Falcon support (trust-remote-code and autogptq checkboxes) (#2367)

---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>

README.md

@@ -226,7 +226,7 @@ Optionally, you can use the following command-line flags:
 | `--no-cache`                                | Set `use_cache` to False while generating text. This reduces the VRAM usage a bit with a performance cost. |
 | `--xformers`                                | Use xformer's memory efficient attention. This should increase your tokens/s. |
 | `--sdp-attention`                           | Use torch 2.0's sdp attention. |
-| `--trust-remote-code`                       | Set trust_remote_code=True while loading a model. Necessary for ChatGLM. |
+| `--trust-remote-code`                       | Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon. |
 
 #### Accelerate 4-bit
 

modules/AutoGPTQ_loader.py

@@ -35,6 +35,7 @@ def load_quantized(model_name):
         'device': "cuda:0" if not shared.args.cpu else "cpu",
         'use_triton': shared.args.triton,
         'use_safetensors': use_safetensors,
+        'trust_remote_code': shared.args.trust_remote_code,
         'max_memory': get_max_memory_dict()
     }
 

modules/shared.py

@@ -110,7 +110,7 @@ parser.add_argument('--bf16', action='store_true', help='Load the model with bfl
 parser.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces the VRAM usage a bit at a performance cost.')
 parser.add_argument('--xformers', action='store_true', help="Use xformer's memory efficient attention. This should increase your tokens/s.")
 parser.add_argument('--sdp-attention', action='store_true', help="Use torch 2.0's sdp attention.")
-parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM.")
+parser.add_argument('--trust-remote-code', action='store_true', help="Set trust_remote_code=True while loading a model. Necessary for ChatGLM and Falcon.")
 
 # Accelerate 4-bit
 parser.add_argument('--load-in-4bit', action='store_true', help='Load the model with 4-bit precision (using bitsandbytes).')

modules/ui.py

@@ -30,7 +30,7 @@ theme = gr.themes.Default(
 
 
 def list_model_elements():
-    elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
+    elements = ['cpu_memory', 'auto_devices', 'disk', 'cpu', 'bf16', 'load_in_8bit', 'trust_remote_code', 'load_in_4bit', 'compute_dtype', 'quant_type', 'use_double_quant', 'wbits', 'groupsize', 'model_type', 'pre_layer', 'autogptq', 'threads', 'n_batch', 'no_mmap', 'mlock', 'n_gpu_layers', 'n_ctx', 'llama_cpp_seed']
     for i in range(torch.cuda.device_count()):
         elements.append(f'gpu_memory_{i}')
 

requirements.txt

@@ -1,5 +1,6 @@
 colorama
 datasets
+einops
 flexgen==0.1.7
 gradio_client==0.2.5
 gradio==3.31.0

server.py

@@ -366,6 +366,7 @@ def create_model_menus():
                         shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu)
                         shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
                         shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit)
+                        shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Make sure to inspect the .py files inside the model folder before loading it with this option enabled.')
                         
             with gr.Box():
                 gr.Markdown('Transformers 4-bit')
@@ -391,9 +392,10 @@ def create_model_menus():
                     with gr.Column():
                         shared.gradio['wbits'] = gr.Dropdown(label="wbits", choices=["None", 1, 2, 3, 4, 8], value=shared.args.wbits if shared.args.wbits > 0 else "None")
                         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", "llama", "opt", "gptj"], value=shared.args.model_type or "None")
 
                     with gr.Column():
-                        shared.gradio['model_type'] = gr.Dropdown(label="model_type", choices=["None", "llama", "opt", "gptj"], value=shared.args.model_type or "None")
+                        shared.gradio['autogptq'] = gr.Checkbox(label="autogptq", value=shared.args.autogptq, info='AutoGPTQ needs to be manually installed from source. When enabled, gpu-memory should be used for CPU offloading instead of pre_layer.')
                         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)
 
             with gr.Box():