github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4823] I encountered this error when converting the Tongyi-Finance-14B-Chat-Int4-AWQ model #65084

New Issue
Open
opened 2026-05-03 19:43:16 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-05-03 19:43:16 -05:00
Owner
Copy Link

Originally created by @wangkai111111 on GitHub (Jun 5, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4823

What is the issue?

(.venv) [root@bastion ollama]# python llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin INFO:hf-to-gguf:Loading model: model INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only INFO:hf-to-gguf:Set model parameters INFO:hf-to-gguf:Set model tokenizer Traceback (most recent call last): File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in <module> main() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2850, in main model_instance.set_vocab() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1592, in set_vocab self._set_vocab_qwen() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 530, in _set_vocab_qwen assert len(merged) == 2 AssertionError

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.1.41

Originally created by @wangkai111111 on GitHub (Jun 5, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4823 ### What is the issue? `(.venv) [root@bastion ollama]# python llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin INFO:hf-to-gguf:Loading model: model INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only INFO:hf-to-gguf:Set model parameters INFO:hf-to-gguf:Set model tokenizer Traceback (most recent call last): File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in <module> main() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2850, in main model_instance.set_vocab() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 1592, in set_vocab self._set_vocab_qwen() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 530, in _set_vocab_qwen assert len(merged) == 2 AssertionError ` ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.41
GiteaMirror added the bug label 2026-05-03 19:43:16 -05:00
GiteaMirror commented 2026-05-03 19:43:18 -05:00
Author
Owner
Copy Link

@wangkai111111 commented on GitHub (Jun 5, 2024):

I changedlen(merged) == 2tolen(merged) >= 2This error appeared again. Please help.

`(.venv) [root@bastion ollama]# python llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin

INFO:hf-to-gguf:Loading model: model
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Adding 153463 merge(s).
INFO:gguf.vocab:Setting special token type bos to 153719
INFO:gguf.vocab:Setting special token type eos to 153719
INFO:gguf.vocab:Setting special token type unk to 153719
INFO:hf-to-gguf:Exporting model to 'converted.bin'
INFO:hf-to-gguf:gguf: loading model part 'model.safetensors'
INFO:hf-to-gguf:output.weight, torch.bfloat16 --> F16, shape = {5120, 154112}
INFO:hf-to-gguf:blk.0.attn_qkv.bias, torch.float16 --> F32, shape = {15360}
Traceback (most recent call last):
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in
main()
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2859, in main
model_instance.write()
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 325, in write
self.write_tensors()
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 262, in write_tensors
for new_name, data in ((n, d.squeeze().numpy()) for n, d in self.modify_tensors(data_torch, name, bid)):
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 229, in modify_tensors
return [(self.map_tensor_name(name), data_torch)]
File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 180, in map_tensor_name
raise ValueError(f"Can not map tensor {name!r}")
ValueError: Can not map tensor 'transformer.h.0.attn.c_attn.qweight'
`

<!-- gh-comment-id:2148748974 --> @wangkai111111 commented on GitHub (Jun 5, 2024): I changed`len(merged) == 2`to`len(merged) >= 2`This error appeared again. Please help. `(.venv) [root@bastion ollama]# python llm/llama.cpp/convert-hf-to-gguf.py ./model --outtype f16 --outfile converted.bin INFO:hf-to-gguf:Loading model: model INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only INFO:hf-to-gguf:Set model parameters INFO:hf-to-gguf:Set model tokenizer INFO:gguf.vocab:Adding 153463 merge(s). INFO:gguf.vocab:Setting special token type bos to 153719 INFO:gguf.vocab:Setting special token type eos to 153719 INFO:gguf.vocab:Setting special token type unk to 153719 INFO:hf-to-gguf:Exporting model to 'converted.bin' INFO:hf-to-gguf:gguf: loading model part 'model.safetensors' INFO:hf-to-gguf:output.weight, torch.bfloat16 --> F16, shape = {5120, 154112} INFO:hf-to-gguf:blk.0.attn_qkv.bias, torch.float16 --> F32, shape = {15360} Traceback (most recent call last): File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2865, in <module> main() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 2859, in main model_instance.write() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 325, in write self.write_tensors() File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 262, in write_tensors for new_name, data in ((n, d.squeeze().numpy()) for n, d in self.modify_tensors(data_torch, name, bid)): File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 229, in modify_tensors return [(self.map_tensor_name(name), data_torch)] File "/root/model/ollama/llm/llama.cpp/convert-hf-to-gguf.py", line 180, in map_tensor_name raise ValueError(f"Can not map tensor {name!r}") ValueError: Can not map tensor 'transformer.h.0.attn.c_attn.qweight' `
GiteaMirror commented 2026-05-03 19:43:18 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Jun 5, 2024):

@wangkai111111 I don't recognize that tensor name, so I'm not sure that architecture is supported. You may want to check w/ the llama.cpp folks to see if they are planning to support it.

<!-- gh-comment-id:2150925970 --> @pdevine commented on GitHub (Jun 5, 2024): @wangkai111111 I don't recognize that tensor name, so I'm not sure that architecture is supported. You may want to check w/ the llama.cpp folks to see if they are planning to support it.
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 Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#65084
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?