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

formatting comments and vocab test for gpt2

Browse source
This commit is contained in:
manikbhandari 2023-12-22 06:43:17 -05:00
parent f618e95eba
commit 39515c50cc
3 changed files with 5 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
convert-hf-to-gguf.py
View file

@ -988,6 +988,7 @@ class QwenModel(Model):
print(f"{new_name}, n_dims = {n_dims}, {old_dtype} --> {data.dtype}")
self.gguf_writer.add_tensor(new_name, data)
class GPT2Model(Model):
def set_gguf_parameters(self):
self.gguf_writer.add_name(self.dir_model.name)
@ -1002,7 +1003,7 @@ class GPT2Model(Model):
def write_tensors(self):
block_count = self.hparams.get("n_layers", self.hparams.get("num_hidden_layers", self.hparams.get("n_layer")))
tensor_map = gguf.get_tensor_name_map(self.model_arch, block_count)
# import pdb; pdb.set_trace()
for name, data_torch in self.get_tensors():
# we don't need these
if name.endswith((".attention.masked_bias", ".attention.bias", ".attention.rotary_emb.inv_freq", ".attn.bias")):
@ -1049,6 +1050,7 @@ class GPT2Model(Model):
print(f"output.weight, n_dims = {n_dims}, {old_dtype} --> {data.dtype}")
self.gguf_writer.add_tensor("output.weight", data)
class Phi2Model(Model):
def set_gguf_parameters(self):
block_count = self.hparams["n_layer"]

1
llama.cpp
View file

@ -5739,6 +5739,7 @@ struct llm_build_context {
return gf;
}
struct ggml_cgraph * build_gpt2() {
struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false);

1
tests/CMakeLists.txt
View file

@ -41,6 +41,7 @@ llama_test_executable (test-tokenizer-1-stablelm-3b-4e1t test-tokenizer-1-bpe.cp
llama_test_executable (test-tokenizer-1-gpt-neox test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf)
llama_test_executable (test-tokenizer-1-refact test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
llama_test_executable (test-tokenizer-1-starcoder test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
llama_test_executable (test-tokenizer-1-gpt2 test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt2.gguf)
# llama_test_executable (test-tokenizer-1-bloom test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bloom.gguf) # BIG
llama_build_and_test_executable(test-grammar-parser.cpp)