Recommend ExLlama_HF and ExLlamav2_HF

modules/loaders.py

@@ -71,7 +71,6 @@ loaders_and_params = OrderedDict({
         'compress_pos_emb',
         'cfg_cache',
         'no_use_fast',
-        'exllama_HF_info',
     ],
     'ExLlamav2_HF': [
         'gpu_split',
@@ -133,6 +132,7 @@ loaders_and_params = OrderedDict({
         'cache_8bit',
         'alpha_value',
         'compress_pos_emb',
+        'exllamav2_info',
     ],
     'ctransformers': [
         'n_ctx',

modules/ui_model_menu.py

@@ -95,7 +95,7 @@ def create_ui():
                             shared.gradio['groupsize'] = gr.Dropdown(label="groupsize", choices=["None", 32, 64, 128, 1024], value=shared.args.groupsize if shared.args.groupsize > 0 else "None")
                             shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None"], value=shared.args.model_type or "None")
                             shared.gradio['pre_layer'] = gr.Slider(label="pre_layer", minimum=0, maximum=100, value=shared.args.pre_layer[0] if shared.args.pre_layer is not None else 0)
-                            shared.gradio['autogptq_info'] = gr.Markdown('* ExLlama_HF is recommended over AutoGPTQ for models derived from LLaMA.')
+                            shared.gradio['autogptq_info'] = gr.Markdown('* ExLlama_HF is recommended over AutoGPTQ for models derived from Llama.')
                             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=shared.settings['truncation_length_max'], step=256, info='Context length. Try lowering this if you run out of memory while loading the model.', value=shared.args.max_seq_len)
                             shared.gradio['alpha_value'] = gr.Slider(label='alpha_value', minimum=1, maximum=8, step=0.05, info='Positional embeddings alpha factor for NTK RoPE scaling. Recommended values (NTKv1): 1.75 for 1.5x context, 2.5 for 2x context. Use either this or compress_pos_emb, not both.', value=shared.args.alpha_value)
@@ -128,9 +128,9 @@ def create_ui():
                             shared.gradio['no_flash_attn'] = gr.Checkbox(label="no_flash_attn", value=shared.args.no_flash_attn, info='Force flash-attention to not be used.')
                             shared.gradio['cache_8bit'] = gr.Checkbox(label="cache_8bit", value=shared.args.cache_8bit, info='Use 8-bit cache to save VRAM.')
                             shared.gradio['no_use_fast'] = gr.Checkbox(label="no_use_fast", value=shared.args.no_use_fast, info='Set use_fast=False while loading the tokenizer.')
-                            shared.gradio['gptq_for_llama_info'] = gr.Markdown('GPTQ-for-LLaMa support is currently only kept for compatibility with older GPUs. AutoGPTQ or ExLlama is preferred when compatible. GPTQ-for-LLaMa is installed by default with the webui on supported systems. Otherwise, it has to be installed manually following the instructions here: [instructions](https://github.com/oobabooga/text-generation-webui/blob/main/docs/GPTQ-models-(4-bit-mode).md#installation-1).')
+                            shared.gradio['gptq_for_llama_info'] = gr.Markdown('Legacy loader for compatibility with older GPUs. ExLlama_HF or AutoGPTQ are preferred for GPTQ models when supported.')
-                            shared.gradio['exllama_info'] = gr.Markdown('For more information, consult the [docs](https://github.com/oobabooga/text-generation-webui/wiki/04-%E2%80%90-Model-Tab#exllama_hf).')
+                            shared.gradio['exllama_info'] = gr.Markdown("ExLlama_HF is recommended over ExLlama for better integration with extensions and more consistent sampling behavior across loaders.")
-                            shared.gradio['exllama_HF_info'] = gr.Markdown('ExLlama_HF is a wrapper that lets you use ExLlama like a Transformers model, which means it can use the Transformers samplers. It\'s a bit slower than the regular ExLlama.')
+                            shared.gradio['exllamav2_info'] = gr.Markdown("ExLlamav2_HF is recommended over ExLlamav2 for better integration with extensions and more consistent sampling behavior across loaders.")
                             shared.gradio['llamacpp_HF_info'] = gr.Markdown('llamacpp_HF loads llama.cpp as a Transformers model. To use it, you need to download a tokenizer.\n\nOption 1: download `oobabooga/llama-tokenizer` under "Download model or LoRA". That\'s a default Llama tokenizer.\n\nOption 2: place your .gguf in a subfolder of models/ along with these 3 files: tokenizer.model, tokenizer_config.json, and special_tokens_map.json. This takes precedence over Option 1.')
 
             with gr.Column():