mirror of
https://github.com/KoboldAI/KoboldAI-Client.git
synced 2025-06-05 21:59:24 +02:00
Revision Fixes
This commit is contained in:
Henk
94
aiserver.py
94
aiserver.py
@@ -1590,13 +1590,13 @@ def get_layer_count(model, directory=""):
|
||||
model = directory
|
||||
from transformers import AutoConfig
|
||||
if(os.path.isdir(model.replace('/', '_'))):
|
||||
model_config = AutoConfig.from_pretrained(model.replace('/', '_'), revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained(model.replace('/', '_'), revision=args.revision, cache_dir="cache")
|
||||
elif(os.path.isdir("models/{}".format(model.replace('/', '_')))):
|
||||
model_config = AutoConfig.from_pretrained("models/{}".format(model.replace('/', '_')), revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained("models/{}".format(model.replace('/', '_')), revision=args.revision, cache_dir="cache")
|
||||
elif(os.path.isdir(directory)):
|
||||
model_config = AutoConfig.from_pretrained(directory, revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained(directory, revision=args.revision, cache_dir="cache")
|
||||
else:
|
||||
model_config = AutoConfig.from_pretrained(model, revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained(model, revision=args.revision, cache_dir="cache")
|
||||
try:
|
||||
if ((utils.HAS_ACCELERATE and model_config.model_type != 'gpt2') or model_config.model_type in ("gpt_neo", "gptj", "xglm", "opt")) and not vars.nobreakmodel:
|
||||
return utils.num_layers(model_config)
|
||||
@@ -2231,19 +2231,19 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
from transformers import AutoConfig
|
||||
if(os.path.isdir(vars.custmodpth.replace('/', '_'))):
|
||||
try:
|
||||
model_config = AutoConfig.from_pretrained(vars.custmodpth.replace('/', '_'), revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained(vars.custmodpth.replace('/', '_'), revision=args.revision, cache_dir="cache")
|
||||
vars.model_type = model_config.model_type
|
||||
except ValueError as e:
|
||||
vars.model_type = "not_found"
|
||||
elif(os.path.isdir("models/{}".format(vars.custmodpth.replace('/', '_')))):
|
||||
try:
|
||||
model_config = AutoConfig.from_pretrained("models/{}".format(vars.custmodpth.replace('/', '_')), revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained("models/{}".format(vars.custmodpth.replace('/', '_')), revision=args.revision, cache_dir="cache")
|
||||
vars.model_type = model_config.model_type
|
||||
except ValueError as e:
|
||||
vars.model_type = "not_found"
|
||||
else:
|
||||
try:
|
||||
model_config = AutoConfig.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
model_config = AutoConfig.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
vars.model_type = model_config.model_type
|
||||
except ValueError as e:
|
||||
vars.model_type = "not_found"
|
||||
@@ -2482,19 +2482,19 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
with(maybe_use_float16()):
|
||||
try:
|
||||
if os.path.exists(vars.custmodpth):
|
||||
model = GPT2LMHeadModel.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
model = GPT2LMHeadModel.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
elif os.path.exists(os.path.join("models/", vars.custmodpth)):
|
||||
model = GPT2LMHeadModel.from_pretrained(os.path.join("models/", vars.custmodpth), revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(os.path.join("models/", vars.custmodpth), revision=vars.revision, cache_dir="cache")
|
||||
model = GPT2LMHeadModel.from_pretrained(os.path.join("models/", vars.custmodpth), revision=args.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(os.path.join("models/", vars.custmodpth), revision=args.revision, cache_dir="cache")
|
||||
else:
|
||||
model = GPT2LMHeadModel.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
model = GPT2LMHeadModel.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
if("out of memory" in traceback.format_exc().lower()):
|
||||
raise RuntimeError("One of your GPUs ran out of memory when KoboldAI tried to load your model.")
