Misaka27260

/

Qwen2.5-VL-7B-Instruct-abliterated-GGUF

like 2

Q4_K_M works fine here.

Try delete the old version of mmproj gguf file.The old version used Qwen2vl-7b's mmproj gguf file.

I used the latest mmproj-Qwen2.5-VL-7B-Instruct.gguf
MD5: 8a37d9b4b86445b8349b6ab4349f4553
Qwen2.5-VL-7B-Instruct-abliterated-F16Out-Q4_K_M.gguf
MD5: a70176aa524a912854b9629f9e359a5e
(LMStudio 0.3.15.11)
I can upload images but it gives error: the model does not support images, try a model that support images

I've tried your deleted models Qwen2.5-VL-7B-Instruct-abliterated-F16Out-Q6_K.gguf
same
which version of LMStudio are you using?
can you check MD5 of the mmproj?

Also, I have gemma3 12b vision models and several others that work fine with (LMStudio 0.3.15.11)

名称: mmproj-Qwen2.5-VL-7B-Instruct.gguf
大小: 1354163328 字节 : 1291 MiB
MD5: 8a37d9b4b86445b8349b6ab4349f4553
名称: Qwen2.5-VL-7B-Instruct-abliterated-F16Out-Q4_K_M.gguf
大小: 5326000064 字节 : 5079 MiB
MD5: a70176aa524a912854b9629f9e359a5e

template jinja (i believe it is default):
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0]['role'] == 'system' %}
{{- messages[0]['content'] }}
{%- else %}
{{- 'You are a helpful assistant.' }}
{%- endif %}
{{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{"name": , "arguments": }\n<|im_end|>\n" }}
{%- else %}
{%- if messages[0]['role'] == 'system' %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- for message in messages %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{{- '<|im_start|>' + message.role }}
{%- if message.content %}
{{- '\n' + message.content }}
{%- endif %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '\n\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{{- tool_call.arguments | tojson }}
{{- '}\n' }}
{%- endfor %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n\n' }}
{{- message.content }}
{{- '\n' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

Have you ever upgraded your runtime environment?V12.9.0 supports Qwen2.5VL.

updating to 1.29 (beta) solved the problem, thanks... pls add this to Read.me
Because 1.29 is BETA and not visible by default