Created some models #10
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
F47-503
requested changes
Sep 14, 2023
models/huggingface_models.py
Outdated
| model = AutoModel.from_pretrained("daryl149/llama-2-7b-chat-hf") | ||
|
|
||
|
|
||
| # tokenizer = LlamaTokenizer.from_pretrained("/output/path") |
There was a problem hiding this comment.
Better do not leave commented unused code like this
bzz
reviewed
Sep 14, 2023
server/models/huggingface_models.py
Outdated
| pipeline = transformers.pipeline( | ||
| "text-generation", | ||
| model=model, | ||
| torch_dtype=torch.float16, |
There was a problem hiding this comment.
let's use torch.bfloat16 but still that would be ~12Gb
I've used int4 quantisation
nf4_config = BitsAndBytesConfig(
load_in_4bit=True,
bnb_4bit_quant_type="nf4",
bnb_4bit_use_double_quant=True,
bnb_4bit_compute_dtype=torch.bfloat16
)
model_nf4 = AutoModelForCausalLM.from_pretrained(model_name, quantization_config=nf4_config)
tokenizer = AutoTokenizer.from_pretrained(model_name)
pipeline = transformers.pipeline(
"text-generation",
model=model_nf4,
torch_dtype=torch.bfloat16,
tokenizer=tokenizer
)
bzz
reviewed
Sep 14, 2023
The reason why I cannot test locally - I have Metal architecture. The most common error is the inability to use int4 in Metal, but it is used in model implementation, so I simply have not got access to this part of the code.
BitsAndBytes, without local testing
|
ATM this can not be merged until the conflicts are resolved. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.