From 739cccd8ed9e1da819a3b7260e9c4c79f8a1ab43 Mon Sep 17 00:00:00 2001 From: Henk Date: Tue, 31 Jan 2023 04:48:46 +0100 Subject: [PATCH 1/5] Revision Fixes --- aiserver.py | 94 ++++++++++++++++++++++++++--------------------------- utils.py | 14 ++++---- 2 files changed, 54 insertions(+), 54 deletions(-) diff --git a/aiserver.py b/aiserver.py index 629dcba3..665b43f6 100644 --- a/aiserver.py +++ b/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) diff --git a/utils.py b/utils.py index baa74add..79f90b11 100644 --- a/utils.py +++ b/utils.py @@ -261,7 +261,7 @@ def _transformers22_aria2_hook(pretrained_model_name_or_path: str, force_downloa if token is None: raise EnvironmentError("You specified use_auth_token=True, but a huggingface token was not found.") _cache_dir = str(cache_dir) if cache_dir is not None else transformers.TRANSFORMERS_CACHE - _revision = revision if revision is not None else huggingface_hub.constants.DEFAULT_REVISION + _revision = args.revision if args.revision is not None else huggingface_hub.constants.DEFAULT_REVISION sharded = False headers = {"user-agent": transformers.file_utils.http_user_agent(user_agent)} if use_auth_token: @@ -272,7 +272,7 @@ def _transformers22_aria2_hook(pretrained_model_name_or_path: str, force_downloa def is_cached(filename): try: - huggingface_hub.hf_hub_download(pretrained_model_name_or_path, filename, cache_dir=cache_dir, local_files_only=True) + huggingface_hub.hf_hub_download(pretrained_model_name_or_path, filename, cache_dir=cache_dir, local_files_only=True, revision=_revision) except ValueError: return False return True @@ -281,7 +281,7 @@ def _transformers22_aria2_hook(pretrained_model_name_or_path: str, force_downloa filename = transformers.modeling_utils.WEIGHTS_INDEX_NAME if sharded else transformers.modeling_utils.WEIGHTS_NAME except AttributeError: return - url = huggingface_hub.hf_hub_url(pretrained_model_name_or_path, filename, revision=revision) + url = huggingface_hub.hf_hub_url(pretrained_model_name_or_path, filename, revision=_revision) if is_cached(filename) or requests.head(url, allow_redirects=True, proxies=proxies, headers=headers): break if sharded: @@ -295,7 +295,7 @@ def _transformers22_aria2_hook(pretrained_model_name_or_path: str, force_downloa with open(map_filename) as f: map_data = json.load(f) filenames = set(map_data["weight_map"].values()) - urls = [huggingface_hub.hf_hub_url(pretrained_model_name_or_path, n, revision=revision) for n in filenames] + urls = [huggingface_hub.hf_hub_url(pretrained_model_name_or_path, n, revision=_revision) for n in filenames] if not force_download: urls = [u for u, n in zip(urls, filenames) if not is_cached(n)] if not urls: @@ -494,7 +494,7 @@ def aria2_hook(pretrained_model_name_or_path: str, force_download=False, cache_d filename = transformers.modeling_utils.WEIGHTS_INDEX_NAME if sharded else transformers.modeling_utils.WEIGHTS_NAME except AttributeError: return - url = huggingface_hub.hf_hub_url(pretrained_model_name_or_path, filename, revision=revision) + url = huggingface_hub.hf_hub_url(pretrained_model_name_or_path, filename, revision=_revision) if is_cached(url) or requests.head(url, allow_redirects=True, proxies=proxies, headers=headers): break if sharded: @@ -508,7 +508,7 @@ def aria2_hook(pretrained_model_name_or_path: str, force_download=False, cache_d with open(map_filename) as f: map_data = json.load(f) filenames = set(map_data["weight_map"].values()) - urls = [huggingface_hub.hf_hub_url(pretrained_model_name_or_path, n, revision=revision) for n in filenames] + urls = [huggingface_hub.hf_hub_url(pretrained_model_name_or_path, n, revision=_revision) for n in filenames] if not force_download: urls = [u for u in urls if not is_cached(u)] if not urls: @@ -555,7 +555,7 @@ def get_num_shards(filename): def get_sharded_checkpoint_num_tensors(pretrained_model_name_or_path, filename, cache_dir=None, force_download=False, proxies=None, resume_download=False, local_files_only=False, use_auth_token=None, user_agent=None, revision=None, **kwargs): import transformers.modeling_utils import torch - shard_paths, _ = transformers.modeling_utils.get_checkpoint_shard_files(pretrained_model_name_or_path, filename, cache_dir=cache_dir, force_download=force_download, proxies=proxies, resume_download=resume_download, local_files_only=local_files_only, use_auth_token=use_auth_token, user_agent=user_agent, revision=revision) + shard_paths, _ = transformers.modeling_utils.get_checkpoint_shard_files(pretrained_model_name_or_path, filename, cache_dir=cache_dir, force_download=force_download, proxies=proxies, resume_download=resume_download, local_files_only=local_files_only, use_auth_token=use_auth_token, user_agent=user_agent, revision=_revision) return list(itertools.chain(*(torch.load(p, map_location="cpu").keys() for p in shard_paths))) #==================================================================# From 257a535be59a6ebc57eabf26089bbfdd85310994 Mon Sep 17 00:00:00 2001 From: Henk Date: Tue, 31 Jan 2023 05:17:34 +0100 Subject: [PATCH 2/5] Revision Fixes Fixes --- utils.py | 2 ++ 1 file changed, 2 insertions(+) diff --git a/utils.py b/utils.py index 79f90b11..01c8b2a3 100644 --- a/utils.py +++ b/utils.py @@ -460,6 +460,7 @@ def aria2_hook(pretrained_model_name_or_path: str, force_download=False, cache_d import transformers import transformers.modeling_utils from huggingface_hub import HfFolder + _revision = args.revision if args.revision is not None else huggingface_hub.constants.DEFAULT_REVISION if shutil.which("aria2c") is None: # Don't do anything if aria2 is not installed return if local_files_only: # If local_files_only is true, we obviously don't need to download anything @@ -555,6 +556,7 @@ def get_num_shards(filename): def get_sharded_checkpoint_num_tensors(pretrained_model_name_or_path, filename, cache_dir=None, force_download=False, proxies=None, resume_download=False, local_files_only=False, use_auth_token=None, user_agent=None, revision=None, **kwargs): import transformers.modeling_utils import torch + _revision = args.revision if args.revision is not None else huggingface_hub.constants.DEFAULT_REVISION shard_paths, _ = transformers.modeling_utils.get_checkpoint_shard_files(pretrained_model_name_or_path, filename, cache_dir=cache_dir, force_download=force_download, proxies=proxies, resume_download=resume_download, local_files_only=local_files_only, use_auth_token=use_auth_token, user_agent=user_agent, revision=_revision) return list(itertools.chain(*(torch.load(p, map_location="cpu").keys() for p in shard_paths))) From 661bd5c99e7a03c94bfea436ad5f04614f2953f2 Mon Sep 17 00:00:00 2001 From: henk717 Date: Tue, 31 Jan 2023 19:24:19 +0100 Subject: [PATCH 3/5] Hide Pygmalion 6B Dev, currently only supported on the GPU --- colab/TPU.