mirror of
https://github.com/oobabooga/text-generation-webui.git
synced 2025-06-07 06:06:20 -04:00
Restructure the repository (#6904)
This commit is contained in:
oobabooga
GitHub
parent
d4017fbb6d
commit
d9de14d1f7
116 changed files with 254 additions and 261 deletions
20
.gitignore
vendored
20
.gitignore
vendored
|
|
@ -1,26 +1,8 @@
|
|||
/cache
|
||||
/characters
|
||||
/css
|
||||
/extensions
|
||||
/grammars
|
||||
/installer_files
|
||||
/logs
|
||||
/loras
|
||||
/models
|
||||
/presets
|
||||
/prompts
|
||||
/repositories
|
||||
/softprompts
|
||||
/torch-dumps
|
||||
/training/datasets
|
||||
|
||||
/CMD_FLAGS.txt
|
||||
/img_bot*
|
||||
/img_me*
|
||||
/models/config-user.yaml
|
||||
/notification.mp3
|
||||
/settings*.json
|
||||
/settings*.yaml
|
||||
/user_data
|
||||
|
||||
.chroma
|
||||
.DS_Store
|
||||
|
|
|
|||
239
README.md
239
README.md
|
|
@ -182,131 +182,140 @@ List of command-line flags
|
|||
</summary>
|
||||
|
||||
```txt
|
||||
usage: server.py [-h] [--multi-user] [--character CHARACTER] [--model MODEL] [--lora LORA [LORA ...]] [--model-dir MODEL_DIR] [--lora-dir LORA_DIR] [--settings SETTINGS]
|
||||
[--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--cpu] [--auto-devices] [--gpu-memory GPU_MEMORY [GPU_MEMORY ...]]
|
||||
[--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR] [--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code] [--force-safetensors] [--no_use_fast]
|
||||
[--use_flash_attention_2] [--use_eager_attention] [--torch-compile] [--load-in-4bit] [--use_double_quant] [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE] [--flash-attn]
|
||||
[--n_ctx N_CTX] [--threads THREADS] [--threads-batch THREADS_BATCH] [--batch-size BATCH_SIZE] [--no-mmap] [--mlock] [--n-gpu-layers N_GPU_LAYERS] [--tensor-split TENSOR_SPLIT]
|
||||
[--numa] [--no-kv-offload] [--row-split] [--gpu-split GPU_SPLIT] [--autosplit] [--max_seq_len MAX_SEQ_LEN] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa]
|
||||
[--num_experts_per_token NUM_EXPERTS_PER_TOKEN] [--enable_tp] [--hqq-backend HQQ_BACKEND] [--cpp-runner] [--cache_type CACHE_TYPE] [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR]
|
||||
[--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE] [--compress_pos_emb COMPRESS_POS_EMB] [--listen] [--listen-port LISTEN_PORT]
|
||||
[--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH] [--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE]
|
||||
[--subpath SUBPATH] [--old-colors] [--api] [--public-api] [--public-api-id PUBLIC_API_ID] [--api-port API_PORT] [--api-key API_KEY] [--admin-key ADMIN_KEY] [--api-enable-ipv6]
|
||||
[--api-disable-ipv4] [--nowebui]
|
||||
usage: server.py [-h] [--multi-user] [--character CHARACTER] [--model MODEL] [--lora LORA [LORA ...]] [--model-dir MODEL_DIR] [--lora-dir LORA_DIR] [--model-menu] [--settings SETTINGS]
|
||||
[--extensions EXTENSIONS [EXTENSIONS ...]] [--verbose] [--idle-timeout IDLE_TIMEOUT] [--loader LOADER] [--cpu] [--cpu-memory CPU_MEMORY] [--disk] [--disk-cache-dir DISK_CACHE_DIR]
|
||||
[--load-in-8bit] [--bf16] [--no-cache] [--trust-remote-code] [--force-safetensors] [--no_use_fast] [--use_flash_attention_2] [--use_eager_attention] [--torch-compile] [--load-in-4bit]
|
||||
[--use_double_quant] [--compute_dtype COMPUTE_DTYPE] [--quant_type QUANT_TYPE] [--flash-attn] [--threads THREADS] [--threads-batch THREADS_BATCH] [--batch-size BATCH_SIZE] [--no-mmap]
|
||||
[--mlock] [--n-gpu-layers N_GPU_LAYERS] [--tensor-split TENSOR_SPLIT] [--numa] [--no-kv-offload] [--row-split] [--extra-flags EXTRA_FLAGS] [--streaming-llm] [--ctx-size CTX_SIZE]
|
||||
[--model-draft MODEL_DRAFT] [--draft-max DRAFT_MAX] [--gpu-layers-draft GPU_LAYERS_DRAFT] [--device-draft DEVICE_DRAFT] [--ctx-size-draft CTX_SIZE_DRAFT] [--gpu-split GPU_SPLIT]
|
||||
[--autosplit] [--cfg-cache] [--no_flash_attn] [--no_xformers] [--no_sdpa] [--num_experts_per_token NUM_EXPERTS_PER_TOKEN] [--enable_tp] [--hqq-backend HQQ_BACKEND] [--cpp-runner]
|
||||
[--cache_type CACHE_TYPE] [--deepspeed] [--nvme-offload-dir NVME_OFFLOAD_DIR] [--local_rank LOCAL_RANK] [--alpha_value ALPHA_VALUE] [--rope_freq_base ROPE_FREQ_BASE]
|
||||
[--compress_pos_emb COMPRESS_POS_EMB] [--listen] [--listen-port LISTEN_PORT] [--listen-host LISTEN_HOST] [--share] [--auto-launch] [--gradio-auth GRADIO_AUTH]
|
||||
[--gradio-auth-path GRADIO_AUTH_PATH] [--ssl-keyfile SSL_KEYFILE] [--ssl-certfile SSL_CERTFILE] [--subpath SUBPATH] [--old-colors] [--api] [--public-api]
|
||||
[--public-api-id PUBLIC_API_ID] [--api-port API_PORT] [--api-key API_KEY] [--admin-key ADMIN_KEY] [--api-enable-ipv6] [--api-disable-ipv4] [--nowebui]
|
||||
|
||||
Text generation web UI
|
||||
|
||||
options:
|
||||
-h, --help show this help message and exit
|
||||
-h, --help show this help message and exit
|
||||
|
||||
Basic settings:
|
||||
--multi-user Multi-user mode. Chat histories are not saved or automatically loaded. Warning: this is likely not safe for sharing publicly.
|
||||
--character CHARACTER The name of the character to load in chat mode by default.
|
||||
--model MODEL Name of the model to load by default.
|
||||
--lora LORA [LORA ...] The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.
|
||||
--model-dir MODEL_DIR Path to directory with all the models.
|
||||
--lora-dir LORA_DIR Path to directory with all the loras.
|
||||
--settings SETTINGS Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this
|
||||
file will be loaded by default without the need to use the --settings flag.
|
||||
--extensions EXTENSIONS [EXTENSIONS ...] The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.
|
||||
--verbose Print the prompts to the terminal.
|
||||
--idle-timeout IDLE_TIMEOUT Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.
|
||||
--multi-user Multi-user mode. Chat histories are not saved or automatically loaded. Warning: this is likely not safe for sharing publicly.
|
||||
--character CHARACTER The name of the character to load in chat mode by default.
|
||||
--model MODEL Name of the model to load by default.
|
||||
--lora LORA [LORA ...] The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.
|
||||
--model-dir MODEL_DIR Path to directory with all the models.
|
||||
--lora-dir LORA_DIR Path to directory with all the loras.
|
||||
--model-menu Show a model menu in the terminal when the web UI is first launched.
|
||||
--settings SETTINGS Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml,
|
||||
this file will be loaded by default without the need to use the --settings flag.
|
||||
--extensions EXTENSIONS [EXTENSIONS ...] The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.
|
||||
--verbose Print the prompts to the terminal.
|
||||
--idle-timeout IDLE_TIMEOUT Unload model after this many minutes of inactivity. It will be automatically reloaded when you try to use it again.
|
||||
|
||||
Model loader:
|
||||
--loader LOADER Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF, ExLlamav2,
|
||||
HQQ, TensorRT-LLM.
|
||||
--loader LOADER Choose the model loader manually, otherwise, it will get autodetected. Valid options: Transformers, llama.cpp, ExLlamav3_HF, ExLlamav2_HF,
|
||||
ExLlamav2, HQQ, TensorRT-LLM.
|
||||
|
||||
Transformers/Accelerate:
|
||||
--cpu Use the CPU to generate text. Warning: Training on CPU is extremely slow.
|
||||
--auto-devices Automatically split the model across the available GPU(s) and CPU.
|
||||
--gpu-memory GPU_MEMORY [GPU_MEMORY ...] Maximum GPU memory in GiB to be allocated per GPU. Example: --gpu-memory 10 for a single GPU, --gpu-memory 10 5 for two GPUs. You can also set values
|
||||
in MiB like --gpu-memory 3500MiB.
|
||||
--cpu-memory CPU_MEMORY Maximum CPU memory in GiB to allocate for offloaded weights. Same as above.
|
||||
--disk If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.
|
||||
--disk-cache-dir DISK_CACHE_DIR Directory to save the disk cache to. Defaults to "cache".
|
||||
--load-in-8bit Load the model with 8-bit precision (using bitsandbytes).
|
||||
--bf16 Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
|
||||
--no-cache Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.
|
||||
--trust-remote-code Set trust_remote_code=True while loading the model. Necessary for some models.
|
||||
--force-safetensors Set use_safetensors=True while loading the model. This prevents arbitrary code execution.
|
||||
--no_use_fast Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast.
|
||||
--use_flash_attention_2 Set use_flash_attention_2=True while loading the model.
|
||||
--use_eager_attention Set attn_implementation= eager while loading the model.
|
||||
--torch-compile Compile the model with torch.compile for improved performance.
|
||||
--cpu Use the CPU to generate text. Warning: Training on CPU is extremely slow.
|
||||
--cpu-memory CPU_MEMORY Maximum CPU memory in GiB. Use this for CPU offloading.
