diff options
| author | saood06 <saood05@gmail.com> | 2025-07-10 02:37:36 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-10 02:37:36 -0500 |
| commit | c53cb65251168006b29da91fea7e5e42d815af15 (patch) | |
| tree | 0afdec44454a7e3dc379102de8346bbe6c92cd91 /gguf-py/gguf/tensor_mapping.py | |
| parent | 283753cabcabd30eb2cfb93739d9c1679200bf1f (diff) | |
Support for dots.llm1 models (#573)
* Add llama.cpp changes for dots1 support
* Add python changes for dots1 support
* Fix to make it convert
* Remove V reshaping, remove BOS by default for dots1 and fix warmup to handle models without BOS
* Minor fix
* Remove commented lines
Diffstat (limited to 'gguf-py/gguf/tensor_mapping.py')
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 9688b02c..d507725c 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -257,7 +257,7 @@ class TensorNameMap: ), MODEL_TENSOR.FFN_EXP_PROBS_B: ( - "model.layers.{bid}.mlp.gate.e_score_correction", # deepseek-v3 + "model.layers.{bid}.mlp.gate.e_score_correction", # deepseek-v3 dots1 ), # Feed-forward up |