10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 634 ms

1. 1Llama-3.3-70B-Instruct-prism4-synth-doc-reward-wireheadingverified and signedpassport

   modelrecord14 downloads/month

   • text-generation

     Task: text-generation

2. 2meta/meta-llama-3-70b-instructverified and signedpassport

   modelrecord

   • meta/meta-llama-3-70b-instruct

     A 70 billion parameter language model from Meta, fine tuned for chat completions

3. 3meta/codellama-70b-instructverified and signedpassport

   modelrecord

   • meta/codellama-70b-instruct

     A 70 billion parameter Llama tuned for coding and conversation

4. 4Meta/Llama3-70b-instructverified and signedpassport

   modelrecord

   • llama3-70b-instruct

     Task: Llama3-70b-instruct

   • llama3

     Task: llama3

5. 5Meta: Llama 3.3 70B Instructverified and signedpassport

   modelrecord

   • text->text

     Takes text; returns text.

   • structured-outputs

     Can return JSON matching a schema.

6. 6lucataco/upstage-llama-2-70b-instruct-v2verified and signedpassport

   modelrecord

   • lucataco/upstage-llama-2-70b-instruct-v2

     Upstage/Llama-2-70B-instruct-v2 - GPTQ

7. 7Llama-3.1-70b-instruct PB October 2024 (PB 24h2)verified and signedpassport

   modelrecord

   • llama3.1-70b-instruct

     Task: Llama3.1-70b-instruct

8. 8Llama-3.1-Nemotron-70B-Instructverified and signedpassport

   modelrecord

   • llama-3.1-nemotron-70b-instruct

     Task: Llama-3.1-Nemotron-70B-Instruct