|
||||
--disk If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.
|
||||
--disk-cache-dir DISK_CACHE_DIR Directory to save the disk cache to. Defaults to "user_data/cache".
|
||||
--load-in-8bit Load the model with 8-bit precision (using bitsandbytes).
|
||||
--bf16 Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
|
||||
--no-cache Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.
|
||||
--trust-remote-code Set trust_remote_code=True while loading the model. Necessary for some models.
|
||||
--force-safetensors Set use_safetensors=True while loading the model. This prevents arbitrary code execution.
|
||||
--no_use_fast Set use_fast=False while loading the tokenizer (it's True by default). Use this if you have any problems related to use_fast.
|
||||
--use_flash_attention_2 Set use_flash_attention_2=True while loading the model.
|
||||
--use_eager_attention Set attn_implementation= eager while loading the model.
|
||||
--torch-compile Compile the model with torch.compile for improved performance.
|
||||
|
||||
bitsandbytes 4-bit:
|
||||
--load-in-4bit Load the model with 4-bit precision (using bitsandbytes).
|
||||
--use_double_quant use_double_quant for 4-bit.
|
||||
--compute_dtype COMPUTE_DTYPE compute dtype for 4-bit. Valid options: bfloat16, float16, float32.
|
||||
--quant_type QUANT_TYPE quant_type for 4-bit. Valid options: nf4, fp4.
|
||||
--load-in-4bit Load the model with 4-bit precision (using bitsandbytes).
|
||||
--use_double_quant use_double_quant for 4-bit.
|
||||
--compute_dtype COMPUTE_DTYPE compute dtype for 4-bit. Valid options: bfloat16, float16, float32.
|
||||
--quant_type QUANT_TYPE quant_type for 4-bit. Valid options: nf4, fp4.
|
||||
|
||||
llama.cpp:
|
||||
--flash-attn Use flash-attention.
|
||||
--n_ctx N_CTX Size of the prompt context.
|
||||
--threads THREADS Number of threads to use.
|
||||
--threads-batch THREADS_BATCH Number of threads to use for batches/prompt processing.
|
||||
--batch-size BATCH_SIZE Maximum number of prompt tokens to batch together when calling llama_eval.
|
||||
--no-mmap Prevent mmap from being used.
|
||||
--mlock Force the system to keep the model in RAM.
|
||||
--n-gpu-layers N_GPU_LAYERS Number of layers to offload to the GPU.
|
||||
--tensor-split TENSOR_SPLIT Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.
|
||||
--numa Activate NUMA task allocation for llama.cpp.
|
||||
--no-kv-offload Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
|
||||
--row-split Split the model by rows across GPUs. This may improve multi-gpu performance.
|
||||
--flash-attn Use flash-attention.
|
||||
--threads THREADS Number of threads to use.
|
||||
--threads-batch THREADS_BATCH Number of threads to use for batches/prompt processing.
|
||||
--batch-size BATCH_SIZE Maximum number of prompt tokens to batch together when calling llama_eval.
|
||||
--no-mmap Prevent mmap from being used.
|
||||
--mlock Force the system to keep the model in RAM.
|
||||
--n-gpu-layers N_GPU_LAYERS Number of layers to offload to the GPU.
|
||||
--tensor-split TENSOR_SPLIT Split the model across multiple GPUs. Comma-separated list of proportions. Example: 60,40.
|
||||
--numa Activate NUMA task allocation for llama.cpp.
|
||||
--no-kv-offload Do not offload the K, Q, V to the GPU. This saves VRAM but reduces the performance.
|
||||
--row-split Split the model by rows across GPUs. This may improve multi-gpu performance.
|
||||
--extra-flags EXTRA_FLAGS Extra flags to pass to llama-server. Format: "flag1=value1;flag2;flag3=value3". Example: "override-tensor=exps=CPU"
|
||||
--streaming-llm Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.
|
||||
|
||||
Context and cache management:
|
||||
--ctx-size CTX_SIZE, --n_ctx CTX_SIZE, --max_seq_len CTX_SIZE
|
||||
Context size in tokens.
|
||||
|
||||
Speculative decoding:
|
||||
--model-draft MODEL_DRAFT Path to the draft model for speculative decoding.
|
||||
--draft-max DRAFT_MAX Number of tokens to draft for speculative decoding.
|
||||
--gpu-layers-draft GPU_LAYERS_DRAFT Number of layers to offload to the GPU for the draft model.
|
||||
--device-draft DEVICE_DRAFT Comma-separated list of devices to use for offloading the draft model. Example: CUDA0,CUDA1
|
||||
--ctx-size-draft CTX_SIZE_DRAFT Size of the prompt context for the draft model. If 0, uses the same as the main model.
|
||||
|
||||
ExLlamaV2:
|
||||
--gpu-split GPU_SPLIT Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.
|
||||
--autosplit Autosplit the model tensors across the available GPUs. This causes --gpu-split to be ignored.
|
||||
--max_seq_len MAX_SEQ_LEN Maximum sequence length.
|
||||
--cfg-cache ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.
|
||||
--no_flash_attn Force flash-attention to not be used.
|
||||
--no_xformers Force xformers to not be used.
|
||||
--no_sdpa Force Torch SDPA to not be used.
|
||||
--num_experts_per_token NUM_EXPERTS_PER_TOKEN Number of experts to use for generation. Applies to MoE models like Mixtral.
|
||||
--enable_tp Enable Tensor Parallelism (TP) in ExLlamaV2.
|
||||
--gpu-split GPU_SPLIT Comma-separated list of VRAM (in GB) to use per GPU device for model layers. Example: 20,7,7.
|
||||
--autosplit Autosplit the model tensors across the available GPUs. This causes --gpu-split to be ignored.
|
||||
--cfg-cache ExLlamav2_HF: Create an additional cache for CFG negative prompts. Necessary to use CFG with that loader.
|
||||
--no_flash_attn Force flash-attention to not be used.
|
||||
--no_xformers Force xformers to not be used.
|
||||
--no_sdpa Force Torch SDPA to not be used.
|
||||
--num_experts_per_token NUM_EXPERTS_PER_TOKEN Number of experts to use for generation. Applies to MoE models like Mixtral.
|
||||
--enable_tp Enable Tensor Parallelism (TP) in ExLlamaV2.
|
||||
|
||||
HQQ:
|
||||
--hqq-backend HQQ_BACKEND Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.
|
||||
--hqq-backend HQQ_BACKEND Backend for the HQQ loader. Valid options: PYTORCH, PYTORCH_COMPILE, ATEN.
|
||||
|
||||
TensorRT-LLM:
|
||||
--cpp-runner Use the ModelRunnerCpp runner, which is faster than the default ModelRunner but doesn't support streaming yet.
|
||||
--cpp-runner Use the ModelRunnerCpp runner, which is faster than the default ModelRunner but doesn't support streaming yet.
|
||||
|
||||
Cache:
|
||||
--cache_type CACHE_TYPE KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4.
|
||||
--cache_type CACHE_TYPE KV cache type; valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4.
|
||||
|
||||
DeepSpeed:
|
||||
--deepspeed Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.
|
||||
--nvme-offload-dir NVME_OFFLOAD_DIR DeepSpeed: Directory to use for ZeRO-3 NVME offloading.
|
||||
--local_rank LOCAL_RANK DeepSpeed: Optional argument for distributed setups.
|
||||
--deepspeed Enable the use of DeepSpeed ZeRO-3 for inference via the Transformers integration.
|
||||
--nvme-offload-dir NVME_OFFLOAD_DIR DeepSpeed: Directory to use for ZeRO-3 NVME offloading.
|
||||
--local_rank LOCAL_RANK DeepSpeed: Optional argument for distributed setups.
|
||||
|
||||
RoPE:
|
||||
--alpha_value ALPHA_VALUE Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.
|
||||
--rope_freq_base ROPE_FREQ_BASE If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63).
|
||||
--compress_pos_emb COMPRESS_POS_EMB Positional embeddings compression factor. Should be set to (context length) / (model's original context length). Equal to 1/rope_freq_scale.
|
||||
--alpha_value ALPHA_VALUE Positional embeddings alpha factor for NTK RoPE scaling. Use either this or compress_pos_emb, not both.
|
||||
--rope_freq_base ROPE_FREQ_BASE If greater than 0, will be used instead of alpha_value. Those two are related by rope_freq_base = 10000 * alpha_value ^ (64 / 63).
|
||||
--compress_pos_emb COMPRESS_POS_EMB Positional embeddings compression factor. Should be set to (context length) / (model's original context length). Equal to 1/rope_freq_scale.
|
||||
|
||||
Gradio:
|
||||
--listen Make the web UI reachable from your local network.
|
||||
--listen-port LISTEN_PORT The listening port that the server will use.
|
||||
--listen-host LISTEN_HOST The hostname that the server will use.
|
||||
--share Create a public URL. This is useful for running the web UI on Google Colab or similar.
|
||||
--auto-launch Open the web UI in the default browser upon launch.
|
||||
--gradio-auth GRADIO_AUTH Set Gradio authentication password in the format "username:password". Multiple credentials can also be supplied with "u1:p1,u2:p2,u3:p3".
|
||||
--gradio-auth-path GRADIO_AUTH_PATH Set the Gradio authentication file path. The file should contain one or more user:password pairs in the same format as above.
|
||||
--ssl-keyfile SSL_KEYFILE The path to the SSL certificate key file.
|
||||
--ssl-certfile SSL_CERTFILE The path to the SSL certificate cert file.
|
||||
--subpath SUBPATH Customize the subpath for gradio, use with reverse proxy
|
||||
--old-colors Use the legacy Gradio colors, before the December/2024 update.
|
||||
--listen Make the web UI reachable from your local network.
|
||||
--listen-port LISTEN_PORT The listening port that the server will use.
|
||||
--listen-host LISTEN_HOST The hostname that the server will use.
|
||||
--share Create a public URL. This is useful for running the web UI on Google Colab or similar.
|
||||
--auto-launch Open the web UI in the default browser upon launch.
