diff --git a/modules/loaders.py b/modules/loaders.py index a0104e90..6107dac7 100644 --- a/modules/loaders.py +++ b/modules/loaders.py @@ -26,7 +26,7 @@ loaders_and_params = OrderedDict({ 'compress_pos_emb', 'disable_exllama', 'disable_exllamav2', - 'transformers_info' + 'transformers_info', ], 'llama.cpp': [ 'n_ctx', diff --git a/modules/ui_model_menu.py b/modules/ui_model_menu.py index f03d45c9..98868f2c 100644 --- a/modules/ui_model_menu.py +++ b/modules/ui_model_menu.py @@ -77,63 +77,69 @@ def create_ui(): with gr.Box(): with gr.Row(): with gr.Column(): - for i in range(len(total_mem)): - shared.gradio[f'gpu_memory_{i}'] = gr.Slider(label=f"gpu-memory in MiB for device :{i}", maximum=total_mem[i], value=default_gpu_mem[i]) + with gr.Blocks(): + for i in range(len(total_mem)): + shared.gradio[f'gpu_memory_{i}'] = gr.Slider(label=f"gpu-memory in MiB for device :{i}", maximum=total_mem[i], value=default_gpu_mem[i]) + + shared.gradio['cpu_memory'] = gr.Slider(label="cpu-memory in MiB", maximum=total_cpu_mem, value=default_cpu_mem) + + with gr.Blocks(): + shared.gradio['transformers_info'] = gr.Markdown('load-in-4bit params:') + shared.gradio['compute_dtype'] = gr.Dropdown(label="compute_dtype", choices=["bfloat16", "float16", "float32"], value=shared.args.compute_dtype) + shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type) - shared.gradio['cpu_memory'] = gr.Slider(label="cpu-memory in MiB", maximum=total_cpu_mem, value=default_cpu_mem) - shared.gradio['transformers_info'] = gr.Markdown('load-in-4bit params:') - shared.gradio['compute_dtype'] = gr.Dropdown(label="compute_dtype", choices=["bfloat16", "float16", "float32"], value=shared.args.compute_dtype) - shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type) shared.gradio['hqq_backend'] = gr.Dropdown(label="hqq_backend", choices=["PYTORCH", "PYTORCH_COMPILE", "ATEN"], value=shared.args.hqq_backend) - shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers) shared.gradio['n_ctx'] = gr.Slider(minimum=0, maximum=shared.settings['truncation_length_max'], step=256, label="n_ctx", value=shared.args.n_ctx, info='Context length. Try lowering this if you run out of memory while loading the model.') + shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 18,17') + shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch) shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=32, value=shared.args.threads) shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=32, value=shared.args.threads_batch) - shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch) - 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"], 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('ExLlamav2_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) - 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.Blocks(): + 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) + 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) + + shared.gradio['autogptq_info'] = gr.Markdown('ExLlamav2_HF is recommended over AutoGPTQ for models derived from Llama.') shared.gradio['quipsharp_info'] = gr.Markdown('QuIP# has to be installed manually at the moment.') with gr.Column(): - shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='Use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards. NVIDIA only.') + shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit) + shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit) + shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant) + shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.') + shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices) + shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This increases performance on RTX cards.') + shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu, info='llama.cpp: Use llama-cpp-python compiled without GPU acceleration. Transformers: use PyTorch in CPU mode.') + shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split the model by rows across GPUs. This may improve multi-gpu performance.') shared.gradio['no_offload_kqv'] = gr.Checkbox(label="no_offload_kqv", value=shared.args.no_offload_kqv, info='Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.') - shared.gradio['row_split'] = gr.Checkbox(label="row_split", value=shared.args.row_split, info='Split model by rows across GPUs. Improves performance on some cards.') + shared.gradio['no_mul_mat_q'] = gr.Checkbox(label="no_mul_mat_q", value=shared.args.no_mul_mat_q, info='Disable the mulmat kernels.') shared.gradio['triton'] = gr.Checkbox(label="triton", value=shared.args.triton) shared.gradio['no_inject_fused_attention'] = gr.Checkbox(label="no_inject_fused_attention", value=shared.args.no_inject_fused_attention, info='Disable