vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

remove convert.py

Browse source 
can i just use the changes view?
This commit is contained in:
Henri Vasserman 2023-05-30 16:42:11 +03:00 • committed by GitHub
parent aeacc57d3b
commit 2e84ad53ca
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

20
convert.py
View file

@ -143,22 +143,12 @@ class Params:
def guessed(model: 'LazyModel', file_type: GGMLFileType) -> 'Params': def guessed(model: 'LazyModel', file_type: GGMLFileType) -> 'Params':
n_vocab, n_embd = model["tok_embeddings.weight"].shape n_vocab, n_embd = model["tok_embeddings.weight"].shape
n_mult=256
n_head=n_embd // 128
n_layer=next(i for i in itertools.count() if f"layers.{i}.attention.wq.weight" not in model)
# TODO: hack for open_llama_3b
if n_embd == 3200:
n_mult = 216
n_head = 32
n_layer = 26
return Params( return Params(
n_vocab=n_vocab, n_vocab=n_vocab,
n_embd=n_embd, n_embd=n_embd,
n_mult=n_mult, n_mult=256,
n_head=n_head, n_head=n_embd // 128,
n_layer=n_layer, n_layer=next(i for i in itertools.count() if f"layers.{i}.attention.wq.weight" not in model),
file_type=file_type, file_type=file_type,
) )
@ -607,9 +597,7 @@ def convert_transformers_to_orig(model: LazyModel) -> LazyModel:
out["norm.weight"] = model["model.norm.weight"] out["norm.weight"] = model["model.norm.weight"]
out["output.weight"] = model["lm_head.weight"] out["output.weight"] = model["lm_head.weight"]
# TODO: hack for open_llama_3b n_head = model["model.layers.0.self_attn.q_proj.weight"].shape[1] // 128
n_embd = model["model.layers.0.self_attn.q_proj.weight"].shape[1]
n_head = 32 if n_embd == 3200 else n_embd // 128
for i in itertools.count(): for i in itertools.count():
if f"model.layers.{i}.self_attn.q_proj.weight" not in model: if f"model.layers.{i}.self_attn.q_proj.weight" not in model:
break break