|
||||
--gradio-auth GRADIO_AUTH Set Gradio authentication password in the format "username:password". Multiple credentials can also be supplied with "u1:p1,u2:p2,u3:p3".
|
||||
--gradio-auth-path GRADIO_AUTH_PATH Set the Gradio authentication file path. The file should contain one or more user:password pairs in the same format as above.
|
||||
--ssl-keyfile SSL_KEYFILE The path to the SSL certificate key file.
|
||||
--ssl-certfile SSL_CERTFILE The path to the SSL certificate cert file.
|
||||
--subpath SUBPATH Customize the subpath for gradio, use with reverse proxy
|
||||
--old-colors Use the legacy Gradio colors, before the December/2024 update.
|
||||
|
||||
API:
|
||||
--api Enable the API extension.
|
||||
--public-api Create a public URL for the API using Cloudfare.
|
||||
--public-api-id PUBLIC_API_ID Tunnel ID for named Cloudflare Tunnel. Use together with public-api option.
|
||||
--api-port API_PORT The listening port for the API.
|
||||
--api-key API_KEY API authentication key.
|
||||
--admin-key ADMIN_KEY API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key.
|
||||
--api-enable-ipv6 Enable IPv6 for the API
|
||||
--api-disable-ipv4 Disable IPv4 for the API
|
||||
--nowebui Do not launch the Gradio UI. Useful for launching the API in standalone mode.
|
||||
--api Enable the API extension.
|
||||
--public-api Create a public URL for the API using Cloudfare.
|
||||
--public-api-id PUBLIC_API_ID Tunnel ID for named Cloudflare Tunnel. Use together with public-api option.
|
||||
--api-port API_PORT The listening port for the API.
|
||||
--api-key API_KEY API authentication key.
|
||||
--admin-key ADMIN_KEY API authentication key for admin tasks like loading and unloading models. If not set, will be the same as --api-key.
|
||||
--api-enable-ipv6 Enable IPv6 for the API
|
||||
--api-disable-ipv4 Disable IPv4 for the API
|
||||
--nowebui Do not launch the Gradio UI. Useful for launching the API in standalone mode.
|
||||
```
|
||||
|
||||
</details>
|
||||
|
|
@ -317,35 +326,37 @@ https://github.com/oobabooga/text-generation-webui/wiki
|
|||
|
||||
## Downloading models
|
||||
|
||||
Models should be placed in the folder `text-generation-webui/models`. They are usually downloaded from [Hugging Face](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads).
|
||||
Models should be placed in the folder `text-generation-webui/user_data/models`. They are usually downloaded from [Hugging Face](https://huggingface.co/models?pipeline_tag=text-generation&sort=downloads).
|
||||
|
||||
* GGUF models are a single file and should be placed directly into `models`. Example:
|
||||
* GGUF models are a single file and should be placed directly into `user_data/models`. Example:
|
||||
|
||||
```
|
||||
text-generation-webui
|
||||
└── models
|
||||
└── llama-2-13b-chat.Q4_K_M.gguf
|
||||
└── user_data
|
||||
└── models
|
||||
└── llama-2-13b-chat.Q4_K_M.gguf
|
||||
```
|
||||
|
||||
* The remaining model types (like 16-bit Transformers models and EXL2 models) are made of several files and must be placed in a subfolder. Example:
|
||||
|
||||
```
|
||||
text-generation-webui
|
||||
├── models
|
||||
│ ├── lmsys_vicuna-33b-v1.3
|
||||
│ │ ├── config.json
|
||||
│ │ ├── generation_config.json
|
||||
│ │ ├── pytorch_model-00001-of-00007.bin
|
||||
│ │ ├── pytorch_model-00002-of-00007.bin
|
||||
│ │ ├── pytorch_model-00003-of-00007.bin
|
||||
│ │ ├── pytorch_model-00004-of-00007.bin
|
||||
│ │ ├── pytorch_model-00005-of-00007.bin
|
||||
│ │ ├── pytorch_model-00006-of-00007.bin
|
||||
│ │ ├── pytorch_model-00007-of-00007.bin
|
||||
│ │ ├── pytorch_model.bin.index.json
|
||||
│ │ ├── special_tokens_map.json
|
||||
│ │ ├── tokenizer_config.json
|
||||
│ │ └── tokenizer.model
|
||||
└── user_data
|
||||
└── models
|
||||
└── lmsys_vicuna-33b-v1.3
|
||||
├── config.json
|
||||
├── generation_config.json
|
||||
├── pytorch_model-00001-of-00007.bin
|
||||
├── pytorch_model-00002-of-00007.bin
|
||||
├── pytorch_model-00003-of-00007.bin
|
||||
├── pytorch_model-00004-of-00007.bin
|
||||
├── pytorch_model-00005-of-00007.bin
|
||||
├── pytorch_model-00006-of-00007.bin
|
||||
├── pytorch_model-00007-of-00007.bin
|
||||
├── pytorch_model.bin.index.json
|
||||
├── special_tokens_map.json
|
||||
├── tokenizer_config.json
|
||||
└── tokenizer.model
|
||||
```
|
||||
|
||||
In both cases, you can use the "Model" tab of the UI to download the model from Hugging Face automatically. It is also possible to download it via the command-line with:
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
'''
|
||||
Downloads models from Hugging Face to models/username_modelname.
|
||||
Downloads models from Hugging Face to user_data/models/username_modelname.
|
||||
|
||||
Example:
|
||||
python download-model.py facebook/opt-1.3b
|
||||
|
|
@ -175,7 +175,7 @@ class ModelDownloader:
|
|||
if model_dir:
|
||||
base_folder = model_dir
|
||||
else:
|
||||
base_folder = 'models' if not is_lora else 'loras'
|
||||
base_folder = 'user_data/models' if not is_lora else 'user_data/loras'
|
||||
|
||||
# If the model is of type GGUF, save directly in the base_folder
|
||||
if is_llamacpp:
|
||||
|
|
@ -356,7 +356,7 @@ if __name__ == '__main__':
|
|||
parser.add_argument('--specific-file', type=str, default=None, help='Name of the specific file to download (if not provided, downloads all).')
|
||||
parser.add_argument('--exclude-pattern', type=str, default=None, help='Regex pattern to exclude files from download.')
|
||||
parser.add_argument('--output', type=str, default=None, help='Save the model files to this folder.')
|
||||
parser.add_argument('--model-dir', type=str, default=None, help='Save the model files to a subfolder of this folder instead of the default one (text-generation-webui/models).')
|
||||
parser.add_argument('--model-dir', type=str, default=None, help='Save the model files to a subfolder of this folder instead of the default one (text-generation-webui/user_data/models).')
|
||||
parser.add_argument('--clean', action='store_true', help='Does not resume the previous download.')
|
||||
parser.add_argument('--check', action='store_true', help='Validates the checksums of model files.')
|
||||
parser.add_argument('--max-retries', type=int, default=7, help='Max retries count when get error in download time.')
|
||||
|
|
|
|||
|
|
@ -175,23 +175,23 @@ def ui():
|
|||
with gr.Row():
|
||||
with gr.Column():
|
||||
with gr.Row():
|
||||
dataset = gr.Dropdown(choices=get_datasets('training/datasets', 'json'), value='None', label='Dataset', info='The dataset file to use for training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(dataset, lambda: None, lambda: {'choices': get_datasets('training/datasets', 'json')}, 'refresh-button')
|
||||
dataset = gr.Dropdown(choices=get_datasets('user_data/training/datasets', 'json'), value='None', label='Dataset', info='The dataset file to use for training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(dataset, lambda: None, lambda: {'choices': get_datasets('user_data/training/datasets', 'json')}, 'refresh-button')
|
||||
with gr.Row():
|
||||
eval_dataset = gr.Dropdown(choices=get_datasets('training/datasets', 'json'), value='None', label='Evaluation Dataset', info='The (optional) dataset file used to evaluate the model after training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(eval_dataset, lambda: None, lambda: {'choices': get_datasets('training/datasets', 'json')}, 'refresh-button')
|
||||
eval_dataset = gr.Dropdown(choices=get_datasets('user_data/training/datasets', 'json'), value='None', label='Evaluation Dataset', info='The (optional) dataset file used to evaluate the model after training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(eval_dataset, lambda: None, lambda: {'choices': get_datasets('user_data/training/datasets', 'json')}, 'refresh-button')
|
||||
|
||||
with gr.Column():
|
||||
with gr.Row():
|
||||
format = gr.Dropdown(choices=get_datasets('training/formats', 'json'), value='None', label='Data Format', info='The format file used to decide how to format the dataset input.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(format, lambda: None, lambda: {'choices': get_datasets('training/formats', 'json')}, 'refresh-button')
|
||||
format = gr.Dropdown(choices=get_datasets('user_data/training/formats', 'json'), value='None', label='Data Format', info='The format file used to decide how to format the dataset input.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(format, lambda: None, lambda: {'choices': get_datasets('user_data/training/formats', 'json')}, 'refresh-button')
|
||||
with gr.Row():
|
||||
eval_steps = gr.Number(label='Evaluate every n steps', value=100, info='If an evaluation dataset is given, test it every time this many steps pass.')
