Mirrors/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2025-01-07 03:14:06 +01:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6623 from oobabooga/dev

Browse Source 
Merge dev branch
This commit is contained in:
oobabooga 2024-12-31 20:47:48 -03:00 committed by GitHub
commit 88a6331abf
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
27 changed files with 262 additions and 222 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
css/html_instruct_style.css
View File

@ -17,36 +17,22 @@
line-height: 28px !important;
}
.dark .chat .message-body p,
.dark .chat .message-body li,
.dark .chat .message-body q {
.dark .chat .message-body :is(p, li, q, h1, h2, h3, h4, h5, h6) {
color: #d1d5db !important;
}
.chat .message-body p,
.chat .message-body ul,
.chat .message-body ol {
margin-top: 1.25em !important;
margin-bottom: 1.25em !important;
.chat .message-body :is(p, ul, ol) {
margin: 1.25em 0 !important;
}
.chat .message-body p:first-child,
.chat .message-body ul:first-child,
.chat .message-body ol:first-child {
.chat .message-body :is(p, ul, ol):first-child {
margin-top: 0 !important;
}
.chat .message-body p:last-child,
.chat .message-body ul:last-child,
.chat .message-body ol:last-child {
.chat .message-body :is(p, ul, ol):last-child {
margin-bottom: 0 !important;
}
.chat .message-body li {
margin-top: 1.25em !important;
margin-bottom: 1.25em !important;
}
.user-message, .assistant-message {
font-family: Inter, Helvetica, Arial, sans-serif;
}
@ -60,13 +46,13 @@
}
.chat .user-message {
background: #f4f4f4;
padding: 1.5rem 1rem;
border-radius: 0;
border-bottom-right-radius: 0;
}
.chat .assistant-message {
background: #f4f4f4;
padding: 1.5rem 1rem;
border-radius: 0;
border: 0;
@ -82,7 +68,7 @@
.chat .user-message .text,
.chat .assistant-message .text {
max-width: 40.25rem;
max-width: 645px;
margin-left: auto;
margin-right: auto;
}

86
css/main.css
View File

@ -38,7 +38,7 @@ div.svelte-iyf88w {
/* "info" messages without a title above */
.block > .svelte-e8n7p6:not(:only-of-type, #chat-mode *) {
margin-bottom: 2px;
margin-bottom: 0;
}
.py-6 {
@ -433,12 +433,56 @@ div.svelte-362y77>*, div.svelte-362y77>.form>* {
padding-top: 20px;
}
.message-body h1,
.message-body h2,
.message-body h3,
.message-body {
font-size: 16px;
}
.dark .message-body :is(h1, h2, h3, h4, h5, h6) {
color: white !important;
}
.message-body h1 {
font-weight: 800;
font-size: 2.25em;
margin-top: 0;
margin-bottom: 0.8888889em;
line-height: 1.1111111;
}
.message-body h2 {
font-weight: 700;
font-size: 1.5em;
margin-top: 2em;
margin-bottom: 1em;
line-height: 1.3333333;
}
.message-body h3 {
font-weight: 600;
font-size: 1.25em;
margin-top: 1.6em;
margin-bottom: 0.6em;
line-height: 1.6;
}
.message-body h4 {
color: var(--body-text-color);
margin: 20px 0 10px;
font-weight: 600;
font-size: 1em;
margin-top: 1.5em;
margin-bottom: 0.5em;
line-height: 1.5;
}
.message-body h5 {
font-weight: normal;
font-size: 1em;
margin: 0;
}
.message-body h6 {
font-weight: normal;
font-size: 1em;
margin: 0;
}
.dark .message q {
@ -451,29 +495,28 @@ div.svelte-362y77>*, div.svelte-362y77>.form>* {
.message-body li {
list-style-position: outside;
margin-top: 0.5em !important;
margin-bottom: 0.5em !important;
}
.message-body ul.long-list li,
.message-body ol.long-list li {
margin-top: 1.25em !important;
margin-bottom: 1.25em !important;
}
.message-body a {
font-weight: 500;
}
.chat .message-body ul, .chat .message-body ol {
padding-inline-start: 2em;
}
.chat .message-body li:not(:last-child) {
margin-top: 0;
margin-bottom: 2px;
}
.chat .message-body li:last-child {
margin-bottom: 0 !important;
}
.message-body li > p {
display: inline !important;
}
.message-body ul, .message-body ol {
font-size: 15px !important;
}
.message-body ul {
list-style-type: disc !important;
}
@ -786,8 +829,9 @@ div.svelte-362y77>*, div.svelte-362y77>.form>* {
padding-bottom: 80px !important;
}
.chat ol, .chat ul {
margin-top: 6px !important;
.message-body ol, .message-body ul {
margin-top: 0 !important;
margin-bottom: 1.25em !important;
}
/* ----------------------------------------------