fused attention. Fused attention improves inference performance but uses more VRAM. Fuses layers for AutoAWQ. Disable if running low on VRAM.') shared.gradio['no_inject_fused_mlp'] = gr.Checkbox(label="no_inject_fused_mlp", value=shared.args.no_inject_fused_mlp, info='Affects Triton only. Disable fused MLP. Fused MLP improves performance but uses more VRAM. Disable if running low on VRAM.') shared.gradio['no_use_cuda_fp16'] = gr.Checkbox(label="no_use_cuda_fp16", value=shared.args.no_use_cuda_fp16, info='This can make models faster on some systems.') shared.gradio['desc_act'] = gr.Checkbox(label="desc_act", value=shared.args.desc_act, info='\'desc_act\', \'wbits\', and \'groupsize\' are used for old models without a quantize_config.json.') - shared.gradio['no_mul_mat_q'] = gr.Checkbox(label="no_mul_mat_q", value=shared.args.no_mul_mat_q, info='Disable the mulmat kernels.') shared.gradio['no_mmap'] = gr.Checkbox(label="no-mmap", value=shared.args.no_mmap) shared.gradio['mlock'] = gr.Checkbox(label="mlock", value=shared.args.mlock) shared.gradio['numa'] = gr.Checkbox(label="numa", value=shared.args.numa, info='NUMA support can help on some systems with non-uniform memory access.') - shared.gradio['cpu'] = gr.Checkbox(label="cpu", value=shared.args.cpu) - shared.gradio['load_in_8bit'] = gr.Checkbox(label="load-in-8bit", value=shared.args.load_in_8bit) - shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16) - shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices) shared.gradio['disk'] = gr.Checkbox(label="disk", value=shared.args.disk) - shared.gradio['load_in_4bit'] = gr.Checkbox(label="load-in-4bit", value=shared.args.load_in_4bit) - shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant) - shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='Split the model across multiple GPUs, comma-separated list of proportions, e.g. 18,17') - shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='To enable this option, start the web UI with the --trust-remote-code flag. It is necessary for some models.', interactive=shared.args.trust_remote_code) - shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Create an additional cache for CFG negative prompts.') - shared.gradio['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work. Otherwise, ignore it, as it makes prompt processing slower.') - shared.gradio['use_flash_attention_2'] = gr.Checkbox(label="use_flash_attention_2", value=shared.args.use_flash_attention_2, info='Set use_flash_attention_2=True while loading the model.') - shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel.') - shared.gradio['disable_exllamav2'] = gr.Checkbox(label="disable_exllamav2", value=shared.args.disable_exllamav2, info='Disable ExLlamav2 kernel.') - 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['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16) 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['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['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.') + with gr.Blocks(): + shared.gradio['trust_remote_code'] = gr.Checkbox(label="trust-remote-code", value=shared.args.trust_remote_code, info='Set trust_remote_code=True while loading the tokenizer/model. To enable this option, start the web UI with the --trust-remote-code flag.', interactive=shared.args.trust_remote_code) + 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['logits_all'] = gr.Checkbox(label="logits_all", value=shared.args.logits_all, info='Needs to be set for perplexity evaluation to work with this loader. Otherwise, ignore it, as it makes prompt processing slower.') + + shared.gradio['disable_exllama'] = gr.Checkbox(label="disable_exllama", value=shared.args.disable_exllama, info='Disable ExLlama kernel for GPTQ models.') + shared.gradio['disable_exllamav2'] = gr.Checkbox(label="disable_exllamav2", value=shared.args.disable_exllamav2, info='Disable ExLlamav2 kernel for GPTQ models.') shared.gradio['num_experts_per_token'] = gr.Number(label="Number of experts per token", value=shared.args.num_experts_per_token, info='Only applies to MoE models like Mixtral.') shared.gradio['gptq_for_llama_info'] = gr.Markdown('Legacy loader for compatibility with older GPUs. ExLlamav2_HF or AutoGPTQ are preferred for GPTQ models when supported.') 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 (recommended): place your .gguf in a subfolder of models/ along with these 4 files: special_tokens_map.json, tokenizer_config.json, tokenizer.json, tokenizer.model.\n\nOption 2: download `oobabooga/llama-tokenizer` under "Download model or LoRA". That\'s a default Llama tokenizer that will work for some (but not all) models.')