|
||||
|
||||
with gr.Tab(label="Text file"):
|
||||
with gr.Row():
|
||||
raw_text_file = gr.Dropdown(choices=get_datasets('training/datasets', 'txt'), value='None', label='Text file', info='The text file to use for training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(raw_text_file, lambda: None, lambda: {'choices': get_datasets('training/datasets', 'txt')}, 'refresh-button')
|
||||
raw_text_file = gr.Dropdown(choices=get_datasets('user_data/training/datasets', 'txt'), value='None', label='Text file', info='The text file to use for training.', elem_classes=['slim-dropdown'])
|
||||
create_refresh_button(raw_text_file, lambda: None, lambda: {'choices': get_datasets('user_data/training/datasets', 'txt')}, 'refresh-button')
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
|
|
@ -208,7 +208,7 @@ def ui():
|
|||
download_file_url = gr.Textbox(label='Download JSON or txt file to datasets (or formats) folder', value='',info='The URL of a file to download. If on github, make sure you get url of the raw file (https://raw.githubusercontent.com/...). If huggin face, make sure the url has /resolve/ in it not /blob/')
|
||||
with gr.Row():
|
||||
download_check_overwrite = gr.Checkbox(label='Overwrite', value=False, info='Overwrite if file exist')
|
||||
download_folder = gr.Radio(label="Destination", value='training/datasets', choices=['training/datasets', 'training/formats'], interactive=True)
|
||||
download_folder = gr.Radio(label="Destination", value='user_data/training/datasets', choices=['user_data/training/datasets', 'user_data/training/formats'], interactive=True)
|
||||
download_button = gr.Button('Download')
|
||||
download_status = gr.Textbox(label='Download Status', value='', interactive=False)
|
||||
with gr.Row():
|
||||
|
|
@ -235,7 +235,7 @@ def ui():
|
|||
with gr.Row():
|
||||
with gr.Column():
|
||||
models = gr.Dropdown(utils.get_available_models(), label='Models', multiselect=True)
|
||||
evaluate_text_file = gr.Dropdown(choices=['wikitext', 'ptb', 'ptb_new'] + get_datasets('training/datasets', 'txt')[1:], value='wikitext', label='Input dataset', info='The text file on which the model will be evaluated. The first options are automatically downloaded: wikitext, ptb, and ptb_new. The next options are your local text files under training/datasets.')
|
||||
evaluate_text_file = gr.Dropdown(choices=['wikitext', 'ptb', 'ptb_new'] + get_datasets('user_data/training/datasets', 'txt')[1:], value='wikitext', label='Input dataset', info='The text file on which the model will be evaluated. The first options are automatically downloaded: wikitext, ptb, and ptb_new. The next options are your local text files under user_data/training/datasets.')
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
stride_length = gr.Slider(label='Stride', minimum=1, maximum=2048, value=512, step=1, info='Used to make the evaluation faster at the cost of accuracy. 1 = slowest but most accurate. 512 is a common value.')
|
||||
|
|
@ -310,7 +310,7 @@ def ui():
|
|||
|
||||
if raw_text_file not in ['None', '']:
|
||||
logger.info("Loading Text file...")
|
||||
fullpath = clean_path('training/datasets', f'{raw_text_file}')
|
||||
fullpath = clean_path('user_data/training/datasets', f'{raw_text_file}')
|
||||
fullpath = Path(fullpath)
|
||||
if fullpath.is_dir():
|
||||
logger.info('Training path directory {}'.format(raw_text_file))
|
||||
|
|
@ -324,10 +324,10 @@ def ui():
|
|||
logger.info(f"Loaded training file: {file_path.name}")
|
||||
else:
|
||||
try:
|
||||
with open(clean_path('training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
with open(clean_path('user_data/training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
raw_text = file.read().replace('\r', '')
|
||||
except:
|
||||
yield f"{raw_text_file}.txt doesn't seem to exsist anymore... check your training/datasets folder"
|
||||
yield f"{raw_text_file}.txt doesn't seem to exsist anymore... check your user_data/training/datasets folder"
|
||||
return
|
||||
|
||||
|
||||
|
|
@ -353,7 +353,7 @@ def ui():
|
|||
yield "Select format choice for dataset."
|
||||
return
|
||||
|
||||
with open(clean_path('training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
with open(clean_path('user_data/training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
format_data: dict[str, str] = json.load(formatFile)
|
||||
|
||||
def generate_prompt(data_point: dict[str, str]):
|
||||
|
|
@ -381,7 +381,7 @@ def ui():
|
|||
return tokenize_dummy(prompt)
|
||||
|
||||
logger.info("Loading JSON datasets...")
|
||||
data = load_dataset("json", data_files=clean_path('training/datasets', f'{dataset}.json'))
|
||||
data = load_dataset("json", data_files=clean_path('user_data/training/datasets', f'{dataset}.json'))
|
||||
|
||||
data_keys = []
|
||||
|
||||
|
|
@ -456,7 +456,7 @@ def ui():
|
|||
#debug_slicer.change(lambda x: non_serialized_params.update({"debug_slicer": x}), debug_slicer, None)
|
||||
|
||||
def update_dataset():
|
||||
return gr.update(choices=get_datasets('training/datasets', 'json')), gr.update(choices=get_datasets('training/datasets', 'txt'))
|
||||
return gr.update(choices=get_datasets('user_data/training/datasets', 'json')), gr.update(choices=get_datasets('user_data/training/datasets', 'txt'))
|
||||
|
||||
download_button.click(download_file_from_url, [download_file_url,download_check_overwrite,download_folder] , download_status).then(update_dataset,None,[dataset , raw_text_file])
|
||||
|
||||
|
|
@ -670,7 +670,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
if raw_text_file not in ['None', '']:
|
||||
train_template["template_type"] = "raw_text"
|
||||
logger.info("Loading text file...")
|
||||
fullpath = clean_path('training/datasets', f'{raw_text_file}')
|
||||
fullpath = clean_path('user_data/training/datasets', f'{raw_text_file}')
|
||||
fullpath = Path(fullpath)
|
||||
if fullpath.is_dir():
|
||||
logger.info('Training path directory {}'.format(raw_text_file))
|
||||
|
|
@ -683,7 +683,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
|
||||
logger.info(f"Loaded training file: {file_path.name}")
|
||||
else:
|
||||
with open(clean_path('training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
with open(clean_path('user_data/training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
raw_text = file.read().replace('\r', '')
|
||||
|
||||
# FPHAM PRECISE SLICING
|
||||
|
|
@ -720,7 +720,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
|
||||
train_template["template_type"] = "dataset"
|
||||
|
||||
with open(clean_path('training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
with open(clean_path('user_data/training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
format_data: dict[str, str] = json.load(formatFile)
|
||||
|
||||
# == store training prompt ==
|
||||
|
|
@ -742,7 +742,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
return tokenize(prompt, add_eos_token, add_bos_token)
|
||||
|
||||
logger.info("Loading JSON datasets...")
|
||||
data = load_dataset("json", data_files=clean_path('training/datasets', f'{dataset}.json'))
|
||||
data = load_dataset("json", data_files=clean_path('user_data/training/datasets', f'{dataset}.json'))
|
||||
train_data = data['train'].map(generate_and_tokenize_prompt, new_fingerprint='%030x' % random.randrange(16**30))
|
||||
|
||||
print(f"BOS: {add_bos_token} EOS: {add_eos_token}")
|
||||
|
|
@ -751,7 +751,7 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
if eval_dataset == 'None':
|
||||
eval_data = None
|
||||
else:
|
||||
eval_data = load_dataset("json", data_files=clean_path('training/datasets', f'{eval_dataset}.json'))
|
||||
eval_data = load_dataset("json", data_files=clean_path('user_data/training/datasets', f'{eval_dataset}.json'))
|
||||
eval_data = eval_data['train'].map(generate_and_tokenize_prompt, new_fingerprint='%030x' % random.randrange(16**30))
|
||||
|
||||
# == We MUST reload model if it went through any previous training, even failed one ==
|
||||
|
|
@ -1157,11 +1157,11 @@ def do_train(lora_name: str, always_override: bool, save_steps: int, micro_batch
|
|||
decoded_entries.append({"value": decoded_text})
|
||||
|
||||
# Write the log file
|
||||
Path('logs').mkdir(exist_ok=True)
|
||||
with open(Path('logs/train_dataset_sample.json'), 'w') as json_file:
|
||||
Path('user_data/logs').mkdir(exist_ok=True)
|
||||
with open(Path('user_data/logs/train_dataset_sample.json'), 'w') as json_file:
|
||||
json.dump(decoded_entries, json_file, indent=4)
|
||||
|
||||
logger.info("Log file 'train_dataset_sample.json' created in the 'logs' directory.")
|
||||
logger.info("Log file 'train_dataset_sample.json' created in the 'user_data/logs' directory.")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create log file due to error: {e}")
|
||||
|
||||
|
|
|
|||
|
|
@ -194,13 +194,13 @@ def precise_cut(text: str, overlap: bool, min_chars_cut: int, eos_to_hc: bool, c
|
|||
|
||||
if debug_slicer:
|
||||
# Write the log file
|
||||
Path('logs').mkdir(exist_ok=True)
|
||||
Path('user_data/logs').mkdir(exist_ok=True)
|
||||
sentencelist_dict = {index: sentence for index, sentence in enumerate(sentencelist)}
|
||||
output_file = "logs/sentencelist.json"
|
||||
output_file = "user_data/logs/sentencelist.json"
|
||||
with open(output_file, 'w') as f:
|
||||
json.dump(sentencelist_dict, f,indent=2)
|
||||
|
||||
print("Saved sentencelist.json in logs folder")
|
||||
print("Saved sentencelist.json in user_data/logs folder")
|
||||
|
||||
return sentencelist
|
||||
|
||||
|
|
@ -281,13 +281,13 @@ def sliding_block_cut(text: str, min_chars_cut: int, eos_to_hc: bool, cutoff_len
|
|||
|
||||
if debug_slicer:
|
||||
# Write the log file
|
||||
Path('logs').mkdir(exist_ok=True)
|
||||
Path('user_data/logs').mkdir(exist_ok=True)
|
||||
sentencelist_dict = {index: sentence for index, sentence in enumerate(sentencelist)}
|
||||
output_file = "logs/sentencelist.json"
|
||||
output_file = "user_data/logs/sentencelist.json"
|
||||
with open(output_file, 'w') as f:
|
||||
json.dump(sentencelist_dict, f,indent=2)
|
||||
|
||||
print("Saved sentencelist.json in logs folder")
|
||||
print("Saved sentencelist.json in user_data/logs folder")
|
||||
|
||||
return sentencelist
|
||||
|
||||
|
|
|
|||
|
|
@ -72,13 +72,13 @@ def generate_html():
|
|||
global cards
|
||||
cards = []
|
||||
# Iterate through files in image folder
|
||||
for file in sorted(Path("characters").glob("*")):
|
||||
for file in sorted(Path("user_data/characters").glob("*")):
|
||||
if file.suffix in [".json", ".yml", ".yaml"]:
|
||||
character = file.stem
|
||||
container_html = '<div class="character-container">'
|
||||
image_html = "<div class='placeholder'></div>"
|
||||
|
||||
for path in [Path(f"characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]:
|
||||
for path in [Path(f"user_data/characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]:
|
||||
if path.exists():
|
||||
image_html = f'<img src="file/{get_image_cache(path)}">'
|
||||
break
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ from pydantic import BaseModel, Field
|
|||
|
||||
|
||||
class GenerationOptions(BaseModel):
|
||||
preset: str | None = Field(default=None, description="The name of a file under text-generation-webui/presets (without the .yaml extension). The sampling parameters that get overwritten by this option are the keys in the default_preset() function in modules/presets.py.")
