diff options
| author | saood06 <saood05@gmail.com> | 2025-05-09 09:17:41 -0500 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-05-09 09:17:41 -0500 |
| commit | 967a2e1860482397a6a386952d972ac1205474ad (patch) | |
| tree | e5fce0dba400eaf98ba343a06f007ddad408e5ce /gguf-py | |
| parent | e5a4a3ce78ce96b6822dcd6138a98c4d237ecc9b (diff) | |
Fix missing rope_freqs with convert_hf_to_gguf (#402)
* lora : fix llama conversion script with ROPE_FREQS
* convert : refactor rope_freqs generation
This should also fix vocab-only conversion for Phi-3.
* convert : adapt MiniCPM3 to separate rope_freqs insertion
MiniCPM3's tokenizer is treated as a SentencePiece tokenizer to avoid
having to run its custom Python code which mixes tokenization
in the same file as tool calls.
gguf-py : add long and short RoPE factors to tensor mappings
Empty, but the key names are used to populate the mappings.
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Francis Couture-Harpin <git@compilade.net>
Diffstat (limited to 'gguf-py')
| -rw-r--r-- | gguf-py/gguf/constants.py | 2 | ||||
| -rw-r--r-- | gguf-py/gguf/tensor_mapping.py | 3 |
2 files changed, 5 insertions, 0 deletions
diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py index e2f4eb1a..6819979f 100644 --- a/gguf-py/gguf/constants.py +++ b/gguf-py/gguf/constants.py @@ -806,6 +806,8 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = { MODEL_TENSOR.TOKEN_EMBD, MODEL_TENSOR.OUTPUT_NORM, MODEL_TENSOR.OUTPUT, + MODEL_TENSOR.ROPE_FACTORS_LONG, + MODEL_TENSOR.ROPE_FACTORS_SHORT, MODEL_TENSOR.ATTN_NORM, MODEL_TENSOR.ATTN_QKV, MODEL_TENSOR.ATTN_Q, diff --git a/gguf-py/gguf/tensor_mapping.py b/gguf-py/gguf/tensor_mapping.py index 3ff70cd7..9688b02c 100644 --- a/gguf-py/gguf/tensor_mapping.py +++ b/gguf-py/gguf/tensor_mapping.py @@ -82,6 +82,9 @@ class TensorNameMap: "rope.freqs", # llama-pth "rotary_pos_emb.inv_freq", # chatglm ), + + MODEL_TENSOR.ROPE_FACTORS_LONG: (), + MODEL_TENSOR.ROPE_FACTORS_SHORT: (), } block_mappings_cfg: dict[MODEL_TENSOR, tuple[str, ...]] = { |