CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-01 09:01:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

convert-hf : support Mini-Jamba conversion

Browse Source
This commit is contained in:
Francis Couture-Harpin
2024-05-25 13:55:11 -04:00
parent ea2e63e9d2
commit fc59407efe
2 changed files with 23 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
gguf-py/gguf/tensor_mapping.py
View File

@@ -207,6 +207,7 @@ class TensorNameMap:
"model.layers.{bid}.ffn_norm", # internlm2
"transformer.decoder_layer.{bid}.rms_norm_2", # Grok
"model.layers.{bid}.pre_ff_layernorm", # jamba
"model.layers.{bid}.pre_moe_layernorm", # mini-jamba
),
MODEL_TENSOR.FFN_GATE_INP: (
@@ -390,10 +391,12 @@ class TensorNameMap:
MODEL_TENSOR.SSM_B_NORM: (
"model.layers.{bid}.mamba.b_layernorm", # jamba
"model.layers.{bid}.mamba.B_layernorm", # mini-jamba
),
MODEL_TENSOR.SSM_C_NORM: (
"model.layers.{bid}.mamba.c_layernorm", # jamba
"model.layers.{bid}.mamba.C_layernorm", # mini-jamba
),
MODEL_TENSOR.SSM_D: (