|
||||
preset: str | None = Field(default=None, description="The name of a file under text-generation-webui/user_data/presets (without the .yaml extension). The sampling parameters that get overwritten by this option are the keys in the default_preset() function in modules/presets.py.")
|
||||
dynatemp_low: float = 1
|
||||
dynatemp_high: float = 1
|
||||
dynatemp_exponent: float = 1
|
||||
|
|
@ -103,10 +103,10 @@ class ChatCompletionRequestParams(BaseModel):
|
|||
|
||||
mode: str = Field(default='instruct', description="Valid options: instruct, chat, chat-instruct.")
|
||||
|
||||
instruction_template: str | None = Field(default=None, description="An instruction template defined under text-generation-webui/instruction-templates. If not set, the correct template will be automatically obtained from the model metadata.")
|
||||
instruction_template: str | None = Field(default=None, description="An instruction template defined under text-generation-webui/user_data/instruction-templates. If not set, the correct template will be automatically obtained from the model metadata.")
|
||||
instruction_template_str: str | None = Field(default=None, description="A Jinja2 instruction template. If set, will take precedence over everything else.")
|
||||
|
||||
character: str | None = Field(default=None, description="A character defined under text-generation-webui/characters. If not set, the default \"Assistant\" character will be used.")
|
||||
character: str | None = Field(default=None, description="A character defined under text-generation-webui/user_data/characters. If not set, the default \"Assistant\" character will be used.")
|
||||
bot_name: str | None = Field(default=None, description="Overwrites the value set by character field.", alias="name2")
|
||||
context: str | None = Field(default=None, description="Overwrites the value set by character field.")
|
||||
greeting: str | None = Field(default=None, description="Overwrites the value set by character field.")
|
||||
|
|
|
|||
|
|
@ -395,7 +395,7 @@ let bigPictureVisible = false;
|
|||
function addBigPicture() {
|
||||
var imgElement = document.createElement("img");
|
||||
var timestamp = new Date().getTime();
|
||||
imgElement.src = "/file/cache/pfp_character.png?time=" + timestamp;
|
||||
imgElement.src = "/file/user_data/cache/pfp_character.png?time=" + timestamp;
|
||||
imgElement.classList.add("bigProfilePicture");
|
||||
imgElement.addEventListener("load", function () {
|
||||
this.style.visibility = "visible";
|
||||
|
|
|
|||
|
|
@ -2,6 +2,6 @@ function updateBigPicture() {
|
|||
var existingElement = document.querySelector(".bigProfilePicture");
|
||||
if (existingElement) {
|
||||
var timestamp = new Date().getTime();
|
||||
existingElement.src = "/file/cache/pfp_character.png?time=" + timestamp;
|
||||
existingElement.src = "/file/user_data/cache/pfp_character.png?time=" + timestamp;
|
||||
}
|
||||
}
|
||||
|
|
|
|||
|
|
@ -525,9 +525,9 @@ def start_new_chat(state):
|
|||
|
||||
def get_history_file_path(unique_id, character, mode):
|
||||
if mode == 'instruct':
|
||||
p = Path(f'logs/instruct/{unique_id}.json')
|
||||
p = Path(f'user_data/logs/instruct/{unique_id}.json')
|
||||
else:
|
||||
p = Path(f'logs/chat/{character}/{unique_id}.json')
|
||||
p = Path(f'user_data/logs/chat/{character}/{unique_id}.json')
|
||||
|
||||
return p
|
||||
|
||||
|
|
@ -563,13 +563,13 @@ def rename_history(old_id, new_id, character, mode):
|
|||
|
||||
def get_paths(state):
|
||||
if state['mode'] == 'instruct':
|
||||
return Path('logs/instruct').glob('*.json')
|
||||
return Path('user_data/logs/instruct').glob('*.json')
|
||||
else:
|
||||
character = state['character_menu']
|
||||
|
||||
# Handle obsolete filenames and paths
|
||||
old_p = Path(f'logs/{character}_persistent.json')
|
||||
new_p = Path(f'logs/persistent_{character}.json')
|
||||
old_p = Path(f'user_data/logs/{character}_persistent.json')
|
||||
new_p = Path(f'user_data/logs/persistent_{character}.json')
|
||||
if old_p.exists():
|
||||
logger.warning(f"Renaming \"{old_p}\" to \"{new_p}\"")
|
||||
old_p.rename(new_p)
|
||||
|
|
@ -581,7 +581,7 @@ def get_paths(state):
|
|||
p.parent.mkdir(exist_ok=True)
|
||||
new_p.rename(p)
|
||||
|
||||
return Path(f'logs/chat/{character}').glob('*.json')
|
||||
return Path(f'user_data/logs/chat/{character}').glob('*.json')
|
||||
|
||||
|
||||
def find_all_histories(state):
|
||||
|
|
@ -732,7 +732,7 @@ def generate_pfp_cache(character):
|
|||
if not cache_folder.exists():
|
||||
cache_folder.mkdir()
|
||||
|
||||
for path in [Path(f"characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]:
|
||||
for path in [Path(f"user_data/characters/{character}.{extension}") for extension in ['png', 'jpg', 'jpeg']]:
|
||||
if path.exists():
|
||||
original_img = Image.open(path)
|
||||
original_img.save(Path(f'{cache_folder}/pfp_character.png'), format='PNG')
|
||||
|
|
@ -752,12 +752,12 @@ def load_character(character, name1, name2):
|
|||
|
||||
filepath = None
|
||||
for extension in ["yml", "yaml", "json"]:
|
||||
filepath = Path(f'characters/{character}.{extension}')
|
||||
filepath = Path(f'user_data/characters/{character}.{extension}')
|
||||
if filepath.exists():
|
||||
break
|
||||
|
||||
if filepath is None or not filepath.exists():
|
||||
logger.error(f"Could not find the character \"{character}\" inside characters/. No character has been loaded.")
|
||||
logger.error(f"Could not find the character \"{character}\" inside user_data/characters. No character has been loaded.")
|
||||
raise ValueError
|
||||
|
||||
file_contents = open(filepath, 'r', encoding='utf-8').read()
|
||||
|
|
@ -796,7 +796,7 @@ def load_instruction_template(template):
|
|||
if template == 'None':
|
||||
return ''
|
||||
|
||||
for filepath in [Path(f'instruction-templates/{template}.yaml'), Path('instruction-templates/Alpaca.yaml')]:
|
||||
for filepath in [Path(f'user_data/instruction-templates/{template}.yaml'), Path('user_data/instruction-templates/Alpaca.yaml')]:
|
||||
if filepath.exists():
|
||||
break
|
||||
else:
|
||||
|
|
@ -838,17 +838,17 @@ def upload_character(file, img, tavern=False):
|
|||
|
||||
outfile_name = name
|
||||
i = 1
|
||||
while Path(f'characters/{outfile_name}.yaml').exists():
|
||||
while Path(f'user_data/characters/{outfile_name}.yaml').exists():
|
||||
outfile_name = f'{name}_{i:03d}'
|
||||
i += 1
|
||||
|
||||
with open(Path(f'characters/{outfile_name}.yaml'), 'w', encoding='utf-8') as f:
|
||||
with open(Path(f'user_data/characters/{outfile_name}.yaml'), 'w', encoding='utf-8') as f:
|
||||
f.write(yaml_data)
|
||||
|
||||
if img is not None:
|
||||
img.save(Path(f'characters/{outfile_name}.png'))
|
||||
img.save(Path(f'user_data/characters/{outfile_name}.png'))
|
||||
|
||||
logger.info(f'New character saved to "characters/{outfile_name}.yaml".')
|
||||
logger.info(f'New character saved to "user_data/characters/{outfile_name}.yaml".')
|
||||
return gr.update(value=outfile_name, choices=get_available_characters())
|
||||
|
||||
|
||||
|
|
@ -923,9 +923,9 @@ def save_character(name, greeting, context, picture, filename):
|
|||
return
|
||||
|
||||
data = generate_character_yaml(name, greeting, context)
|
||||
filepath = Path(f'characters/{filename}.yaml')
|
||||
filepath = Path(f'user_data/characters/{filename}.yaml')
|
||||
save_file(filepath, data)
|
||||
path_to_img = Path(f'characters/{filename}.png')
|
||||
path_to_img = Path(f'user_data/characters/{filename}.png')
|
||||
if picture is not None:
|
||||
picture.save(path_to_img)
|
||||
logger.info(f'Saved {path_to_img}.')
