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

llama : add SEA-LION support (#6448)

Browse source 
* initial commit for sealion support

* add sealion support

* minor fix

* q/k ln and pos_embd only if required

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* minor : clear whitespaces

---------

Co-authored-by: bryan <bryansiow@aisingapore.org>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
bryanSwk 2024-04-04 02:05:10 +08:00 • committed by GitHub
parent 9f62c0173d
commit bb43cf7e9d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 65 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

15
convert-hf-to-gguf.py
View file

@ -510,6 +510,16 @@ class BloomModel(Model):
class MPTModel(Model):
model_arch = gguf.MODEL_ARCH.MPT
def set_vocab(self):
try:
self._set_vocab_gpt2()
except:
self._set_vocab_sentencepiece()
self.gguf_writer.add_add_bos_token(False)
self.gguf_writer.add_pad_token_id(3)
self.gguf_writer.add_eos_token_id(1)
self.gguf_writer.add_unk_token_id(0)
def set_gguf_parameters(self):
block_count = self.hparams["n_layers"]
self.gguf_writer.add_name(self.dir_model.name)
@ -523,7 +533,10 @@ class MPTModel(Model):
self.gguf_writer.add_layer_norm_eps(1e-5)
if self.hparams["attn_config"]["clip_qkv"] is not None:
self.gguf_writer.add_clamp_kqv(self.hparams["attn_config"]["clip_qkv"])
self.gguf_writer.add_max_alibi_bias(self.hparams["attn_config"]["alibi_bias_max"])
if self.hparams["attn_config"]["alibi"]:
self.gguf_writer.add_max_alibi_bias(self.hparams["attn_config"]["alibi_bias_max"])
else:
self.gguf_writer.add_max_alibi_bias(0.0)
def write_tensors(self):
block_count = self.hparams.get("n_layers", self.hparams.get("num_hidden_layers"))