8
modules/chat.py
View File

@ -353,14 +353,14 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
# Extract the reply
if state['mode'] in ['chat', 'chat-instruct']:
visible_reply = re.sub("(<USER>|<user>|{{user}})", state['name1'], reply + '❚')
visible_reply = re.sub("(<USER>|<user>|{{user}})", state['name1'], reply + '▍')
else:
visible_reply = reply + '❚'
visible_reply = reply + '▍'
visible_reply = html.escape(visible_reply)
if shared.stop_everything:
if output['visible'][-1][1].endswith('❚'):
if output['visible'][-1][1].endswith('▍'):
output['visible'][-1][1] = output['visible'][-1][1][:-1]
output['visible'][-1][1] = apply_extensions('output', output['visible'][-1][1], state, is_chat=True)
@ -378,7 +378,7 @@ def chatbot_wrapper(text, state, regenerate=False, _continue=False, loading_mess
if is_stream:
yield output
if output['visible'][-1][1].endswith('❚'):
if output['visible'][-1][1].endswith('▍'):
output['visible'][-1][1] = output['visible'][-1][1][:-1]
output['visible'][-1][1] = apply_extensions('output', output['visible'][-1][1], state, is_chat=True)

76
modules/html_generator.py
View File

@ -69,6 +69,52 @@ def replace_blockquote(m):
return m.group().replace('\n', '\n> ').replace('\\begin{blockquote}', '').replace('\\end{blockquote}', '')
def add_long_list_class(html):
'''
Adds a long-list class to <ul> or <ol> containing long <li> items.
These will receive a smaller margin/padding in the CSS.
'''
# Helper function to check if a tag is within <pre> or <code>
def is_within_block(start_idx, end_idx, block_matches):
return any(start < start_idx < end or start < end_idx < end for start, end in block_matches)
# Find all <pre>...</pre> and <code>...</code> blocks
pre_blocks = [(m.start(), m.end()) for m in re.finditer(r'<pre.*?>.*?</pre>', html, re.DOTALL)]
code_blocks = [(m.start(), m.end()) for m in re.finditer(r'<code.*?>.*?</code>', html, re.DOTALL)]
all_blocks = pre_blocks + code_blocks
# Pattern to find <ul>...</ul> and <ol>...</ol> blocks and their contents
list_pattern = re.compile(r'(<[uo]l.*?>)(.*?)(</[uo]l>)', re.DOTALL)
li_pattern = re.compile(r'<li.*?>(.*?)</li>', re.DOTALL)
def process_list(match):
start_idx, end_idx = match.span()
if is_within_block(start_idx, end_idx, all_blocks):
return match.group(0) # Leave the block unchanged if within <pre> or <code>
opening_tag = match.group(1)
list_content = match.group(2)
closing_tag = match.group(3)
# Find all list items within this list
li_matches = li_pattern.finditer(list_content)
has_long_item = any(len(li_match.group(1).strip()) > 224 for li_match in li_matches)
if has_long_item:
# Add class="long-list" to the opening tag if it doesn't already have a class
if 'class=' not in opening_tag:
opening_tag = opening_tag[:-1] + ' class="long-list">'
else:
# If there's already a class, append long-list to it
opening_tag = re.sub(r'class="([^"]*)"', r'class="\1 long-list"', opening_tag)
return opening_tag + list_content + closing_tag
# Process HTML and replace list blocks
return list_pattern.sub(process_list, html)
@functools.lru_cache(maxsize=None)
def convert_to_markdown(string):
@ -104,7 +150,6 @@ def convert_to_markdown(string):
result = ''
is_code = False
is_latex = False
previous_line_empty = True
for line in string.split('\n'):
stripped_line = line.strip()
@ -122,20 +167,16 @@ def convert_to_markdown(string):
elif stripped_line.endswith('\\\\]'):
is_latex = False
# Preserve indentation for lists and code blocks
if stripped_line.startswith('-') or stripped_line.startswith('*') or stripped_line.startswith('+') or stripped_line.startswith('>') or re.match(r'\d+\.', stripped_line):
result += line + '\n'
previous_line_empty = False
elif is_code or is_latex or line.startswith('|'):
result += line + '\n'
previous_line_empty = False
else:
if previous_line_empty:
result += line.strip() + '\n'
else:
result += line.strip() + '\n\n'
result += line
previous_line_empty = stripped_line == ''
# Don't add an extra \n for code, LaTeX, or tables
if is_code or is_latex or line.startswith('|'):
result += '\n'
# Also don't add an extra \n for lists
elif stripped_line.startswith('-') or stripped_line.startswith('*') or stripped_line.startswith('+') or stripped_line.startswith('>') or re.match(r'\d+\.', stripped_line):
result += '\n'
else:
result += ' \n'
result = result.strip()
if is_code:
@ -154,7 +195,7 @@ def convert_to_markdown(string):
result = re.sub(list_item_pattern, r'\g<1> ' + delete_str, result)
# Convert to HTML using markdown
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'], tab_length=2)
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'])
# Remove the delete string from the HTML output
pos = html_output.rfind(delete_str)
@ -162,12 +203,15 @@ def convert_to_markdown(string):
html_output = html_output[:pos] + html_output[pos + len(delete_str):]
else:
# Convert to HTML using markdown
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'], tab_length=2)
html_output = markdown.markdown(result, extensions=['fenced_code', 'tables'])
# Unescape code blocks
pattern = re.compile(r'<code[^>]*>(.*?)</code>', re.DOTALL)
html_output = pattern.sub(lambda x: html.unescape(x.group()), html_output)
# Add "long-list" class to <ul> or <ol> containing a long <li> item
html_output = add_long_list_class(html_output)
return html_output