|
||||
raise e
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
model.save_pretrained("models/{}".format(vars.model.replace('/', '_')), max_shard_size="500MiB")
|
||||
tokenizer.save_pretrained("models/{}".format(vars.model.replace('/', '_')))
|
||||
vars.modeldim = get_hidden_size_from_model(model)
|
||||
@@ -2541,38 +2541,38 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
lowmem = {}
|
||||
if(os.path.isdir(vars.custmodpth)):
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
try:
|
||||
model = AutoModelForCausalLM.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = AutoModelForCausalLM.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache", **lowmem)
|
||||
except Exception as e:
|
||||
if("out of memory" in traceback.format_exc().lower()):
|
||||
raise RuntimeError("One of your GPUs ran out of memory when KoboldAI tried to load your model.")
|
||||
model = GPTNeoForCausalLM.from_pretrained(vars.custmodpth, revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = GPTNeoForCausalLM.from_pretrained(vars.custmodpth, revision=args.revision, cache_dir="cache", **lowmem)
|
||||
elif(os.path.isdir("models/{}".format(vars.model.replace('/', '_')))):
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
try:
|
||||
model = AutoModelForCausalLM.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = AutoModelForCausalLM.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=args.revision, cache_dir="cache", **lowmem)
|
||||
except Exception as e:
|
||||
if("out of memory" in traceback.format_exc().lower()):
|
||||
raise RuntimeError("One of your GPUs ran out of memory when KoboldAI tried to load your model.")
|
||||
model = GPTNeoForCausalLM.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = GPTNeoForCausalLM.from_pretrained("models/{}".format(vars.model.replace('/', '_')), revision=args.revision, cache_dir="cache", **lowmem)
|
||||
else:
|
||||
old_rebuild_tensor = torch._utils._rebuild_tensor
|
||||
def new_rebuild_tensor(storage: Union[torch_lazy_loader.LazyTensor, torch.Storage], storage_offset, shape, stride):
|
||||
@@ -2588,21 +2588,21 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
torch._utils._rebuild_tensor = new_rebuild_tensor
|
||||
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.model, revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.model, revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.model, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained(vars.model, revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
try:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.model, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained(vars.model, revision=args.revision, cache_dir="cache")
|
||||
except Exception as e:
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
try:
|
||||
model = AutoModelForCausalLM.from_pretrained(vars.model, revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = AutoModelForCausalLM.from_pretrained(vars.model, revision=args.revision, cache_dir="cache", **lowmem)
|
||||
except Exception as e:
|
||||
if("out of memory" in traceback.format_exc().lower()):
|
||||
raise RuntimeError("One of your GPUs ran out of memory when KoboldAI tried to load your model.")
|
||||
model = GPTNeoForCausalLM.from_pretrained(vars.model, revision=vars.revision, cache_dir="cache", **lowmem)
|
||||
model = GPTNeoForCausalLM.from_pretrained(vars.model, revision=args.revision, cache_dir="cache", **lowmem)
|
||||
|
||||
torch._utils._rebuild_tensor = old_rebuild_tensor
|
||||
|
||||
@@ -2619,10 +2619,10 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
import huggingface_hub
|
||||
legacy = packaging.version.parse(transformers_version) < packaging.version.parse("4.22.0.dev0")
|
||||
# Save the config.json
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, transformers.configuration_utils.CONFIG_NAME, revision=vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.configuration_utils.CONFIG_NAME))
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, transformers.configuration_utils.CONFIG_NAME, revision=args.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.configuration_utils.CONFIG_NAME))
|
||||
if(utils.num_shards is None):
|
||||
# Save the pytorch_model.bin of an unsharded model
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, transformers.modeling_utils.WEIGHTS_NAME, revision=args.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_NAME))
|
||||
else:
|
||||
with open(utils.from_pretrained_index_filename) as f:
|
||||
map_data = json.load(f)
|
||||
@@ -2631,7 +2631,7 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
shutil.move(os.path.realpath(utils.from_pretrained_index_filename), os.path.join("models/{}".format(vars.model.replace('/', '_')), transformers.modeling_utils.WEIGHTS_INDEX_NAME))
|
||||
# Then save the pytorch_model-#####-of-#####.bin files
|
||||
for filename in filenames:
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, filename, revision=vars.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), filename))
|
||||
shutil.move(os.path.realpath(huggingface_hub.hf_hub_download(vars.model, filename, revision=args.revision, cache_dir="cache", local_files_only=True, legacy_cache_layout=legacy)), os.path.join("models/{}".format(vars.model.replace('/', '_')), filename))
|
||||
shutil.rmtree("cache/")
|
||||
|
||||
if(vars.badwordsids is vars.badwordsids_default and vars.model_type not in ("gpt2", "gpt_neo", "gptj")):
|
||||
@@ -2677,7 +2677,7 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
|
||||
else:
|
||||
from transformers import GPT2Tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
else:
|
||||
from transformers import PreTrainedModel
|
||||
from transformers import modeling_utils
|
||||
@@ -2776,11 +2776,11 @@ def load_model(use_gpu=True, gpu_layers=None, disk_layers=None, initial_load=Fal
