CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : parameter conversion and loading fixes for PLaMo2 variants (#16075)

Browse Source 
* Fix to use hidden_size_per_head

* Fix num heads

* Fix array

* Fix loading weights

* Support old GGUF converted by the previous version of llama.cpp

* Update src/llama-model.cpp

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

* Move shared parameter definitions to the outside of loop

* Not calculating n_embd_head_k,v by n_embd / n_head

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Shunta Saito
2025-10-02 06:08:15 +09:00
committed by GitHub
parent 1fe4e38cc2
commit ded67b9444
3 changed files with 27 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
convert_hf_to_gguf.py
View File

@@ -4250,7 +4250,8 @@ class Plamo2Model(TextModel):
# This logic matches modeling_plamo.py's is_mamba function
mamba_step = hparams.get("mamba_step", 2)
mamba_enabled = hparams.get("mamba_enabled", True)
mamba_layers = []
num_key_value_heads = []
num_attention_heads = []
if mamba_enabled:
for i in range(block_count):
@@ -4260,17 +4261,21 @@ class Plamo2Model(TextModel):
else:
is_mamba = (i % mamba_step) != (mamba_step // 2)
if is_mamba:
mamba_layers.append(0)
num_key_value_heads.append(0)
num_attention_heads.append(0)
else:
mamba_layers.append(hparams.get("num_key_value_heads", 4))
num_key_value_heads.append(hparams.get("num_key_value_heads", 4))
num_attention_heads.append(hparams.get("num_attention_heads", 32))
if mamba_layers:
self.gguf_writer.add_head_count_kv(mamba_layers)
if num_key_value_heads and num_attention_heads:
self.gguf_writer.add_head_count_kv(num_key_value_heads)
self.gguf_writer.add_head_count(num_attention_heads)
self.gguf_writer.add_context_length(hparams.get("max_position_embeddings", 2048))
self.gguf_writer.add_embedding_length(hparams.get("hidden_size", 4096))
self.gguf_writer.add_key_length(hparams.get("hidden_size_per_head", 128))
self.gguf_writer.add_value_length(hparams.get("hidden_size_per_head", 128))
self.gguf_writer.add_block_count(block_count)
self.gguf_writer.add_head_count(hparams.get("num_attention_heads", 32))
self.gguf_writer.add_layer_norm_rms_eps(hparams.get("rms_norm_eps", 1e-06))
self.gguf_writer.add_rope_freq_base(hparams.get("rope_theta", 10000))