1
modules/loaders.py
View File

@ -26,7 +26,6 @@ loaders_and_params = OrderedDict({
'compress_pos_emb',
'disable_exllama',
'disable_exllamav2',
'transformers_info',
],
'llama.cpp': [
'n_ctx',

71
modules/ui_model_menu.py
View File

@ -80,59 +80,52 @@ def create_ui():
with gr.Blocks():
with gr.Row():
with gr.Column():
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])
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['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, info='Must be set to more than 0 for your GPU to be used.')
shared.gradio['n_ctx'] = gr.Number(label="n_ctx", precision=0, step=256, 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: 60,40')
shared.gradio['n_batch'] = gr.Slider(label="n_batch", minimum=1, maximum=2048, step=1, value=shared.args.n_batch)
shared.gradio['cpu_memory'] = gr.Slider(label="cpu-memory in MiB", maximum=total_cpu_mem, value=default_cpu_mem)
shared.gradio['n_gpu_layers'] = gr.Slider(label="n-gpu-layers", minimum=0, maximum=256, value=shared.args.n_gpu_layers, info='Must be greater than 0 for the GPU to be used. ⚠️ Lower this value if you can\'t load the model.')
shared.gradio['threads'] = gr.Slider(label="threads", minimum=0, step=1, maximum=256, value=shared.args.threads)
shared.gradio['threads_batch'] = gr.Slider(label="threads_batch", minimum=0, step=1, maximum=256, 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['hqq_backend'] = gr.Dropdown(label="hqq_backend", choices=["PYTORCH", "PYTORCH_COMPILE", "ATEN"], value=shared.args.hqq_backend)
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['n_ctx'] = gr.Number(label="n_ctx", precision=0, step=256, value=shared.args.n_ctx, info='Context length. ⚠️ Lower this value if you can\'t load the model.')
shared.gradio['max_seq_len'] = gr.Number(label='max_seq_len', precision=0, step=256, value=shared.args.max_seq_len, info='Context length. ⚠️ Lower this value if you can\'t load the model.')
shared.gradio['cache_type'] = gr.Dropdown(label="cache_type", choices=['fp16', 'q8_0', 'q4_0', 'fp8', 'q8', 'q6', 'q4'], value=shared.args.cache_type, info='Valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4.')
shared.gradio['tensor_split'] = gr.Textbox(label='tensor_split', info='List of proportions to split the model across multiple GPUs. Example: 60,40')
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.Number(label='max_seq_len', precision=0, step=256, value=shared.args.max_seq_len, info='Context length. Try lowering this if you run out of memory while loading the model.')
with gr.Blocks():
shared.gradio['alpha_value'] = gr.Number(label='alpha_value', value=shared.args.alpha_value, precision=2, 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.')
shared.gradio['rope_freq_base'] = gr.Number(label='rope_freq_base', value=shared.args.rope_freq_base, precision=0, info='Positional embeddings frequency base for NTK RoPE scaling. Related to alpha_value by rope_freq_base = 10000 * alpha_value ^ (64 / 63). 0 = from model.')
shared.gradio['compress_pos_emb'] = gr.Number(label='compress_pos_emb', value=shared.args.compress_pos_emb, precision=2, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.')
shared.gradio['autogptq_info'] = gr.Markdown('ExLlamav2_HF is recommended over AutoGPTQ for models derived from Llama.')
shared.gradio['alpha_value'] = gr.Number(label='alpha_value', value=shared.args.alpha_value, precision=2, 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.')
shared.gradio['rope_freq_base'] = gr.Number(label='rope_freq_base', value=shared.args.rope_freq_base, precision=0, info='Positional embeddings frequency base for NTK RoPE scaling. Related to alpha_value by rope_freq_base = 10000 * alpha_value ^ (64 / 63). 0 = from model.')
shared.gradio['compress_pos_emb'] = gr.Number(label='compress_pos_emb', value=shared.args.compress_pos_emb, precision=2, info='Positional embeddings compression factor. Should be set to (context length) / (model\'s original context length). Equal to 1/rope_freq_scale.')
shared.gradio['compute_dtype'] = gr.Dropdown(label="compute_dtype", choices=["bfloat16", "float16", "float32"], value=shared.args.compute_dtype, info='Used by load-in-4bit.')
shared.gradio['quant_type'] = gr.Dropdown(label="quant_type", choices=["nf4", "fp4"], value=shared.args.quant_type, info='Used by load-in-4bit.')
shared.gradio['attention_sink_size'] = gr.Number(label="attention_sink_size", value=shared.args.attention_sink_size, precision=0, info='StreamingLLM: number of sink tokens. Only used if the trimmed prompt doesn\'t share a prefix with the old prompt.')
