diff options
| author | ningshanwutuobang <ningshanwutuobang@gmail.com> | 2023-06-28 23:53:37 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-28 18:53:37 +0300 |
| commit | cfa0750bc9dbc2d957a91b8ed09ab0035d8f3d4e (patch) | |
| tree | c8d6d6e6548d4f03899704f64bce6939e471e4e6 /convert-lora-to-ggml.py | |
| parent | 9d23589d638dc74577d5ff880e6d4248b795f12e (diff) | |
llama : support input embeddings directly (#1910)
* add interface for float input
* fixed inpL shape and type
* add examples of input floats
* add test example for embd input
* fixed sampling
* add free for context
* fixed add end condition for generating
* add examples for llava.py
* add READMD for llava.py
* add READMD for llava.py
* add example of PandaGPT
* refactor the interface and fixed the styles
* add cmake build for embd-input
* add cmake build for embd-input
* Add MiniGPT-4 example
* change the order of the args of llama_eval_internal
* fix ci error
Diffstat (limited to 'convert-lora-to-ggml.py')
| -rw-r--r-- | convert-lora-to-ggml.py | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/convert-lora-to-ggml.py b/convert-lora-to-ggml.py index 9090e8d..f43c836 100644 --- a/convert-lora-to-ggml.py +++ b/convert-lora-to-ggml.py @@ -113,6 +113,10 @@ with open(output_path, "wb") as fout: write_file_header(fout, params) for k, v in model.items(): + if k.endswith(".default.weight"): + k = k.replace(".default.weight", ".weight") + if k in ["llama_proj.weight", "llama_proj.bias"]: + continue if k.endswith("lora_A.weight"): if v.dtype != torch.float16 and v.dtype != torch.float32: v = v.float() @@ -120,7 +124,7 @@ with open(output_path, "wb") as fout: else: v = v.float() - t = v.numpy() + t = v.detach().numpy() tname = translate_tensor_name(k) print(f"{k} => {tname} {t.shape} {t.dtype} {t.nbytes/1024/1024:.2f}MB") write_tensor_header(fout, tname, t.shape, t.dtype) |