From f98eb31c517c95960df1d0abc48002787f145f3b Mon Sep 17 00:00:00 2001 From: compilade Date: Wed, 8 May 2024 18:16:38 -0400 Subject: convert-hf : save memory with lazy evaluation (#7075) * convert-hf : begin refactoring write_tensor * convert : upgrade to sentencepiece v0.2.0 * convert-hf : remove unused n_dims in extra_*_tensors * convert-hf : simplify MoE weights stacking * convert-hf : flake8 linter doesn't like semicolons * convert-hf : allow unusual model part names For example, loading `model-00001-of-00001.safetensors` now works. * convert-hf : fix stacking MoE expert tensors `torch.stack` and `torch.cat` don't do the same thing. * convert-hf : fix Mamba conversion Tested to work even with a SentencePiece-based tokenizer. * convert : use a string for the SentencePiece tokenizer path * convert-hf : display tensor shape * convert-hf : convert norms to f32 by default * convert-hf : sort model part names `os.listdir` is said to list files in arbitrary order. Sorting the file names should let "model-00009-of-00042.safetensors" be loaded before "model-00010-of-00042.safetensors". * convert-hf : use an ABC for Model again It seems Protocol can't be used as a statically type-checked ABC, because its subclasses also can't be instantiated. (why did it seem to work?) At least there's still a way to throw an error when forgetting to define the `model_arch` property of any registered Model subclasses. * convert-hf : use a plain class for Model, and forbid direct instantiation There are no abstract methods used anyway, so using ABC isn't really necessary. * convert-hf : more consistent formatting of cmdline args * convert-hf : align the message logged for converted tensors * convert-hf : fix Refact conversion * convert-hf : save memory with lazy evaluation * convert-hf : flake8 doesn't like lowercase L as a variable name * convert-hf : remove einops requirement for InternLM2 * convert-hf : faster model parts loading Instead of pre-loading them all into a dict, iterate on the tensors in the model parts progressively as needed in Model.write_tensors Conversion for some architectures relies on checking for the presence of specific tensor names, so for multi-part models, the weight map is read from the relevant json file to quickly get these names up-front. * convert-hf : minor changes for consistency * gguf-py : add tqdm as a dependency It's small, and used for a progress bar in GGUFWriter.write_tensors_to_file --- examples/server/tests/features/steps/steps.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/server') diff --git a/examples/server/tests/features/steps/steps.py b/examples/server/tests/features/steps/steps.py index 0882a5d3..f4b1ac1d 100644 --- a/examples/server/tests/features/steps/steps.py +++ b/examples/server/tests/features/steps/steps.py @@ -939,7 +939,7 @@ async def oai_chat_completions(user_prompt, while event_received: event_received = False async for line_in_bytes in response.content: - line = line_in_bytes.decode('utf8') + line = line_in_bytes.decode('utf-8') line = line.rstrip('\n').rstrip('\r') if line == '': continue -- cgit v1.2.3