|
||||
|
|
@ -933,9 +933,9 @@ def save_character(name, greeting, context, picture, filename):
|
|||
|
||||
def delete_character(name, instruct=False):
|
||||
for extension in ["yml", "yaml", "json"]:
|
||||
delete_file(Path(f'characters/{name}.{extension}'))
|
||||
delete_file(Path(f'user_data/characters/{name}.{extension}'))
|
||||
|
||||
delete_file(Path(f'characters/{name}.png'))
|
||||
delete_file(Path(f'user_data/characters/{name}.png'))
|
||||
|
||||
|
||||
def jinja_template_from_old_format(params, verbose=False):
|
||||
|
|
@ -1238,7 +1238,7 @@ def handle_save_template_click(instruction_template_str):
|
|||
contents = generate_instruction_template_yaml(instruction_template_str)
|
||||
return [
|
||||
"My Template.yaml",
|
||||
"instruction-templates/",
|
||||
"user_data/instruction-templates/",
|
||||
contents,
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
|
@ -1247,7 +1247,7 @@ def handle_save_template_click(instruction_template_str):
|
|||
def handle_delete_template_click(template):
|
||||
return [
|
||||
f"{template}.yaml",
|
||||
"instruction-templates/",
|
||||
"user_data/instruction-templates/",
|
||||
gr.update(visible=False)
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -12,8 +12,8 @@ from modules.text_generation import encode
|
|||
|
||||
|
||||
def load_past_evaluations():
|
||||
if Path('logs/evaluations.csv').exists():
|
||||
df = pd.read_csv(Path('logs/evaluations.csv'), dtype=str)
|
||||
if Path('user_data/logs/evaluations.csv').exists():
|
||||
df = pd.read_csv(Path('user_data/logs/evaluations.csv'), dtype=str)
|
||||
df['Perplexity'] = pd.to_numeric(df['Perplexity'])
|
||||
return df
|
||||
else:
|
||||
|
|
@ -26,7 +26,7 @@ past_evaluations = load_past_evaluations()
|
|||
def save_past_evaluations(df):
|
||||
global past_evaluations
|
||||
past_evaluations = df
|
||||
filepath = Path('logs/evaluations.csv')
|
||||
filepath = Path('user_data/logs/evaluations.csv')
|
||||
filepath.parent.mkdir(parents=True, exist_ok=True)
|
||||
df.to_csv(filepath, index=False)
|
||||
|
||||
|
|
@ -69,7 +69,7 @@ def calculate_perplexity(models, input_dataset, stride, _max_length):
|
|||
data = load_dataset('ptb_text_only', 'penn_treebank', split='test')
|
||||
text = " ".join(data['sentence'])
|
||||
else:
|
||||
with open(Path(f'training/datasets/{input_dataset}.txt'), 'r', encoding='utf-8') as f:
|
||||
with open(Path(f'user_data/training/datasets/{input_dataset}.txt'), 'r', encoding='utf-8') as f:
|
||||
text = f.read()
|
||||
|
||||
for model in models:
|
||||
|
|
|
|||
|
|
@ -387,13 +387,13 @@ def generate_cai_chat_html(history, name1, name2, style, character, reset_cache=
|
|||
|
||||
# We use ?character and ?time.time() to force the browser to reset caches
|
||||
img_bot = (
|
||||
f'<img src="file/cache/pfp_character_thumb.png?{character}" class="pfp_character">'
|
||||
if Path("cache/pfp_character_thumb.png").exists() else ''
|
||||
f'<img src="file/user_data/cache/pfp_character_thumb.png?{character}" class="pfp_character">'
|
||||
if Path("user_data/cache/pfp_character_thumb.png").exists() else ''
|
||||
)
|
||||
|
||||
img_me = (
|
||||
f'<img src="file/cache/pfp_me.png?{time.time() if reset_cache else ""}">'
|
||||
if Path("cache/pfp_me.png").exists() else ''
|
||||
f'<img src="file/user_data/cache/pfp_me.png?{time.time() if reset_cache else ""}">'
|
||||
if Path("user_data/cache/pfp_me.png").exists() else ''
|
||||
)
|
||||
|
||||
for i in range(len(history['visible'])):
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ def get_fallback_settings():
|
|||
def get_model_metadata(model):
|
||||
model_settings = {}
|
||||
|
||||
# Get settings from models/config.yaml and models/config-user.yaml
|
||||
# Get settings from user_data/models/config.yaml and user_data/models/config-user.yaml
|
||||
settings = shared.model_config
|
||||
for pat in settings:
|
||||
if re.match(pat.lower(), Path(model).name.lower()):
|
||||
|
|
@ -144,7 +144,7 @@ def get_model_metadata(model):
|
|||
if 'rope_freq_base' in model_settings and model_settings['rope_freq_base'] == 10000:
|
||||
model_settings.pop('rope_freq_base')
|
||||
|
||||
# Apply user settings from models/config-user.yaml
|
||||
# Apply user settings from user_data/models/config-user.yaml
|
||||
settings = shared.user_config
|
||||
for pat in settings:
|
||||
if re.match(pat.lower(), Path(model).name.lower()):
|
||||
|
|
@ -223,7 +223,7 @@ def apply_model_settings_to_state(model, state):
|
|||
|
||||
def save_model_settings(model, state):
|
||||
'''
|
||||
Save the settings for this model to models/config-user.yaml
|
||||
Save the settings for this model to user_data/models/config-user.yaml
|
||||
'''
|
||||
if model == 'None':
|
||||
yield ("Not saving the settings because no model is selected in the menu.")
|
||||
|
|
|
|||
|
|
@ -58,7 +58,7 @@ def presets_params():
|
|||
def load_preset(name, verbose=False):
|
||||
generate_params = default_preset()
|
||||
if name not in ['None', None, '']:
|
||||
path = Path(f'presets/{name}.yaml')
|
||||
path = Path(f'user_data/presets/{name}.yaml')
|
||||
if path.exists():
|
||||
with open(path, 'r') as infile:
|
||||
preset = yaml.safe_load(infile)
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ def load_prompt(fname):
|
|||
if fname in ['None', '']:
|
||||
return ''
|
||||
else:
|
||||
file_path = Path(f'prompts/{fname}.txt')
|
||||
file_path = Path(f'user_data/prompts/{fname}.txt')
|
||||
if not file_path.exists():
|
||||
return ''
|
||||
|
||||
|
|
|
|||
|
|
@ -78,8 +78,8 @@ group.add_argument('--multi-user', action='store_true', help='Multi-user mode. C
|
|||
group.add_argument('--character', type=str, help='The name of the character to load in chat mode by default.')
|
||||
group.add_argument('--model', type=str, help='Name of the model to load by default.')
|
||||
group.add_argument('--lora', type=str, nargs='+', help='The list of LoRAs to load. If you want to load more than one LoRA, write the names separated by spaces.')
|
||||
group.add_argument('--model-dir', type=str, default='models/', help='Path to directory with all the models.')
|
||||
group.add_argument('--lora-dir', type=str, default='loras/', help='Path to directory with all the loras.')
|
||||
group.add_argument('--model-dir', type=str, default='user_data/models', help='Path to directory with all the models.')
|
||||
group.add_argument('--lora-dir', type=str, default='user_data/loras', help='Path to directory with all the loras.')
|
||||
group.add_argument('--model-menu', action='store_true', help='Show a model menu in the terminal when the web UI is first launched.')
|
||||
group.add_argument('--settings', type=str, help='Load the default interface settings from this yaml file. See settings-template.yaml for an example. If you create a file called settings.yaml, this file will be loaded by default without the need to use the --settings flag.')
|
||||
group.add_argument('--extensions', type=str, nargs='+', help='The list of extensions to load. If you want to load more than one extension, write the names separated by spaces.')
|
||||
|
|
@ -95,7 +95,7 @@ group = parser.add_argument_group('Transformers/Accelerate')
|
|||
group.add_argument('--cpu', action='store_true', help='Use the CPU to generate text. Warning: Training on CPU is extremely slow.')
|
||||
group.add_argument('--cpu-memory', type=float, default=0, help='Maximum CPU memory in GiB. Use this for CPU offloading.')
|
||||
group.add_argument('--disk', action='store_true', help='If the model is too large for your GPU(s) and CPU combined, send the remaining layers to the disk.')
|
||||
group.add_argument('--disk-cache-dir', type=str, default='cache', help='Directory to save the disk cache to. Defaults to "cache".')
|
||||
group.add_argument('--disk-cache-dir', type=str, default='user_data/cache', help='Directory to save the disk cache to. Defaults to "user_data/cache".')
|
||||
group.add_argument('--load-in-8bit', action='store_true', help='Load the model with 8-bit precision (using bitsandbytes).')
|
||||
group.add_argument('--bf16', action='store_true', help='Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.')
|
||||
group.add_argument('--no-cache', action='store_true', help='Set use_cache to False while generating text. This reduces VRAM usage slightly, but it comes at a performance cost.')
|
||||
|
|
@ -207,7 +207,7 @@ group.add_argument('--nowebui', action='store_true', help='Do not launch the Gra
|
|||
group = parser.add_argument_group('Deprecated')
|
||||
|
||||
# Handle CMD_FLAGS.txt
|
||||
cmd_flags_path = Path(__file__).parent.parent / "CMD_FLAGS.txt"
|
||||
cmd_flags_path = Path(__file__).parent.parent / "user_data" / "CMD_FLAGS.txt"
|
||||
if cmd_flags_path.exists():
|
||||
with cmd_flags_path.open('r', encoding='utf-8') as f:
|
||||
cmd_flags = ' '.join(
|
||||
|
|
|
|||
|
|
@ -106,23 +106,23 @@ def create_ui():
|
|||
with gr.Column():
|
||||
with gr.Tab(label='Formatted Dataset'):
|
||||
with gr.Row():
|
||||
format = gr.Dropdown(choices=utils.get_datasets('training/formats', 'json'), value='None', label='Data Format', info='The format file used to decide how to format the dataset input.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(format, lambda: None, lambda: {'choices': utils.get_datasets('training/formats', 'json')}, 'refresh-button', interactive=not mu)
|
||||
format = gr.Dropdown(choices=utils.get_datasets('user_data/training/formats', 'json'), value='None', label='Data Format', info='The format file used to decide how to format the dataset input.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(format, lambda: None, lambda: {'choices': utils.get_datasets('user_data/training/formats', 'json')}, 'refresh-button', interactive=not mu)
|
||||
|
||||
with gr.Row():
|
||||
dataset = gr.Dropdown(choices=utils.get_datasets('training/datasets', 'json'), value='None', label='Dataset', info='The dataset file to use for training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(dataset, lambda: None, lambda: {'choices': utils.get_datasets('training/datasets', 'json')}, 'refresh-button', interactive=not mu)
|
||||
dataset = gr.Dropdown(choices=utils.get_datasets('user_data/training/datasets', 'json'), value='None', label='Dataset', info='The dataset file to use for training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(dataset, lambda: None, lambda: {'choices': utils.get_datasets('user_data/training/datasets', 'json')}, 'refresh-button', interactive=not mu)
|
||||
|
||||
with gr.Row():
|
||||
eval_dataset = gr.Dropdown(choices=utils.get_datasets('training/datasets', 'json'), value='None', label='Evaluation Dataset', info='The (optional) dataset file used to evaluate the model after training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(eval_dataset, lambda: None, lambda: {'choices': utils.get_datasets('training/datasets', 'json')}, 'refresh-button', interactive=not mu)
|
||||
eval_dataset = gr.Dropdown(choices=utils.get_datasets('user_data/training/datasets', 'json'), value='None', label='Evaluation Dataset', info='The (optional) dataset file used to evaluate the model after training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(eval_dataset, lambda: None, lambda: {'choices': utils.get_datasets('user_data/training/datasets', 'json')}, 'refresh-button', interactive=not mu)
|
||||
|
||||
eval_steps = gr.Number(label='Evaluate every n steps', value=100, info='If an evaluation dataset is given, test it every time this many steps pass.')
