diff options
| author | saood06 <saood05@gmail.com> | 2025-05-09 02:09:59 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 10:09:59 +0300 |
| commit | bc6ae515ceb14eeaf198e00251a9689539cea176 (patch) | |
| tree | 82ca4aa8afa0dce38e0f3cb6fa9c7a78ec0065d2 /gguf-py/gguf/tensor_mapping.py | |
| parent | 4084ca7331611da4426d781a15a6ffa68312759e (diff) | |
Support for Llama-3-Nemotron models (#377)
* conflict resolution
* Changes to make work and add longrope support
* Changes to n_attention_wv rule
* Untested support of 253B
* DeciLMCausalModel now reads rope_theta from config.json properly
* Remove errant Granite mentions
* Better n_attention_vw rule
* Update vocab.py
---------
Co-authored-by: Yee Man Chan <ymchan@gmail.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'gguf-py/gguf/tensor_mapping.py')
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 1dea6a82..3ff70cd7 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -176,7 +176,8 @@ class TensorNameMap: "transformer.blocks.{bid}.attn.out_proj", # mpt "transformer.h.{bid}.self_attention.dense", # falcon "h.{bid}.self_attention.dense", # bloom - "model.layers.{bid}.self_attn.o_proj", # llama-hf + "model.layers.{bid}.self_attn.o_proj", # llama-hf nemotron olmoe olmo2 + "model.layers.{bid}.self_attn.linear_attn", # deci "layers.{bid}.attention.wo", # llama-pth "encoder.layer.{bid}.attention.output.dense", # bert "transformer.h.{bid}.attn.out_proj", # gpt-j |