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.')
with gr.Column():
shared.gradio['tensorcores'] = gr.Checkbox(label="tensorcores", value=shared.args.tensorcores, info='NVIDIA only: use llama-cpp-python compiled with tensor cores support. This may increase performance on newer cards.')
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['use_eager_attention'] = gr.Checkbox(label="use_eager_attention", value=shared.args.use_eager_attention, info='Set attn_implementation= eager while loading the model.')
shared.gradio['flash_attn'] = gr.Checkbox(label="flash_attn", value=shared.args.flash_attn, info='Use flash-attention.')
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 may increase performance on newer cards.')
shared.gradio['cache_type'] = gr.Dropdown(label="cache_type", choices=['fp16', 'q8_0', 'q4_0', 'fp8', 'q8', 'q6', 'q4'], value=shared.args.cache_type, info='Valid options: llama.cpp - fp16, q8_0, q4_0; ExLlamaV2 - fp16, fp8, q8, q6, q4.')
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['streaming_llm'] = gr.Checkbox(label="streaming_llm", value=shared.args.streaming_llm, info='(experimental) Activate StreamingLLM to avoid re-evaluating the entire prompt when old messages are removed.')
shared.gradio['attention_sink_size'] = gr.Number(label="attention_sink_size", value=shared.args.attention_sink_size, precision=0, info='StreamingLLM: number of sink tokens. Only used if the trimmed prompt doesn\'t share a prefix with the old prompt.')
shared.gradio['auto_devices'] = gr.Checkbox(label="auto-devices", value=shared.args.auto_devices)
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['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
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['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['triton'] = gr.Checkbox(label="triton", value=shared.args.triton)
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_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['disk'] = gr.Checkbox(label="disk", value=shared.args.disk)
shared.gradio['use_double_quant'] = gr.Checkbox(label="use_double_quant", value=shared.args.use_double_quant, info='Used by load-in-4bit.')
shared.gradio['use_eager_attention'] = gr.Checkbox(label="use_eager_attention", value=shared.args.use_eager_attention, info='Set attn_implementation= eager while loading the model.')
shared.gradio['bf16'] = gr.Checkbox(label="bf16", value=shared.args.bf16)
shared.gradio['autosplit'] = gr.Checkbox(label="autosplit", value=shared.args.autosplit, info='Automatically split the model tensors across the available GPUs.')
shared.gradio['enable_tp'] = gr.Checkbox(label="enable_tp", value=shared.args.enable_tp, info='Enable Tensor Parallelism (TP).')
@ -141,16 +134,14 @@ def create_ui():
shared.gradio['no_sdpa'] = gr.Checkbox(label="no_sdpa", value=shared.args.no_sdpa)
shared.gradio['cfg_cache'] = gr.Checkbox(label="cfg-cache", value=shared.args.cfg_cache, info='Necessary to use CFG with this loader.')
shared.gradio['cpp_runner'] = gr.Checkbox(label="cpp-runner", value=shared.args.cpp_runner, info='Enable inference with ModelRunnerCpp, which is faster than the default ModelRunner.')
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.')
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['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['exllamav2_info'] = gr.Markdown("ExLlamav2_HF is recommended over ExLlamav2 for better integration with extensions and more consistent sampling behavior across loaders.")
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['llamacpp_HF_info'] = gr.Markdown("llamacpp_HF loads llama.cpp as a Transformers model. To use it, you need to place your GGUF in a subfolder of models/ with the necessary tokenizer files.\n\nYou can use the \"llamacpp_HF creator\" menu to do that automatically.")
shared.gradio['exllamav2_info'] = gr.Markdown("ExLlamav2_HF is recommended over ExLlamav2 for better integration with extensions and more consistent sampling behavior across loaders.")
shared.gradio['autogptq_info'] = gr.Markdown('ExLlamav2_HF is recommended over AutoGPTQ for models derived from Llama.')
shared.gradio['tensorrt_llm_info'] = gr.Markdown('* TensorRT-LLM has to be installed manually in a separate Python 3.10 environment at the moment. For a guide, consult the description of [this PR](https://github.com/oobabooga/text-generation-webui/pull/5715). \n\n* `max_seq_len` is only used when `cpp-runner` is checked.\n\n* `cpp_runner` does not support streaming at the moment.')
with gr.Column():

