DeepSeek V4 (#24162)
* convert: add dsv4 conversion * add basic setup * add llm_graph_input_dsv4 * add save-load state * add sinkhorn eps - correction by @fairydreaming * add rope fix * cleanup dead code * fix bugs * support pro model: added by @fairydreaming * remove redundant V cache * Chat template * remove debugging leftovers * Add mechanism for inlining templates based on architecture * s/deepseek-v4-flash/deepseek4/g * s/deepseek-v4-flash/deepseek4/g continued * enable graph reuse * enable FA * fix test llama archs * rename * compatibility with antirez ds4 GGUFs * simplified set_gguf_parameters() by calling super class method, replaced moe.score_func with expert_gating_func. * reserve worst-case kv-cache * revert max split inputs * address review comments * add padding to enable FA * pad only the final value of plan.n_kv to 256 * remove built-in cpp chat template * cont: remove cpp built-in template * rm outdated test * replace ggml_view_3d() with ggml_reshape_3d() Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * only support n_seq=1 for now * remove unused var * cont: remove unused var * use scale bias * use correct ptr for can_reuse * remove gen-chat-inline-templates.py * simplify graph reuse * cont: cleanup * remove unused inputs * enable partial checkpointing * add correct shape for kq_mask + set llama_model_n_swa to 0 for dsv4 * precompute source_idx + add comment about dummy write * support multi-seq * remove restored_trim_pos * use split_equal when possible * fix indent * address review comments * use LLM_KV * fix ci --------- Co-authored-by: Piotr Wilkin <piotr.wilkin@syndatis.com> Co-authored-by: Stanisław Szymczyk <sszymczy@gmail.com> Co-authored-by: Xuan Son Nguyen <son@huggingface.co> Co-authored-by: fairydreaming <166155368+fairydreaming@users.noreply.github.com> Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Aman Gupta
co-authored by
Georgi Gerganov
Piotr Wilkin
Stanisław Szymczyk
Xuan Son Nguyen
fairydreaming
Georgi Gerganov
Piotr Wilkin
Stanisław Szymczyk
Xuan Son Nguyen
fairydreaming
parent
6cb18b2f2e
commit
8c146a8366
@@ -0,0 +1,112 @@
|
||||
{%- if not add_generation_prompt is defined -%}
|
||||
{%- set add_generation_prompt = false -%}
|
||||
{%- endif -%}
|
||||
{%- if not thinking is defined -%}
|
||||
{%- if enable_thinking is defined -%}
|
||||
{%- set thinking = enable_thinking -%}
|
||||
{%- else -%}
|
||||
{%- set thinking = false -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- set dsml_token = '｜DSML｜' -%}
|
||||
{%- set thinking_start_token = '<think>' -%}
|
||||
{%- set thinking_end_token = '</think>' -%}
|
||||
{%- set tools_header = '## Tools\n\nYou have access to a set of tools to help answer the user\'s question. You can invoke tools by writing a "<' + dsml_token + 'tool_calls>" block like the following:\n\n<' + dsml_token + 'tool_calls>\n<' + dsml_token + 'invoke name="$TOOL_NAME">\n<' + dsml_token + 'parameter name="$PARAMETER_NAME" string="true|false">$PARAMETER_VALUE</' + dsml_token + 'parameter>\n...\n</' + dsml_token + 'invoke>\n<' + dsml_token + 'invoke name="$TOOL_NAME2">\n...\n</' + dsml_token + 'invoke>\n</' + dsml_token + 'tool_calls>\n\nString parameters should be specified as is and set `string="true"`. For all other types (numbers, booleans, arrays, objects), pass the value in JSON format and set `string="false"`.\n\nIf thinking_mode is enabled (triggered by ' + thinking_start_token + '), you MUST output your complete reasoning inside ' + thinking_start_token + '...' + thinking_end_token + ' BEFORE any tool calls or final response.\n\nOtherwise, output directly after ' + thinking_end_token + ' with tool calls or final response.\n\n### Available Tool Schemas\n\n' -%}
|
||||
{%- set tools_footer = '\nYou MUST strictly follow the above defined tool name and parameter schemas to invoke tool calls.\n' -%}
|
||||
