From da1b04eafd0aa2ef167d6a5d555758a74e48ae27 Mon Sep 17 00:00:00 2001
From: David Sommers <12738+databyte@users.noreply.github.com>
Date: Thu, 18 Jan 2024 12:20:59 -0500
Subject: [PATCH] convert.py : fix llama/llama2 conversion due to vocab_size=-1
 (#5019)

PR #4818 (merged last week) reintroduced a config check for vocab_size that was addressed in PR #4258 (merged 2023-11-30).

Without the fix, llama2 models can't be converted. The error is:

`ValueError: The model's vocab size is set to -1 in params.json. Please update it manually. Maybe 32000?`
---
 convert.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/convert.py b/convert.py
index e38ee5315af30..980e6fc720aa6 100755
--- a/convert.py
+++ b/convert.py
@@ -348,7 +348,7 @@ def load_torch_params(model: LazyModel, config_path: Path) -> "Params":
             f_rope_freq_base = 1e6
 
         return Params(
-            n_vocab=config.get("vocab_size", model["tok_embeddings.weight"].shape[0]),
+            n_vocab=model["tok_embeddings.weight"].shape[0],
             n_embd=config["dim"],
             n_layer=config["n_layers"],
             n_ctx=n_ctx,