|
||||
# If we're running Colab or OAI, we still need a tokenizer.
|
||||
if(vars.model in ("Colab", "API", "CLUSTER")):
|
||||
from transformers import GPT2Tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("EleutherAI/gpt-neo-2.7B", revision=args.revision, cache_dir="cache")
|
||||
loadsettings()
|
||||
elif(vars.model == "OAI"):
|
||||
from transformers import GPT2Tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
loadsettings()
|
||||
# Load the TPU backend if requested
|
||||
elif(vars.use_colab_tpu or vars.model in ("TPUMeshTransformerGPTJ", "TPUMeshTransformerGPTNeoX")):
|
||||
@@ -3037,7 +3037,7 @@ def lua_decode(tokens):
|
||||
if("tokenizer" not in globals()):
|
||||
from transformers import GPT2Tokenizer
|
||||
global tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
return utils.decodenewlines(tokenizer.decode(tokens))
|
||||
|
||||
#==================================================================#
|
||||
@@ -3049,7 +3049,7 @@ def lua_encode(string):
|
||||
if("tokenizer" not in globals()):
|
||||
from transformers import GPT2Tokenizer
|
||||
global tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
return tokenizer.encode(utils.encodenewlines(string), max_length=int(4e9), truncation=True)
|
||||
|
||||
#==================================================================#
|
||||
@@ -4198,19 +4198,19 @@ def actionsubmit(data, actionmode=0, force_submit=False, force_prompt_gen=False,
|
||||
try:
|
||||
if(os.path.isdir(tokenizer_id)):
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=args.revision, cache_dir="cache")
|
||||
except:
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
elif(os.path.isdir("models/{}".format(tokenizer_id.replace('/', '_')))):
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(tokenizer_id.replace('/', '_')), revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(tokenizer_id.replace('/', '_')), revision=args.revision, cache_dir="cache")
|
||||
except:
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(tokenizer_id.replace('/', '_')), revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained("models/{}".format(tokenizer_id.replace('/', '_')), revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
else:
|
||||
try:
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=args.revision, cache_dir="cache")
|
||||
except:
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=vars.revision, cache_dir="cache", use_fast=False)
|
||||
tokenizer = AutoTokenizer.from_pretrained(tokenizer_id, revision=args.revision, cache_dir="cache", use_fast=False)
|
||||
except:
|
||||
logger.warning(f"Unknown tokenizer {repr(tokenizer_id)}")
|
||||
vars.api_tokenizer_id = tokenizer_id
|
||||
@@ -4622,7 +4622,7 @@ def calcsubmitbudget(actionlen, winfo, mem, anotetxt, actions, submission=None,
|
||||
if("tokenizer" not in globals()):
|
||||
from transformers import GPT2Tokenizer
|
||||
global tokenizer
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=vars.revision, cache_dir="cache")
|
||||
tokenizer = GPT2Tokenizer.from_pretrained("gpt2", revision=args.revision, cache_dir="cache")
|
||||
|
||||
lnheader = len(tokenizer._koboldai_header)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user