github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-11-12 03:46:14 -06:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #1361] Add support for gpt4-x-alpaca #713

New Issue
Open
opened 2026-04-12 10:22:58 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 10:22:58 -05:00
Owner
Copy Link
Copy Source

Originally created by @priamai on GitHub (Dec 3, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1361

Hi there,
this is an amazing model:
https://huggingface.co/chavinlo/gpt4-x-alpaca
Cheers.

Originally created by @priamai on GitHub (Dec 3, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1361 Hi there, this is an amazing model: https://huggingface.co/chavinlo/gpt4-x-alpaca Cheers.
GiteaMirror added the model label 2026-04-12 10:22:58 -05:00
GiteaMirror commented 2026-04-12 10:22:59 -05:00
Author
Owner
Copy Link
Copy Source

@technovangelist commented on GitHub (Dec 21, 2023):

This model appears to be no longer supported by llamacpp:

matt@matt:~/llama.cpp$ python3 convert.py ~/chavinlo_gpt4-x-alpaca
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00001-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00001-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00002-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00003-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00004-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00005-of-00006.bin
Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00006-of-00006.bin
params = Params(n_vocab=32001, n_embd=5120, n_layer=40, n_ctx=2048, n_ff=13824, n_head=40, n_head_kv=40, n_experts=None, n_experts_used=None, f_norm_eps=1e-06, rope_scaling_type=None, f_rope_freq_base=None, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=None, path_model=PosixPath('/home/matt/chavinlo_gpt4-x-alpaca'))
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
32000 32000
Vocab info: <VocabLoader with 32000 base tokens and 1 added tokens>
Traceback (most recent call last):
  File "/home/matt/llama.cpp/convert.py", line 1279, in <module>
    main()
  File "/home/matt/llama.cpp/convert.py", line 1259, in main
    special_vocab = gguf.SpecialVocab(model_plus.paths[0].parent,
  File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 33, in __init__
    self._load(Path(path))
  File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 79, in _load
    self._try_load_from_config_json(path)
  File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 184, in _try_load_from_config_json
    self._set_special_token(typ, config.get(f'{typ}_token_id'))
  File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 115, in _set_special_token
    raise ValueError(f'invalid value for special token type {typ}: {tid}')
ValueError: invalid value for special token type pad: -1
<!-- gh-comment-id:1866666253 --> @technovangelist commented on GitHub (Dec 21, 2023): This model appears to be no longer supported by llamacpp: ``` matt@matt:~/llama.cpp$ python3 convert.py ~/chavinlo_gpt4-x-alpaca Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00001-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00001-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00002-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00003-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00004-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00005-of-00006.bin Loading model file /home/matt/chavinlo_gpt4-x-alpaca/pytorch_model-00006-of-00006.bin params = Params(n_vocab=32001, n_embd=5120, n_layer=40, n_ctx=2048, n_ff=13824, n_head=40, n_head_kv=40, n_experts=None, n_experts_used=None, f_norm_eps=1e-06, rope_scaling_type=None, f_rope_freq_base=None, f_rope_scale=None, n_orig_ctx=None, rope_finetuned=None, ftype=None, path_model=PosixPath('/home/matt/chavinlo_gpt4-x-alpaca')) None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used. You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565 32000 32000 Vocab info: <VocabLoader with 32000 base tokens and 1 added tokens> Traceback (most recent call last): File "/home/matt/llama.cpp/convert.py", line 1279, in <module> main() File "/home/matt/llama.cpp/convert.py", line 1259, in main special_vocab = gguf.SpecialVocab(model_plus.paths[0].parent, File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 33, in __init__ self._load(Path(path)) File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 79, in _load self._try_load_from_config_json(path) File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 184, in _try_load_from_config_json self._set_special_token(typ, config.get(f'{typ}_token_id')) File "/home/matt/llama.cpp/gguf-py/gguf/vocab.py", line 115, in _set_special_token raise ValueError(f'invalid value for special token type {typ}: {tid}') ValueError: invalid value for special token type pad: -1 ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No labels model
Milestone
No items
No Milestone
Projects
Clear projects
No projects
Assignees
Clear assignees
GiteaMirror ninjasurge (Kaehlen Rog)
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#713