{%- set ns = namespace(system_prompt='', is_first_sp=true) -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message['role'] == 'system' -%}
|
||||
{%- if ns.is_first_sp -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + (message['content'] or '') -%}
|
||||
{%- set ns.is_first_sp = false -%}
|
||||
{%- else -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + (message['content'] or '') -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- if tools is defined and tools -%}
|
||||
{%- set ts = namespace(schemas='') -%}
|
||||
{%- for tool in tools -%}
|
||||
{%- if tool['type'] == 'function' -%}
|
||||
{%- set ts.schemas = ts.schemas + (tool['function'] | tojson) + '\n' -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- if ns.system_prompt -%}
|
||||
{%- set ns.system_prompt = ns.system_prompt + '\n\n' + tools_header + ts.schemas + tools_footer -%}
|
||||
{%- else -%}
|
||||
{%- set ns.system_prompt = tools_header + ts.schemas + tools_footer -%}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
{{- bos_token -}}
|
||||
{{- ns.system_prompt -}}
|
||||
{%- set last_user_idx = namespace(value=-1) -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message['role'] == 'user' or message['role'] == 'developer' or message['role'] == 'tool' -%}
|
||||
{%- set last_user_idx.value = loop.index0 -%}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- set state = namespace(in_user=false) -%}
|
||||
{%- for message in messages -%}
|
||||
{%- if message['role'] == 'user' or message['role'] == 'developer' -%}
|
||||
{%- if state.in_user -%}
|
||||
{{- '\n\n' -}}
|
||||
{%- else -%}
|
||||
{{- '<｜User｜>' -}}
|
||||
{%- set state.in_user = true -%}
|
||||
{%- endif -%}
|
||||
{{- message['content'] or '' -}}
|
||||
{%- elif message['role'] == 'tool' -%}
|
||||
{%- if state.in_user -%}
|
||||
{{- '\n\n' -}}
|
||||
{%- else -%}
|
||||
{{- '<｜User｜>' -}}
|
||||
{%- set state.in_user = true -%}
|
||||
{%- endif -%}
|
||||
{{- '<tool_result>' + (message['content'] or '') + '</tool_result>' -}}
|
||||
{%- elif message['role'] == 'assistant' -%}
|
||||
{%- set state.in_user = false -%}
|
||||
{{- '<｜Assistant｜>' -}}
|
||||
{%- set is_after_last_user = loop.index0 > last_user_idx.value -%}
|
||||
{%- if is_after_last_user and thinking -%}
|
||||
{{- thinking_start_token -}}
|
||||
{%- if message['reasoning_content'] is defined and message['reasoning_content'] -%}
|
||||
{{- message['reasoning_content'] -}}
|
||||
{%- endif -%}
|
||||
{{- thinking_end_token -}}
|
||||
{%- else -%}
|
||||
{{- thinking_end_token -}}
|
||||
{%- endif -%}
|
||||
{%- if message['content'] is defined and message['content'] -%}
|
||||
{{- message['content'] -}}
|
||||
{%- endif -%}
|
||||
{%- if message['tool_calls'] -%}
|
||||
{{- '\n\n<' + dsml_token + 'tool_calls>\n' -}}
|
||||
{%- for tool in message['tool_calls'] -%}
|
||||
{%- set func = tool['function'] -%}
|
||||
{{- '<' + dsml_token + 'invoke name="' + func['name'] + '">\n' -}}
|
||||
{%- set args = func['arguments'] -%}
|
||||
{%- if args is string -%}
|
||||
{%- set args = args | from_json -%}
|
||||
{%- endif -%}
|
||||
{%- for key, val in args.items() -%}
|
||||
{%- if val is string -%}
|
||||
{{- '<' + dsml_token + 'parameter name="' + key + '" string="true">' + val + '</' + dsml_token + 'parameter>\n' -}}
|
||||
{%- else -%}
|
||||
{{- '<' + dsml_token + 'parameter name="' + key + '" string="false">' + (val | tojson) + '</' + dsml_token + 'parameter>\n' -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{{- '</' + dsml_token + 'invoke>\n' -}}
|
||||
{%- endfor -%}
|
||||
{{- '</' + dsml_token + 'tool_calls>' -}}
|
||||
{%- endif -%}
|
||||
{{- '<｜end▁of▁sentence｜>' -}}
|
||||
{%- endif -%}
|
||||
{%- endfor -%}
|
||||
{%- if add_generation_prompt -%}
|
||||
{{- '<｜Assistant｜>' -}}
|
||||
{%- if thinking -%}
|
||||
{{- thinking_start_token -}}
|
||||
{%- else -%}
|
||||
{{- thinking_end_token -}}
|
||||
{%- endif -%}
|
||||
{%- endif -%}
|
||||
Reference in New Issue
Block a user