[PR #5782] [CLOSED] Add hermes-2-pro-llama-3 to the testing matrix #37796

Closed
opened 2026-04-22 22:27:39 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/ollama/ollama/pull/5782
Author: @andreibondarev
Created: 7/18/2024
Status: Closed

Base: mainHead: tools/hermes-2-pro-llama-3


📝 Commits (1)

  • 56905d4 Add hermes-2-pro-llama-3 to the testing matrix

📊 Changes

3 files changed (+74 additions, -3 deletions)

View changed files

📝 server/model_test.go (+7 -3)
server/testdata/tools/hermes-2-pro-llama-3.gotmpl (+43 -0)
server/testdata/tools/hermes-2-pro-llama-3.out (+24 -0)

📄 Description

Adding interstellarninja/hermes-2-pro-llama-3-8b to the testing matrix.

I'm not 100% sure whether the template is completely identical to the llama3-groq-tool-use since some of the tokens are different, specifically: bos_token, eos_token, and pad_token across the 2 models: Groq/Llama-3-Groq-8B-Tool-Use/blob/main/tokenizer_config.json and NousResearch/Hermes-2-Theta-Llama-3-8B/blob/main/tokenizer_config.json.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/ollama/ollama/pull/5782 **Author:** [@andreibondarev](https://github.com/andreibondarev) **Created:** 7/18/2024 **Status:** ❌ Closed **Base:** `main` ← **Head:** `tools/hermes-2-pro-llama-3` --- ### 📝 Commits (1) - [`56905d4`](https://github.com/ollama/ollama/commit/56905d4b10c803d94d6d7dadd3912faf17bbb3c6) Add hermes-2-pro-llama-3 to the testing matrix ### 📊 Changes **3 files changed** (+74 additions, -3 deletions) <details> <summary>View changed files</summary> 📝 `server/model_test.go` (+7 -3) ➕ `server/testdata/tools/hermes-2-pro-llama-3.gotmpl` (+43 -0) ➕ `server/testdata/tools/hermes-2-pro-llama-3.out` (+24 -0) </details> ### 📄 Description Adding `interstellarninja/hermes-2-pro-llama-3-8b` to the testing matrix. I'm not 100% sure whether the template is completely identical to the `llama3-groq-tool-use` since some of the tokens are different, specifically: `bos_token`, `eos_token`, and `pad_token` across the 2 models: [Groq/Llama-3-Groq-8B-Tool-Use/blob/main/tokenizer_config.json](https://huggingface.co/Groq/Llama-3-Groq-8B-Tool-Use/blob/main/tokenizer_config.json#L2108-L2117) and [NousResearch/Hermes-2-Theta-Llama-3-8B/blob/main/tokenizer_config.json](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B/blob/main/tokenizer_config.json#L2060-L2078). --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-04-22 22:27:39 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#37796