|
||||
|
||||
with gr.Tab(label="Raw text file"):
|
||||
with gr.Row():
|
||||
raw_text_file = gr.Dropdown(choices=utils.get_datasets('training/datasets', 'txt'), value='None', label='Text file', info='The raw text file to use for training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(raw_text_file, lambda: None, lambda: {'choices': utils.get_datasets('training/datasets', 'txt')}, 'refresh-button', interactive=not mu)
|
||||
raw_text_file = gr.Dropdown(choices=utils.get_datasets('user_data/training/datasets', 'txt'), value='None', label='Text file', info='The raw text file to use for training.', elem_classes=['slim-dropdown'], interactive=not mu)
|
||||
ui.create_refresh_button(raw_text_file, lambda: None, lambda: {'choices': utils.get_datasets('user_data/training/datasets', 'txt')}, 'refresh-button', interactive=not mu)
|
||||
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
|
|
@ -143,7 +143,7 @@ def create_ui():
|
|||
with gr.Row():
|
||||
with gr.Column():
|
||||
models = gr.Dropdown(utils.get_available_models(), label='Models', multiselect=True, interactive=not mu)
|
||||
evaluate_text_file = gr.Dropdown(choices=['wikitext', 'ptb', 'ptb_new'] + utils.get_datasets('training/datasets', 'txt')[1:], value='wikitext', label='Input dataset', info='The raw text file on which the model will be evaluated. The first options are automatically downloaded: wikitext, ptb, and ptb_new. The next options are your local text files under training/datasets.', interactive=not mu)
|
||||
evaluate_text_file = gr.Dropdown(choices=['wikitext', 'ptb', 'ptb_new'] + utils.get_datasets('user_data/training/datasets', 'txt')[1:], value='wikitext', label='Input dataset', info='The raw text file on which the model will be evaluated. The first options are automatically downloaded: wikitext, ptb, and ptb_new. The next options are your local text files under user_data/training/datasets.', interactive=not mu)
|
||||
with gr.Row():
|
||||
with gr.Column():
|
||||
stride_length = gr.Slider(label='Stride', minimum=0, maximum=32768, value=512, step=256, info='Used to make the evaluation faster at the cost of accuracy. 1 = slowest but most accurate. 512 is a common value.')
|
||||
|
|
@ -402,7 +402,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
|
|||
if raw_text_file not in ['None', '']:
|
||||
train_template["template_type"] = "raw_text"
|
||||
logger.info("Loading raw text file dataset")
|
||||
fullpath = clean_path('training/datasets', f'{raw_text_file}')
|
||||
fullpath = clean_path('user_data/training/datasets', f'{raw_text_file}')
|
||||
fullpath = Path(fullpath)
|
||||
if fullpath.is_dir():
|
||||
logger.info('Training path directory {}'.format(raw_text_file))
|
||||
|
|
@ -415,7 +415,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
|
|||
|
||||
logger.info(f"Loaded training file: {file_path.name}")
|
||||
else:
|
||||
with open(clean_path('training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
with open(clean_path('user_data/training/datasets', f'{raw_text_file}.txt'), 'r', encoding='utf-8') as file:
|
||||
raw_text = file.read().replace('\r', '')
|
||||
|
||||
cut_string = hard_cut_string.replace('\\n', '\n')
|
||||
|
|
@ -460,7 +460,7 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
|
|||
|
||||
train_template["template_type"] = "dataset"
|
||||
|
||||
with open(clean_path('training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
with open(clean_path('user_data/training/formats', f'{format}.json'), 'r', encoding='utf-8-sig') as formatFile:
|
||||
format_data: dict[str, str] = json.load(formatFile)
|
||||
|
||||
# == store training prompt ==
|
||||
|
|
@ -482,13 +482,13 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
|
|||
return tokenize(prompt, add_eos_token)
|
||||
|
||||
logger.info("Loading JSON datasets")
|
||||
data = load_dataset("json", data_files=clean_path('training/datasets', f'{dataset}.json'))
|
||||
data = load_dataset("json", data_files=clean_path('user_data/training/datasets', f'{dataset}.json'))
|
||||
train_data = data['train'].map(generate_and_tokenize_prompt, new_fingerprint='%030x' % random.randrange(16**30))
|
||||
|
||||
if eval_dataset == 'None':
|
||||
eval_data = None
|
||||
else:
|
||||
eval_data = load_dataset("json", data_files=clean_path('training/datasets', f'{eval_dataset}.json'))
|
||||
eval_data = load_dataset("json", data_files=clean_path('user_data/training/datasets', f'{eval_dataset}.json'))
|
||||
eval_data = eval_data['train'].map(generate_and_tokenize_prompt, new_fingerprint='%030x' % random.randrange(16**30))
|
||||
|
||||
# == We MUST reload model if it went through any previous training, even failed one ==
|
||||
|
|
@ -676,11 +676,11 @@ def do_train(lora_name: str, always_override: bool, q_proj_en: bool, v_proj_en:
|
|||
decoded_entries.append({"value": decoded_text})
|
||||
|
||||
# Write the log file
|
||||
Path('logs').mkdir(exist_ok=True)
|
||||
with open(Path('logs/train_dataset_sample.json'), 'w') as json_file:
|
||||
Path('user_data/logs').mkdir(exist_ok=True)
|
||||
with open(Path('user_data/logs/train_dataset_sample.json'), 'w') as json_file:
|
||||
json.dump(decoded_entries, json_file, indent=4)
|
||||
|
||||
logger.info("Log file 'train_dataset_sample.json' created in the 'logs' directory.")
|
||||
logger.info("Log file 'train_dataset_sample.json' created in the 'user_data/logs' directory.")
|
||||
except Exception as e:
|
||||
logger.error(f"Failed to create log file due to error: {e}")
|
||||
|
||||
|
|
|
|||
|
|
@ -249,7 +249,7 @@ def load_model_HF(model_name):
|
|||
)
|
||||
|
||||
if shared.args.disk:
|
||||
params['offload_folder'] = shared.args.disk_cache_dir
|
||||
params['offload_folder'] = str(Path(shared.args.disk_cache_dir))
|
||||
|
||||
if shared.args.compress_pos_emb > 1:
|
||||
params['rope_scaling'] = {'type': 'linear', 'factor': shared.args.compress_pos_emb}
|
||||
|
|
|
|||
|
|
@ -94,7 +94,7 @@ if not shared.args.old_colors:
|
|||
input_radius='0.375rem',
|
||||
)
|
||||
|
||||
if Path("notification.mp3").exists():
|
||||
if Path("user_data/notification.mp3").exists():
|
||||
audio_notification_js = "document.querySelector('#audio_notification audio')?.play();"
|
||||
else:
|
||||
audio_notification_js = ""
|
||||
|
|
|
|||
|
|
@ -146,7 +146,7 @@ def create_chat_settings_ui():
|
|||
|
||||
with gr.Column(scale=1):
|
||||
shared.gradio['character_picture'] = gr.Image(label='Character picture', type='pil', interactive=not mu)
|
||||
shared.gradio['your_picture'] = gr.Image(label='Your picture', type='pil', value=Image.open(Path('cache/pfp_me.png')) if Path('cache/pfp_me.png').exists() else None, interactive=not mu)
|
||||
shared.gradio['your_picture'] = gr.Image(label='Your picture', type='pil', value=Image.open(Path('user_data/cache/pfp_me.png')) if Path('user_data/cache/pfp_me.png').exists() else None, interactive=not mu)
|
||||
|
||||
with gr.Tab('Instruction template'):
|
||||
with gr.Row():
|
||||
|
|
|
|||
|
|
@ -102,7 +102,7 @@ def handle_save_prompt(text):
|
|||
return [
|
||||
text,
|
||||
utils.current_time() + ".txt",
|
||||
"prompts/",
|
||||
"user_data/prompts/",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
||||
|
|
@ -110,6 +110,6 @@ def handle_save_prompt(text):
|
|||
def handle_delete_prompt(prompt):
|
||||
return [
|
||||
prompt + ".txt",
|
||||
"prompts/",
|
||||
"user_data/prompts/",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ def create_ui():
|
|||
|
||||
# Character saver/deleter
|
||||
with gr.Group(visible=False, elem_classes='file-saver') as shared.gradio['character_saver']:
|
||||
shared.gradio['save_character_filename'] = gr.Textbox(lines=1, label='File name', info='The character will be saved to your characters/ folder with this base filename.')
|
||||
shared.gradio['save_character_filename'] = gr.Textbox(lines=1, label='File name', info='The character will be saved to your user_data/characters folder with this base filename.')
|
||||
with gr.Row():
|
||||
shared.gradio['save_character_cancel'] = gr.Button('Cancel', elem_classes="small-button")
|
||||
shared.gradio['save_character_confirm'] = gr.Button('Save', elem_classes="small-button", variant='primary', interactive=not mu)
|
||||
|
|
@ -41,7 +41,7 @@ def create_ui():
|
|||
|
||||
# Preset saver
|
||||
with gr.Group(visible=False, elem_classes='file-saver') as shared.gradio['preset_saver']:
|
||||
shared.gradio['save_preset_filename'] = gr.Textbox(lines=1, label='File name', info='The preset will be saved to your presets/ folder with this base filename.')
