github/AMD-SHARK-Studio
1
1
Fork 0
mirror of https://github.com/nod-ai/AMD-SHARK-Studio.git synced 2026-04-03 03:00:17 -04:00
Code Issues Packages Projects Releases Wiki Activity

[chatbot] Remove few outdated models from list (#1814)

Browse Source
This commit is contained in:
Gaurav Shukla
2023-09-04 21:56:32 +05:30
committed by GitHub
parent 87ae14b6ff
commit d2f64eefa3
2 changed files with 70 additions and 193 deletions
Download Patch File Download Diff File Expand all files Collapse all files

196
apps/stable_diffusion/web/ui/stablelm_ui.py
View File

@@ -26,11 +26,7 @@ model_map = {
"llama2_7b": "meta-llama/Llama-2-7b-chat-hf",
"llama2_13b": "meta-llama/Llama-2-13b-chat-hf",
"llama2_70b": "meta-llama/Llama-2-70b-chat-hf",
"codegen": "Salesforce/codegen25-7b-multi",
"vicuna1p3": "lmsys/vicuna-7b-v1.3",
"vicuna": "TheBloke/vicuna-7B-1.1-HF",
"vicuna4": "TheBloke/vicuna-7B-1.1-HF",
"StableLM": "stabilityai/stablelm-tuned-alpha-3b",
}
# NOTE: Each `model_name` should have its own start message
@@ -62,33 +58,11 @@ start_message = {
"explain why instead of answering something not correct. If you don't know the "
"answer to a question, please don't share false information."
),
"StableLM": (
"<|SYSTEM|># StableLM Tuned (Alpha version)"
"\n- StableLM is a helpful and harmless open-source AI language model "
"developed by StabilityAI."
"\n- StableLM is excited to be able to help the user, but will refuse "
"to do anything that could be considered harmful to the user."
"\n- StableLM is more than just an information source, StableLM is also "
"able to write poetry, short stories, and make jokes."
"\n- StableLM will refuse to participate in anything that "
"could harm a human."
),
"vicuna": (
"A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's "
"questions.\n"
),
"vicuna4": (
"A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's "
"questions.\n"
),
"vicuna1p3": (
"A chat between a curious user and an artificial intelligence assistant. "
"The assistant gives helpful, detailed, and polite answers to the user's "
"questions.\n"
),
"codegen": "",
}
@@ -96,10 +70,7 @@ def create_prompt(model_name, history):
system_message = start_message[model_name]
if model_name in [
"StableLM",
"vicuna",
"vicuna4",
"vicuna1p3",
"llama2_7b",
"llama2_13b",
"llama2_70b",
@@ -183,123 +154,68 @@ def chat(
else:
print("unrecognized device")
from apps.language_models.scripts.vicuna import ShardedVicuna
from apps.language_models.scripts.vicuna import UnshardedVicuna
from apps.stable_diffusion.src import args
new_model_vmfb_key = f"{model_name}#{model_path}#{device}#{precision}"
if model_name in [
"vicuna",
"vicuna4",
"vicuna1p3",
"codegen",
"llama2_7b",
"llama2_13b",
"llama2_70b",
]:
from apps.language_models.scripts.vicuna import ShardedVicuna
from apps.language_models.scripts.vicuna import UnshardedVicuna
from apps.stable_diffusion.src import args
if new_model_vmfb_key != model_vmfb_key:
model_vmfb_key = new_model_vmfb_key
max_toks = 128 if model_name == "codegen" else 512
# get iree flags that need to be overridden, from commandline args
_extra_args = []
# vulkan target triple
if args.iree_vulkan_target_triple != "":
_extra_args.append(
f"-iree-vulkan-target-triple={args.iree_vulkan_target_triple}"
)
if model_name == "vicuna4":
vicuna_model = ShardedVicuna(
model_name,
hf_model_path=model_path,
device=device,
precision=precision,
max_num_tokens=max_toks,
compressed=True,
extra_args_cmd=_extra_args,
)
else:
# if config_file is None:
vicuna_model = UnshardedVicuna(
model_name,
hf_model_path=model_path,
hf_auth_token=args.hf_auth_token,
device=device,
precision=precision,
max_num_tokens=max_toks,
download_vmfb=download_vmfb,
load_mlir_from_shark_tank=True,
extra_args_cmd=_extra_args,
)
# else:
# if config_file is not None:
# config_file = open(config_file)
# config_json = json.load(config_file)
# config_file.close()
# else:
# config_json = get_default_config()
# vicuna_model = ShardedVicuna(
# model_name,
# device=device,
# precision=precision,
# config_json=config_json,
# )
prompt = create_prompt(model_name, history)
partial_text = ""
count = 0
start_time = time.time()
for text, msg in progress.tqdm(
vicuna_model.generate(prompt, cli=cli),
desc="generating response",
):
count += 1
if "formatted" in msg:
history[-1][1] = text
end_time = time.time()
tokens_per_sec = count / (end_time - start_time)
yield history, str(
format(tokens_per_sec, ".2f")
) + " tokens/sec"
else:
partial_text += text + " "
history[-1][1] = partial_text
yield history, ""
return history, ""
# else Model is StableLM
global sharkModel
from apps.language_models.src.pipelines.stablelm_pipeline import (
SharkStableLM,
)
if new_model_vmfb_key != model_vmfb_key:
model_vmfb_key = new_model_vmfb_key
# max_new_tokens=512
shark_slm = SharkStableLM(
model_name
) # pass elements from UI as required
max_toks = 128 if model_name == "codegen" else 512
# get iree flags that need to be overridden, from commandline args
_extra_args = []
# vulkan target triple
if args.iree_vulkan_target_triple != "":
_extra_args.append(
f"-iree-vulkan-target-triple={args.iree_vulkan_target_triple}"
)
if model_name == "vicuna4":
vicuna_model = ShardedVicuna(
model_name,
hf_model_path=model_path,
device=device,
precision=precision,
max_num_tokens=max_toks,
compressed=True,
extra_args_cmd=_extra_args,
)
else:
# if config_file is None:
vicuna_model = UnshardedVicuna(
model_name,
hf_model_path=model_path,
hf_auth_token=args.hf_auth_token,
device=device,
precision=precision,
max_num_tokens=max_toks,
download_vmfb=download_vmfb,
load_mlir_from_shark_tank=True,
extra_args_cmd=_extra_args,
)
# Construct the input message string for the model by concatenating the
# current system message and conversation history
if len(curr_system_message.split()) > 160:
print("clearing context")
prompt = create_prompt(model_name, history)
generate_kwargs = dict(prompt=prompt)
words_list = shark_slm.generate(**generate_kwargs)
partial_text = ""
for new_text in words_list:
partial_text += new_text
history[-1][1] = partial_text
# Yield an empty string to clean up the message textbox and the updated
# conversation history
yield history
return words_list
count = 0
start_time = time.time()
for text, msg in progress.tqdm(
vicuna_model.generate(prompt, cli=cli),
desc="generating response",
):
count += 1
if "formatted" in msg:
history[-1][1] = text
end_time = time.time()
tokens_per_sec = count / (end_time - start_time)
yield history, str(format(tokens_per_sec, ".2f")) + " tokens/sec"
else:
partial_text += text + " "
history[-1][1] = partial_text
yield history, ""
return history, ""
def llm_chat_api(InputData: dict):
@@ -417,7 +333,7 @@ with gr.Blocks(title="Chatbot") as stablelm_chat:
)
model = gr.Dropdown(
label="Select Model",
value=model_choices[4],
value=model_choices[1],
choices=model_choices,
)
supported_devices = available_devices