. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free
-limited license under Meta’s intellectual property or other rights owned by Meta embodied in the Llama
-Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the
-Llama Materials.
-
-  b. Redistribution and Use.
-
-      i. If you distribute or make available the Llama Materials (or any derivative works
-thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide
-a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Meta
-Llama 3” on a related website, user interface, blogpost, about page, or product documentation. If you
-use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is
-distributed or made available, you shall also include “Llama 3” at the beginning of any such AI model
-name.
-
-      ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part 
-of an integrated end user product, then Section 2 of this Agreement will not apply to you.
-
-      iii. You must retain in all copies of the Llama Materials that you distribute the following
-attribution notice within a “Notice” text file distributed as a part of such copies: “Meta Llama 3 is
-licensed under the Meta Llama 3 Community License, Copyright © Meta Platforms, Inc. All Rights
-Reserved.”
-
-      iv. Your use of the Llama Materials must comply with applicable laws and regulations
-(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama
-Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by
-reference into this Agreement.
-
-      v. You will not use the Llama Materials or any output or results of the Llama Materials to
-improve any other large language model (excluding Meta Llama 3 or derivative works thereof).
-
-2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users
-of the products or services made available by or for Licensee, or Licensee’s affiliates, is greater than 700
-million monthly active users in the preceding calendar month, you must request a license from Meta,
-which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the
-rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
-
-3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY
-OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF
-ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED,
-INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT,
-MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR
-DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND
-ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND
-RESULTS.
-
-4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF
-LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING
-OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL,
-INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED
-OF THE POSSIBILITY OF ANY OF THE FOREGOING.
-
-5. Intellectual Property.
-
-  a. No trademark licenses are granted under this Agreement, and in connection with the Llama
-Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other
-or any of its affiliates, except as required for reasonable and customary use in describing and
-redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to
-use “Llama 3” (the “Mark”) solely as required to comply with the last sentence of Section 1.b.i. You will
-comply with Meta’s brand guidelines (currently accessible at
-https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use
-of the Mark will inure to the benefit of Meta.
-
-  b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with
-respect to any derivative works and modifications of the Llama Materials that are made by you, as
-between you and Meta, you are and will be the owner of such derivative works and modifications.
-
-  c. If you institute litigation or other proceedings against Meta or any entity (including a
-cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or
-results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other
-rights owned or licensable by you, then any licenses granted to you under this Agreement shall
-terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold
-harmless Meta from and against any claim by any third party arising out of or related to your use or
-distribution of the Llama Materials.
-
-6. Term and Termination. The term of this Agreement will commence upon your acceptance of this
-Agreement or access to the Llama Materials and will continue in full force and effect until terminated in
-accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in
-breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete
-and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this
-Agreement.
-
-7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of
-the State of California without regard to choice of law principles, and the UN Convention on Contracts
-for the International Sale of Goods does not apply to this Agreement. The courts of California shall have
-exclusive jurisdiction of any dispute arising out of this Agreement.

tokenizers/MIT License

@@ -1,7 +0,0 @@
-Copyright 2022 Anthropic, PBC.
-
-Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

tokenizers/README.md

@@ -1,43 +0,0 @@
-## bert-base-uncased.json
-
-Licensed under Apache License
-
-## claude-v1-tokenization.json
-
-Licensed under MIT License
-
-## all-mpnet-base-v2.json
-
-Licensed under Apache License
-
-## llama-2-70b-chat-hf
-
-Licensed under LLAMA 2 COMMUNITY LICENSE AGREEMENT
-
-## multilingual-e5-large
-
-Licensed under MIT License
-
-## bge-large-en
-
-Licensed under MIT License
-
-## mixtral
-
-Licensed under Apache 2.0 License
-
-## bge-m3
-
-Licensed under MIT License
-
-## Meta-Llama-3-70B-Instruct
-
-Licensed under META LLAMA 3 COMMUNITY LICENSE
-
-## Gemma 3
-
-Licensed under the [Gemma Terms of Use](https://ai.google.dev/gemma/terms)
-
-## Qwen 3
-
-Licensed under the Apache 2.0 License