github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4349] The error occurred when running the fine-tuning trained Llama-3-8B-Instruct model #2712

New Issue
Closed
opened 2026-04-12 13:01:44 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 13:01:44 -05:00
Owner
Copy Link

Originally created by @zhangzhongpeng02 on GitHub (May 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4349

What is the issue?

I fine-tuning trained the Llama-3-8B-Instruct model and converting it to the UGFF model format. then run it by ollama,it's success,but errors happend when I send any msg,
the error:
time=2024-05-06T23:55:49.844+08:00 level=INFO source=server.go:829 msg="llm encode error: 500 Internal Server Error\ninvalid unordered_map<K, T> key"
time=2024-05-06T23:55:49.844+08:00 level=ERROR source=prompt.go:86 msg="failed to encode prompt" err="500 Internal Server Error\ninvalid unordered_map<K, T> key"

Then I tryed this:
1、The same error occurred when run the mode file which directly converting the original safetensors files of the Llama-3-8B-Instruct to the UGFF format.
2、I did the same operations on safetensors models such as qwen:14b-chat-v1.5, llama2-7b-chat, and Mistral-7B-Instruct, However, there were no errors！

OS

Windows

GPU

Nvidia

CPU

Intel

Ollama version

0.1.34

Originally created by @zhangzhongpeng02 on GitHub (May 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4349 ### What is the issue? I fine-tuning trained the Llama-3-8B-Instruct model and converting it to the UGFF model format. then run it by ollama,it's success,but errors happend when I send any msg, the error: time=2024-05-06T23:55:49.844+08:00 level=INFO source=server.go:829 msg="llm encode error: 500 Internal Server Error\ninvalid unordered_map<K, T> key" time=2024-05-06T23:55:49.844+08:00 level=ERROR source=prompt.go:86 msg="failed to encode prompt" err="500 Internal Server Error\ninvalid unordered_map<K, T> key" Then I tryed this: 1、The same error occurred when run the mode file which directly converting the original safetensors files of the Llama-3-8B-Instruct to the UGFF format. 2、I did the same operations on safetensors models such as qwen:14b-chat-v1.5, llama2-7b-chat, and Mistral-7B-Instruct, However, there were no errors！ ### OS Windows ### GPU Nvidia ### CPU Intel ### Ollama version 0.1.34
GiteaMirror added the bug label 2026-04-12 13:01:44 -05:00
GiteaMirror commented 2026-04-12 13:01:45 -05:00
Author
Owner
Copy Link

@zhangzhongpeng02 commented on GitHub (May 11, 2024):

The conversion operation refers to ”https://github.com/ollama/ollama/blob/main/docs/import.md“，and the commond is : python llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin
the modefile:
FROM converted.bin
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>

{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

{{ .Response }}<|eot_id|>"""
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER stop "<|reserved_special_token"

<!-- gh-comment-id:2105626729 --> @zhangzhongpeng02 commented on GitHub (May 11, 2024): The conversion operation refers to ”https://github.com/ollama/ollama/blob/main/docs/import.md“，and the commond is : python llm/llama.cpp/convert.py ./model --outtype f16 --outfile converted.bin the modefile: FROM converted.bin TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> {{ .Response }}<|eot_id|>""" PARAMETER stop "<|start_header_id|>" PARAMETER stop "<|end_header_id|>" PARAMETER stop "<|eot_id|>" PARAMETER stop "<|reserved_special_token"
GiteaMirror commented 2026-04-12 13:01:45 -05:00
Author
Owner
Copy Link

@yuanmenglong-cn commented on GitHub (Jun 27, 2024):

Have you solved this issue? I'm running into this issue as well :(

<!-- gh-comment-id:2193075882 --> @yuanmenglong-cn commented on GitHub (Jun 27, 2024): Have you solved this issue? I'm running into this issue as well :(
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#2712
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?