|
||||
shared.gradio['save_preset_filename'] = gr.Textbox(lines=1, label='File name', info='The preset will be saved to your user_data/presets folder with this base filename.')
|
||||
shared.gradio['save_preset_contents'] = gr.Textbox(lines=10, label='File contents')
|
||||
with gr.Row():
|
||||
shared.gradio['save_preset_cancel'] = gr.Button('Cancel', elem_classes="small-button")
|
||||
|
|
@ -72,7 +72,7 @@ def create_event_handlers():
|
|||
|
||||
def handle_save_preset_confirm_click(filename, contents):
|
||||
try:
|
||||
utils.save_file(f"presets/{filename}.yaml", contents)
|
||||
utils.save_file(f"user_data/presets/{filename}.yaml", contents)
|
||||
available_presets = utils.get_available_presets()
|
||||
output = gr.update(choices=available_presets, value=filename)
|
||||
except Exception:
|
||||
|
|
@ -145,7 +145,7 @@ def handle_save_preset_click(state):
|
|||
def handle_delete_preset_click(preset):
|
||||
return [
|
||||
f"{preset}.yaml",
|
||||
"presets/",
|
||||
"user_data/presets/",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
||||
|
|
@ -154,7 +154,7 @@ def handle_save_grammar_click(grammar_string):
|
|||
return [
|
||||
grammar_string,
|
||||
"My Fancy Grammar.gbnf",
|
||||
"grammars/",
|
||||
"user_data/grammars/",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
||||
|
|
@ -162,6 +162,6 @@ def handle_save_grammar_click(grammar_string):
|
|||
def handle_delete_grammar_click(grammar_file):
|
||||
return [
|
||||
grammar_file,
|
||||
"grammars/",
|
||||
"user_data/grammars/",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
|
|
|||
|
|
@ -223,9 +223,9 @@ def download_model_wrapper(repo_id, specific_file, progress=gr.Progress(), retur
|
|||
model_dir=shared.args.model_dir if shared.args.model_dir != shared.args_defaults.model_dir else None
|
||||
)
|
||||
|
||||
if output_folder == Path("models"):
|
||||
if output_folder == Path("user_data/models"):
|
||||
output_folder = Path(shared.args.model_dir)
|
||||
elif output_folder == Path("loras"):
|
||||
elif output_folder == Path("user_data/loras"):
|
||||
output_folder = Path(shared.args.lora_dir)
|
||||
|
||||
if check:
|
||||
|
|
|
|||
|
|
@ -128,7 +128,7 @@ def get_truncation_length():
|
|||
|
||||
|
||||
def load_grammar(name):
|
||||
p = Path(f'grammars/{name}')
|
||||
p = Path(f'user_data/grammars/{name}')
|
||||
if p.exists():
|
||||
return open(p, 'r', encoding='utf-8').read()
|
||||
else:
|
||||
|
|
|
|||
|
|
@ -48,7 +48,7 @@ def handle_save_settings(state, preset, extensions, show_controls, theme):
|
|||
return [
|
||||
contents,
|
||||
"settings.yaml",
|
||||
"./",
|
||||
"./user_data",
|
||||
gr.update(visible=True)
|
||||
]
|
||||
|
||||
|
|
|
|||
|
|
@ -98,7 +98,7 @@ def get_available_models():
|
|||
dirs_with_gguf = set()
|
||||
for gguf_path in gguf_files:
|
||||
path = Path(gguf_path)
|
||||
if path.parts:
|
||||
if len(path.parts) > 0:
|
||||
dirs_with_gguf.add(path.parts[0])
|
||||
|
||||
# Find directories with safetensors files
|
||||
|
|
@ -141,11 +141,11 @@ def get_available_ggufs():
|
|||
|
||||
|
||||
def get_available_presets():
|
||||
return sorted(set((k.stem for k in Path('presets').glob('*.yaml'))), key=natural_keys)
|
||||
return sorted(set((k.stem for k in Path('user_data/presets').glob('*.yaml'))), key=natural_keys)
|
||||
|
||||
|
||||
def get_available_prompts():
|
||||
prompt_files = list(Path('prompts').glob('*.txt'))
|
||||
prompt_files = list(Path('user_data/prompts').glob('*.txt'))
|
||||
sorted_files = sorted(prompt_files, key=lambda x: x.stat().st_mtime, reverse=True)
|
||||
prompts = [file.stem for file in sorted_files]
|
||||
prompts.append('None')
|
||||
|
|
@ -153,12 +153,12 @@ def get_available_prompts():
|
|||
|
||||
|
||||
def get_available_characters():
|
||||
paths = (x for x in Path('characters').iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
|
||||
paths = (x for x in Path('user_data/characters').iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
|
||||
return sorted(set((k.stem for k in paths)), key=natural_keys)
|
||||
|
||||
|
||||
def get_available_instruction_templates():
|
||||
path = "instruction-templates"
|
||||
path = "user_data/instruction-templates"
|
||||
paths = []
|
||||
if os.path.exists(path):
|
||||
paths = (x for x in Path(path).iterdir() if x.suffix in ('.json', '.yaml', '.yml'))
|
||||
|
|
@ -189,4 +189,4 @@ def get_available_chat_styles():
|
|||
|
||||
|
||||
def get_available_grammars():
|
||||
return ['None'] + sorted([item.name for item in list(Path('grammars').glob('*.gbnf'))], key=natural_keys)
|
||||
return ['None'] + sorted([item.name for item in list(Path('user_data/grammars').glob('*.gbnf'))], key=natural_keys)
|
||||
|
|
|
|||
|
|
@ -293,10 +293,10 @@ def install_webui():
|
|||
|
||||
# Write a flag to CMD_FLAGS.txt for CPU mode
|
||||
if selected_gpu == "NONE":
|
||||
cmd_flags_path = os.path.join(script_dir, "CMD_FLAGS.txt")
|
||||
cmd_flags_path = os.path.join(script_dir, "user_data", "CMD_FLAGS.txt")
|
||||
with open(cmd_flags_path, 'r+') as cmd_flags_file:
|
||||
if "--cpu" not in cmd_flags_file.read():
|
||||
print_big_message("Adding the --cpu flag to CMD_FLAGS.txt.")
|
||||
print_big_message("Adding the --cpu flag to user_data/CMD_FLAGS.txt.")
|
||||
cmd_flags_file.write("\n--cpu\n")
|
||||
|
||||
# Handle CUDA version display
|
||||
|
|
@ -532,7 +532,7 @@ if __name__ == "__main__":
|
|||
flags_list = re.split(' +(?=(?:[^\"]*\"[^\"]*\")*[^\"]*$)|=', flags)
|
||||
model_dir = [flags_list[(flags_list.index(flag) + 1)] for flag in flags_list if flag == '--model-dir'][0].strip('"\'')
|
||||
else:
|
||||
model_dir = 'models'
|
||||
model_dir = 'user_data/models'
|
||||
|
||||
if len([item for item in glob.glob(f'{model_dir}/*') if not item.endswith(('.txt', '.yaml'))]) == 0:
|
||||
print_big_message("You haven't downloaded any model yet.\nOnce the web UI launches, head over to the \"Model\" tab and download one.")
|
||||
|
|
|
|||
18
server.py
18
server.py
|
|
@ -94,8 +94,8 @@ def create_interface():
|
|||
'filter_by_loader': shared.args.loader or 'All'
|
||||
})
|
||||
|
||||
if Path("cache/pfp_character.png").exists():
|
||||
Path("cache/pfp_character.png").unlink()
|
||||
if Path("user_data/cache/pfp_character.png").exists():
|
||||
Path("user_data/cache/pfp_character.png").unlink()
|
||||
|
||||
# css/js strings
|
||||
css = ui.css
|
||||
|
|
@ -112,8 +112,8 @@ def create_interface():
|
|||
shared.gradio['interface_state'] = gr.State({k: None for k in shared.input_elements})
|
||||
|
||||
# Audio notification
|
||||
if Path("notification.mp3").exists():
|
||||
shared.gradio['audio_notification'] = gr.Audio(interactive=False, value="notification.mp3", elem_id="audio_notification", visible=False)
|
||||
if Path("user_data/notification.mp3").exists():
|
||||
shared.gradio['audio_notification'] = gr.Audio(interactive=False, value="user_data/notification.mp3", elem_id="audio_notification", visible=False)
|
||||
|
||||
# Floating menus for saving/deleting files
|
||||
ui_file_saving.create_ui()
|
||||
|
|
@ -179,7 +179,7 @@ def create_interface():
|
|||
ssl_keyfile=shared.args.ssl_keyfile,
|
||||
ssl_certfile=shared.args.ssl_certfile,
|
||||
root_path=shared.args.subpath,
|
||||
allowed_paths=["cache", "css", "extensions", "js"]
|
||||
allowed_paths=["css", "js", "extensions", "user_data/cache"]
|
||||
)
|
||||
|
||||
|
||||
|
|
@ -192,10 +192,10 @@ if __name__ == "__main__":
|
|||
settings_file = None
|
||||
if shared.args.settings is not None and Path(shared.args.settings).exists():
|
||||
settings_file = Path(shared.args.settings)
|
||||
elif Path('settings.yaml').exists():
|
||||
settings_file = Path('settings.yaml')
|
||||
elif Path('settings.json').exists():
|
||||
settings_file = Path('settings.json')
|
||||
elif Path('user_data/settings.yaml').exists():
|
||||
settings_file = Path('user_data/settings.yaml')
|
||||
elif Path('user_data/settings.json').exists():
|
||||
settings_file = Path('user_data/settings.json')
|
||||
|
||||
if settings_file is not None:
|
||||
logger.info(f"Loading settings from \"{settings_file}\"")
|
||||
|
|
|
|||
|
Before Width: | Height: | Size: 206 KiB After Width: | Height: | Size: 206 KiB |
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Reference in a new issue