124
modules/ui_parameters.py
View File

@ -27,80 +27,80 @@ def create_ui(default_preset):
with gr.Column():
with gr.Row():
with gr.Column():
shared.gradio['max_new_tokens'] = gr.Slider(minimum=shared.settings['max_new_tokens_min'], maximum=shared.settings['max_new_tokens_max'], step=1, label='max_new_tokens', value=shared.settings['max_new_tokens'])
gr.Markdown('## Curve shape')
shared.gradio['temperature'] = gr.Slider(0.01, 5, value=generate_params['temperature'], step=0.01, label='temperature')
shared.gradio['top_p'] = gr.Slider(0.0, 1.0, value=generate_params['top_p'], step=0.01, label='top_p')
shared.gradio['top_k'] = gr.Slider(0, 200, value=generate_params['top_k'], step=1, label='top_k')
shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=generate_params['typical_p'], step=0.01, label='typical_p')
shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=generate_params['min_p'], step=0.01, label='min_p')
shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty')
shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=generate_params['frequency_penalty'], step=0.05, label='frequency_penalty')
shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty')
shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range')
shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample')
with gr.Blocks():
shared.gradio['dry_multiplier'] = gr.Slider(0, 5, value=generate_params['dry_multiplier'], step=0.01, label='dry_multiplier', info='Set to greater than 0 to enable DRY. Recommended value: 0.8.')
shared.gradio['dry_allowed_length'] = gr.Slider(1, 20, value=generate_params['dry_allowed_length'], step=1, label='dry_allowed_length', info='Longest sequence that can be repeated without being penalized.')
shared.gradio['dry_base'] = gr.Slider(1, 4, value=generate_params['dry_base'], step=0.01, label='dry_base', info='Controls how fast the penalty grows with increasing sequence length.')
shared.gradio['dry_sequence_breakers'] = gr.Textbox(value=generate_params['dry_sequence_breakers'], label='dry_sequence_breakers', info='Tokens across which sequence matching is not continued. Specified as a comma-separated list of quoted strings.')
with gr.Blocks():
shared.gradio['xtc_threshold'] = gr.Slider(0, 0.5, value=generate_params['xtc_threshold'], step=0.01, label='xtc_threshold', info='If 2 or more tokens have probability above this threshold, consider removing all but the last one.')
shared.gradio['xtc_probability'] = gr.Slider(0, 1, value=generate_params['xtc_probability'], step=0.01, label='xtc_probability', info='Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.')
gr.Markdown("[Learn more](https://github.com/oobabooga/text-generation-webui/wiki/03-%E2%80%90-Parameters-Tab)")
with gr.Column():
with gr.Group():
shared.gradio['auto_max_new_tokens'] = gr.Checkbox(value=shared.settings['auto_max_new_tokens'], label='auto_max_new_tokens', info='Expand max_new_tokens to the available context length.')
shared.gradio['ban_eos_token'] = gr.Checkbox(value=shared.settings['ban_eos_token'], label='Ban the eos_token', info='Forces the model to never end the generation prematurely.')
shared.gradio['add_bos_token'] = gr.Checkbox(value=shared.settings['add_bos_token'], label='Add the bos_token to the beginning of prompts', info='Disabling this can make the replies more creative.')
shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=2, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='Written between "" and separated by commas.', placeholder='"\\n", "\\nYou:"')
shared.gradio['custom_token_bans'] = gr.Textbox(value=shared.settings['custom_token_bans'] or None, label='Token bans', info='Token IDs to ban, separated by commas. The IDs can be found in the Default or Notebook tab.')
shared.gradio['penalty_alpha'] = gr.Slider(0, 5, value=generate_params['penalty_alpha'], label='penalty_alpha', info='For Contrastive Search. do_sample must be unchecked.')
shared.gradio['guidance_scale'] = gr.Slider(-0.5, 2.5, step=0.05, value=generate_params['guidance_scale'], label='guidance_scale', info='For CFG. 1.5 is a good value.')
shared.gradio['negative_prompt'] = gr.Textbox(value=shared.settings['negative_prompt'], label='Negative prompt', lines=3, elem_classes=['add_scrollbar'])
shared.gradio['mirostat_mode'] = gr.Slider(0, 2, step=1, value=generate_params['mirostat_mode'], label='mirostat_mode', info='mode=1 is for llama.cpp only.')
shared.gradio['mirostat_tau'] = gr.Slider(0, 10, step=0.01, value=generate_params['mirostat_tau'], label='mirostat_tau')
shared.gradio['mirostat_eta'] = gr.Slider(0, 1, step=0.01, value=generate_params['mirostat_eta'], label='mirostat_eta')
shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=generate_params['epsilon_cutoff'], step=0.01, label='epsilon_cutoff')
shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=generate_params['eta_cutoff'], step=0.01, label='eta_cutoff')
shared.gradio['encoder_repetition_penalty'] = gr.Slider(0.8, 1.5, value=generate_params['encoder_repetition_penalty'], step=0.01, label='encoder_repetition_penalty')
shared.gradio['no_repeat_ngram_size'] = gr.Slider(0, 20, step=1, value=generate_params['no_repeat_ngram_size'], label='no_repeat_ngram_size')
with gr.Column():
with gr.Row() as shared.gradio['grammar_file_row']:
shared.gradio['grammar_file'] = gr.Dropdown(value='None', choices=utils.get_available_grammars(), label='Load grammar from file (.gbnf)', elem_classes='slim-dropdown')
