From 5c7d8bfdfd90b426e7c03dc8098837d3ed988f81 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Fri, 25 Aug 2023 07:06:57 -0700
Subject: [PATCH] Detect CodeLlama settings

---
 models/config.yaml       | 4 ++++
 modules/ui_model_menu.py | 2 +-
 server.py                | 1 +
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/models/config.yaml b/models/config.yaml
index 366684dc..475eb8e8 100644
--- a/models/config.yaml
+++ b/models/config.yaml
@@ -300,3 +300,7 @@ llama-65b-gptq-3bit:
   instruction_template: 'OpenOrca-Platypus2'
   custom_stopping_strings: '"### Instruction:", "### Response:"'
   rms_norm_eps: 5.0e-6
+.*codellama:
+  rope_freq_base: 1000000
+.*codellama.*instruct:
+  instruction_template: 'Llama-v2'
diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py
index b1eb6ad9..fde2fb38 100644
--- a/modules/ui_model_menu.py
+++ b/modules/ui_model_menu.py
@@ -91,7 +91,7 @@ def create_ui():
                             shared.gradio['gpu_split'] = gr.Textbox(label='gpu-split', info='Comma-separated list of VRAM (in GB) to use per GPU. Example: 20,7,7')
                             shared.gradio['max_seq_len'] = gr.Slider(label='max_seq_len', minimum=0, maximum=16384, step=256, info='Maximum sequence length.', value=shared.args.max_seq_len)
                             shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=0.1, info='Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
-                            shared.gradio['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=100000, step=1000, info='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)', value=shared.args.rope_freq_base)
+                            shared.gradio['rope_freq_base'] = gr.Slider(label='rope_freq_base', minimum=0, maximum=1000000, step=1000, info='If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63)', value=shared.args.rope_freq_base)
                             shared.gradio['compress_pos_emb'] = gr.Slider(label='compress_pos_emb', minimum=1, maximum=8, step=1, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.', value=shared.args.compress_pos_emb)
 
                         with gr.Column():
diff --git a/server.py b/server.py
index ef213a87..f3f7da96 100644
--- a/server.py
+++ b/server.py
@@ -180,6 +180,7 @@ if __name__ == "__main__":
         'truncation_length': shared.settings['truncation_length'],
         'n_gqa': 0,
         'rms_norm_eps': 0,
+        'rope_freq_base': 0,
     }
 
     shared.model_config.move_to_end('.*', last=False)  # Move to the beginning