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/colab/TPU.ipynb b/colab/TPU.ipynb index 60664780..9e2375e2 100644 --- a/colab/TPU.ipynb +++ b/colab/TPU.ipynb @@ -66,7 +66,7 @@ "#@title <-- Select your model below and then click this to start KoboldAI\n", "#@markdown You can find a description of the models below along with instructions on how to start KoboldAI.\n", "\n", - "Model = \"Nerys 13B V2\" #@param [\"Nerys 13B V2\", \"Erebus 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 20B\", \"Erebus 20B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Pygmalion 6B\", \"Pygmalion 6B Dev\", \"Lit V2 6B\", \"Lit 6B\", \"NeoX 20B\", \"OPT 13B\", \"Fairseq Dense 13B\", \"GPT-J-6B\"] {allow-input: true}\n", + "Model = \"Nerys 13B V2\" #@param [\"Nerys 13B V2\", \"Erebus 13B\", \"Janeway 13B\", \"Shinen 13B\", \"Skein 20B\", \"Erebus 20B\", \"Skein 6B\", \"Janeway 6B\", \"Adventure 6B\", \"Shinen 6B\", \"Pygmalion 6B\", \"Lit V2 6B\", \"Lit 6B\", \"NeoX 20B\", \"OPT 13B\", \"Fairseq Dense 13B\", \"GPT-J-6B\"] {allow-input: true}\n", "Version = \"Official\" #@param [\"Official\", \"United\"] {allow-input: true}\n", "Provider = \"Cloudflare\" #@param [\"Localtunnel\", \"Cloudflare\"]\n", "use_google_drive = True #@param {type:\"boolean\"}\n", From b58daa1ba18a7fef38f0da982d948d3807dda92f Mon Sep 17 00:00:00 2001 From: Henk Date: Fri, 10 Feb 2023 19:11:13 +0100 Subject: [PATCH 4/5] Pin Flask-cloudflared --- environments/huggingface.yml | 2 +- environments/rocm.yml | 2 +- requirements.txt | 2 +- requirements_mtj.txt | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/environments/huggingface.yml b/environments/huggingface.yml index 341a8e87..8b36a529 100644 --- a/environments/huggingface.yml +++ b/environments/huggingface.yml @@ -24,7 +24,7 @@ dependencies: - termcolor - psutil - pip: - - flask-cloudflared + - flask-cloudflared==0.0.10 - flask-ngrok - lupa==1.10 - transformers==4.24.0 diff --git a/environments/rocm.yml b/environments/rocm.yml index 3e50c565..6605709f 100644 --- a/environments/rocm.yml +++ b/environments/rocm.yml @@ -23,7 +23,7 @@ dependencies: - pip: - --extra-index-url https://download.pytorch.org/whl/rocm5.1.1 - torch==1.12.1+rocm5.1.1 - - flask-cloudflared + - flask-cloudflared==0.0.10 - flask-ngrok - lupa==1.10 - transformers==4.24.0 diff --git a/requirements.txt b/requirements.txt index a2854835..bed8308a 100644 --- a/requirements.txt +++ b/requirements.txt @@ -4,7 +4,7 @@ Flask Flask-SocketIO requests torch >= 1.9, < 1.13 -flask-cloudflared +flask-cloudflared==0.0.10 flask-ngrok eventlet dnspython==2.2.1 diff --git a/requirements_mtj.txt b/requirements_mtj.txt index f3dfe339..dc6e06dd 100644 --- a/requirements_mtj.txt +++ b/requirements_mtj.txt @@ -11,7 +11,7 @@ progressbar2 git+https://github.com/VE-FORBRYDERNE/mesh-transformer-jax@ck flask Flask-SocketIO -flask-cloudflared >= 0.0.5 +flask-cloudflared==0.0.10 flask-ngrok eventlet dnspython==2.2.1 From cc01ad730ae428c64202220ac5cd141a501ad677 Mon Sep 17 00:00:00 2001 From: Henk Date: Sat, 11 Feb 2023 11:20:21 +0100 Subject: [PATCH 5/5] Don't install safetensors for MTJ --- requirements_mtj.txt | 1 - 1 file changed, 1 deletion(-) diff --git a/requirements_mtj.txt b/requirements_mtj.txt index dc6e06dd..c03a4c5d 100644 --- a/requirements_mtj.txt +++ b/requirements_mtj.txt @@ -21,5 +21,4 @@ bleach==4.1.0 flask-session marshmallow>=3.13 apispec-webframeworks -safetensors loguru