ui.create_refresh_button(shared.gradio['grammar_file'], lambda: None, lambda: {'choices': utils.get_available_grammars()}, 'refresh-button', interactive=not mu)
shared.gradio['save_grammar'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu)
shared.gradio['delete_grammar'] = gr.Button('🗑️ ', elem_classes='refresh-button', interactive=not mu)
shared.gradio['grammar_string'] = gr.Textbox(value='', label='Grammar', lines=16, elem_classes=['add_scrollbar', 'monospace'])
with gr.Row():
with gr.Column():
shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=generate_params['tfs'], step=0.01, label='tfs')
shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=generate_params['top_a'], step=0.01, label='top_a')
shared.gradio['smoothing_factor'] = gr.Slider(0.0, 10.0, value=generate_params['smoothing_factor'], step=0.01, label='smoothing_factor', info='Activates Quadratic Sampling.')
shared.gradio['smoothing_curve'] = gr.Slider(1.0, 10.0, value=generate_params['smoothing_curve'], step=0.01, label='smoothing_curve', info='Adjusts the dropoff curve of Quadratic Sampling.')
shared.gradio['dynamic_temperature'] = gr.Checkbox(value=generate_params['dynamic_temperature'], label='dynamic_temperature')
shared.gradio['dynatemp_low'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_low'], step=0.01, label='dynatemp_low', visible=generate_params['dynamic_temperature'])
shared.gradio['dynatemp_high'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_high'], step=0.01, label='dynatemp_high', visible=generate_params['dynamic_temperature'])
shared.gradio['dynatemp_exponent'] = gr.Slider(0.01, 5, value=generate_params['dynatemp_exponent'], step=0.01, label='dynatemp_exponent', visible=generate_params['dynamic_temperature'])
shared.gradio['temperature_last'] = gr.Checkbox(value=generate_params['temperature_last'], label='temperature_last', info='Moves temperature/dynamic temperature/quadratic sampling to the end of the sampler stack, ignoring their positions in "Sampler priority".')
shared.gradio['sampler_priority'] = gr.Textbox(value=generate_params['sampler_priority'], lines=12, label='Sampler priority', info='Parameter names separated by new lines or commas.')
shared.gradio['smoothing_factor'] = gr.Slider(0.0, 10.0, value=generate_params['smoothing_factor'], step=0.01, label='smoothing_factor', info='Activates Quadratic Sampling.')
shared.gradio['smoothing_curve'] = gr.Slider(1.0, 10.0, value=generate_params['smoothing_curve'], step=0.01, label='smoothing_curve', info='Adjusts the dropoff curve of Quadratic Sampling.')
gr.Markdown('## Curve cutoff')
shared.gradio['min_p'] = gr.Slider(0.0, 1.0, value=generate_params['min_p'], step=0.01, label='min_p')
shared.gradio['top_p'] = gr.Slider(0.0, 1.0, value=generate_params['top_p'], step=0.01, label='top_p')
shared.gradio['top_k'] = gr.Slider(0, 200, value=generate_params['top_k'], step=1, label='top_k')
shared.gradio['typical_p'] = gr.Slider(0.0, 1.0, value=generate_params['typical_p'], step=0.01, label='typical_p')
shared.gradio['xtc_threshold'] = gr.Slider(0, 0.5, value=generate_params['xtc_threshold'], step=0.01, label='xtc_threshold', info='If 2 or more tokens have probability above this threshold, consider removing all but the last one.')
shared.gradio['xtc_probability'] = gr.Slider(0, 1, value=generate_params['xtc_probability'], step=0.01, label='xtc_probability', info='Probability that the removal will actually happen. 0 disables the sampler. 1 makes it always happen.')
shared.gradio['epsilon_cutoff'] = gr.Slider(0, 9, value=generate_params['epsilon_cutoff'], step=0.01, label='epsilon_cutoff')
shared.gradio['eta_cutoff'] = gr.Slider(0, 20, value=generate_params['eta_cutoff'], step=0.01, label='eta_cutoff')
shared.gradio['tfs'] = gr.Slider(0.0, 1.0, value=generate_params['tfs'], step=0.01, label='tfs')
shared.gradio['top_a'] = gr.Slider(0.0, 1.0, value=generate_params['top_a'], step=0.01, label='top_a')
gr.Markdown('## Repetition suppression')
shared.gradio['dry_multiplier'] = gr.Slider(0, 5, value=generate_params['dry_multiplier'], step=0.01, label='dry_multiplier', info='Set to greater than 0 to enable DRY. Recommended value: 0.8.')
shared.gradio['dry_allowed_length'] = gr.Slider(1, 20, value=generate_params['dry_allowed_length'], step=1, label='dry_allowed_length', info='Longest sequence that can be repeated without being penalized.')
shared.gradio['dry_base'] = gr.Slider(1, 4, value=generate_params['dry_base'], step=0.01, label='dry_base', info='Controls how fast the penalty grows with increasing sequence length.')
shared.gradio['repetition_penalty'] = gr.Slider(1.0, 1.5, value=generate_params['repetition_penalty'], step=0.01, label='repetition_penalty')
shared.gradio['frequency_penalty'] = gr.Slider(0, 2, value=generate_params['frequency_penalty'], step=0.05, label='frequency_penalty')
shared.gradio['presence_penalty'] = gr.Slider(0, 2, value=generate_params['presence_penalty'], step=0.05, label='presence_penalty')
shared.gradio['encoder_repetition_penalty'] = gr.Slider(0.8, 1.5, value=generate_params['encoder_repetition_penalty'], step=0.01, label='encoder_repetition_penalty')
shared.gradio['no_repeat_ngram_size'] = gr.Slider(0, 20, step=1, value=generate_params['no_repeat_ngram_size'], label='no_repeat_ngram_size')
shared.gradio['repetition_penalty_range'] = gr.Slider(0, 4096, step=64, value=generate_params['repetition_penalty_range'], label='repetition_penalty_range')
with gr.Column():
shared.gradio['truncation_length'] = gr.Number(precision=0, step=256, value=get_truncation_length(), label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
