add function call parser for DeepSeek V3#5054
add function call parser for DeepSeek V3#5054finger92 wants to merge 73 commits intosgl-project:mainfrom
Conversation
|
great work,let me check it,please wait for a moment :-) |
thanks for replying, actually I found some bugs here. I will update this PR later. |
@finger92 I found the deepseek.jinja and function_call_parser.py has many chinese character, such as <|tool▁calls▁begin|>, <|tool▁sep|> etc. |
you are right, you can also see them in the tokenizor.json for deepseek model |
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com> Co-authored-by: laixinn <xielx@shanghaitech.edu.cn>
…l-project#5050) Co-authored-by: Qingquan Song <ustcsqq@gmail.com> Co-authored-by: Chunan Zeng <zcnrex@gmail.com>
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: laixinn <xielx@shanghaitech.edu.cn> Co-authored-by: sleepcoo <sleepcoo@gmail.com> Co-authored-by: zhyncs <me@zhyncs.com>
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com> Co-authored-by: Shangming Cai <caishangming@linux.alibaba.com> Co-authored-by: Xuchun Shang <xuchun.shang@linux.alibaba.com> Co-authored-by: shangmingc <csmthu@gmail.com>
|
@finger92 Why did you turn this pr off? |
Motivation
support function call for deepseek model issued by #4379
Modifications
add deepseek v3 function call parser
Checklist
validation steps
environment:
H20 * 8
deepseek.jinja
Attention
and I cant find token with id "129279" in deepseek model's tokenizor.json. but this work fine with "outlines", so I add "--grammar-backend outlines" to launch cmd.
3. use a smaller temperature. I found that the default temperature will cause model output unstable for function calling