gr.Markdown('## Alternative sampling methods')
shared.gradio['penalty_alpha'] = gr.Slider(0, 5, value=generate_params['penalty_alpha'], label='penalty_alpha', info='For Contrastive Search. do_sample must be unchecked.')
shared.gradio['guidance_scale'] = gr.Slider(-0.5, 2.5, step=0.05, value=generate_params['guidance_scale'], label='guidance_scale', info='For CFG. 1.5 is a good value.')
shared.gradio['mirostat_mode'] = gr.Slider(0, 2, step=1, value=generate_params['mirostat_mode'], label='mirostat_mode', info='mode=1 is for llama.cpp only.')
shared.gradio['mirostat_tau'] = gr.Slider(0, 10, step=0.01, value=generate_params['mirostat_tau'], label='mirostat_tau')
shared.gradio['mirostat_eta'] = gr.Slider(0, 1, step=0.01, value=generate_params['mirostat_eta'], label='mirostat_eta')
gr.Markdown('## Other options')
shared.gradio['max_new_tokens'] = gr.Slider(minimum=shared.settings['max_new_tokens_min'], maximum=shared.settings['max_new_tokens_max'], value=shared.settings['max_new_tokens'], step=1, label='max_new_tokens', info='⚠️ Setting this too high can cause prompt truncation.')
shared.gradio['prompt_lookup_num_tokens'] = gr.Slider(value=shared.settings['prompt_lookup_num_tokens'], minimum=0, maximum=10, step=1, label='prompt_lookup_num_tokens', info='Activates Prompt Lookup Decoding.')
shared.gradio['max_tokens_second'] = gr.Slider(value=shared.settings['max_tokens_second'], minimum=0, maximum=20, step=1, label='Maximum tokens/second', info='To make text readable in real time.')
shared.gradio['max_updates_second'] = gr.Slider(value=shared.settings['max_updates_second'], minimum=0, maximum=24, step=1, label='Maximum UI updates/second', info='Set this if you experience lag in the UI during streaming.')
shared.gradio['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)')
with gr.Column():
with gr.Row():
with gr.Column():
shared.gradio['do_sample'] = gr.Checkbox(value=generate_params['do_sample'], label='do_sample')
shared.gradio['dynamic_temperature'] = gr.Checkbox(value=generate_params['dynamic_temperature'], label='dynamic_temperature')
shared.gradio['temperature_last'] = gr.Checkbox(value=generate_params['temperature_last'], label='temperature_last', info='Moves temperature/dynamic temperature/quadratic sampling to the end of the sampler stack, ignoring their positions in "Sampler priority".')
shared.gradio['auto_max_new_tokens'] = gr.Checkbox(value=shared.settings['auto_max_new_tokens'], label='auto_max_new_tokens', info='Expand max_new_tokens to the available context length.')
shared.gradio['ban_eos_token'] = gr.Checkbox(value=shared.settings['ban_eos_token'], label='Ban the eos_token', info='Forces the model to never end the generation prematurely.')
shared.gradio['add_bos_token'] = gr.Checkbox(value=shared.settings['add_bos_token'], label='Add the bos_token to the beginning of prompts', info='Disabling this can make the replies more creative.')
shared.gradio['skip_special_tokens'] = gr.Checkbox(value=shared.settings['skip_special_tokens'], label='Skip special tokens', info='Some specific models need this unset.')
shared.gradio['stream'] = gr.Checkbox(value=shared.settings['stream'], label='Activate text streaming')
with gr.Column():
shared.gradio['truncation_length'] = gr.Number(precision=0, step=256, value=get_truncation_length(), label='Truncate the prompt up to this length', info='The leftmost tokens are removed if the prompt exceeds this length. Most models require this to be at most 2048.')
shared.gradio['seed'] = gr.Number(value=shared.settings['seed'], label='Seed (-1 for random)')
shared.gradio['sampler_priority'] = gr.Textbox(value=generate_params['sampler_priority'], lines=12, label='Sampler priority', info='Parameter names separated by new lines or commas.', elem_classes=['add_scrollbar'])
shared.gradio['custom_stopping_strings'] = gr.Textbox(lines=2, value=shared.settings["custom_stopping_strings"] or None, label='Custom stopping strings', info='Written between "" and separated by commas.', placeholder='"\\n", "\\nYou:"')
shared.gradio['custom_token_bans'] = gr.Textbox(value=shared.settings['custom_token_bans'] or None, label='Token bans', info='Token IDs to ban, separated by commas. The IDs can be found in the Default or Notebook tab.')
shared.gradio['negative_prompt'] = gr.Textbox(value=shared.settings['negative_prompt'], label='Negative prompt', info='For CFG. Only used when guidance_scale is different than 1.', lines=3, elem_classes=['add_scrollbar'])
shared.gradio['dry_sequence_breakers'] = gr.Textbox(value=generate_params['dry_sequence_breakers'], label='dry_sequence_breakers', info='Tokens across which sequence matching is not continued. Specified as a comma-separated list of quoted strings.')
with gr.Row() as shared.gradio['grammar_file_row']:
shared.gradio['grammar_file'] = gr.Dropdown(value='None', choices=utils.get_available_grammars(), label='Load grammar from file (.gbnf)', elem_classes='slim-dropdown')
ui.create_refresh_button(shared.gradio['grammar_file'], lambda: None, lambda: {'choices': utils.get_available_grammars()}, 'refresh-button', interactive=not mu)
shared.gradio['save_grammar'] = gr.Button('💾', elem_classes='refresh-button', interactive=not mu)
shared.gradio['delete_grammar'] = gr.Button('🗑️ ', elem_classes='refresh-button', interactive=not mu)
shared.gradio['grammar_string'] = gr.Textbox(value='', label='Grammar', lines=16, elem_classes=['add_scrollbar', 'monospace'])
ui_chat.create_chat_settings_ui()

6
presets/Big O.yaml
View File

@ -1,6 +0,0 @@
temperature: 0.87
top_p: 0.99
typical_p: 0.68
tfs: 0.68
repetition_penalty: 1.01
top_k: 85

2
presets/Creative.yaml Normal file
View File

@ -0,0 +1,2 @@
min_p: 0.02
xtc_probability: 0.5

0
presets/Debug-deterministic.yaml → presets/Deterministic.yaml
View File

4
presets/Divine Intellect.yaml
View File

@ -1,4 +0,0 @@
temperature: 1.31
top_p: 0.14
repetition_penalty: 1.17
top_k: 49

1
presets/Instruct.yaml Normal file
View File

@ -0,0 +1 @@
min_p: 0.2

4
presets/LLaMA-Precise.yaml
View File

@ -1,4 +0,0 @@
temperature: 0.7
top_p: 0.1
repetition_penalty: 1.18
top_k: 40

4
presets/Midnight Enigma.yaml
View File

@ -1,4 +0,0 @@
temperature: 0.98
top_p: 0.37
repetition_penalty: 1.18
top_k: 100

4
presets/Shortwave.yaml
View File

@ -1,4 +0,0 @@
temperature: 1.53
top_p: 0.64
repetition_penalty: 1.07
top_k: 33

4
presets/Yara.yaml
View File

@ -1,4 +0,0 @@
temperature: 0.82
top_p: 0.21
repetition_penalty: 1.19
top_k: 72

4
presets/simple-1.yaml
View File

@ -1,4 +0,0 @@
temperature: 0.7
top_p: 0.9
repetition_penalty: 1.15
top_k: 20

12
requirements.txt
View File

@ -5,7 +5,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -50,11 +50,11 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/te
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.3.5+cu121-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

8
requirements_amd.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -39,6 +39,6 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cp
# AMD wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.3.5+rocm6.1.2-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/rocm/llama_cpp_python_cuda-0.3.5+rocm6.1.2-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+rocm6.1.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+rocm6.1.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+rocm6.1.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+rocm6.1.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

8
requirements_amd_noavx2.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -37,6 +37,6 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cp
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/cpu/llama_cpp_python-0.3.5+cpuavx-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
# AMD wheels
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+rocm6.1.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+rocm6.1.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+rocm6.1.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+rocm6.1.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system != "Darwin" and platform_machine != "x86_64"

4
requirements_apple_intel.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -33,4 +33,4 @@ tiktoken
# Mac wheels
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.3.5-cp311-cp311-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.3.5-cp310-cp310-macosx_14_0_x86_64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl

4
requirements_apple_silicon.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -35,4 +35,4 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/me
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.3.5-cp310-cp310-macosx_13_0_arm64.whl; platform_system == "Darwin" and platform_release >= "22.0.0" and platform_release < "23.0.0" and python_version == "3.10"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.3.5-cp311-cp311-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.11"
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/metal/llama_cpp_python-0.3.5-cp310-cp310-macosx_14_0_arm64.whl; platform_system == "Darwin" and platform_release >= "23.0.0" and platform_release < "24.0.0" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl

2
requirements_cpu_only.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*

2
requirements_cpu_only_noavx2.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*

12
requirements_noavx2.txt
View File

@ -5,7 +5,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*
@ -50,11 +50,11 @@ https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/te
https://github.com/oobabooga/llama-cpp-python-cuBLAS-wheels/releases/download/textgen-webui/llama_cpp_python_cuda_tensorcores-0.3.5+cu121avx-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
# CUDA wheels
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6+cu121.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.6/exllamav2-0.2.6-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7+cu121.torch2.4.1-cp310-cp310-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.10"
https://github.com/oobabooga/exllamav2/releases/download/v0.2.7/exllamav2-0.2.7-py3-none-any.whl; platform_system == "Linux" and platform_machine != "x86_64"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp311-cp311-win_amd64.whl; platform_system == "Windows" and python_version == "3.11"
https://github.com/oobabooga/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu122torch2.4.1cxx11abiFALSE-cp310-cp310-win_amd64.whl; platform_system == "Windows" and python_version == "3.10"
https://github.com/Dao-AILab/flash-attention/releases/download/v2.7.2.post1/flash_attn-2.7.2.post1+cu12torch2.4cxx11abiFALSE-cp311-cp311-linux_x86_64.whl; platform_system == "Linux" and platform_machine == "x86_64" and python_version == "3.11"

2
requirements_nowheels.txt
View File

@ -4,7 +4,7 @@ datasets
einops
fastapi==0.112.4
gradio==4.37.*
jinja2==3.1.4
jinja2==3.1.5
markdown
numba==0.59.*
numpy==1.26.*

3
server.py
View File

@ -154,6 +154,9 @@ def create_interface():
if ({str(shared.settings['dark_theme']).lower()}) {{
document.getElementsByTagName('body')[0].classList.add('dark');
}}
else {{
document.getElementsByTagName('body')[0].classList.remove('dark');
}}
{js}
{ui.show_controls_js}
toggle_controls(x);