NousResearch/Hermes-3-Llama-3.1-70B Korean q5 model with CPT->SFT->DPO

Tools 70B

Updated 13 days ago

13 days ago

e2fd002bd260 · 50GB

model
llama
·
70.6B
·
Q5_K_M
system
You are Linkbricks Horizon AI (링크브릭스 호라이즌 AI) , acting as an heplful assistant.
template
{{ if .Messages }} {{- if or .System .Tools }}<|im_start|>system {{ .System }} {{- if .Tools }} You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags. You may call one or more functions to assist with the user query. Don't make assumptions about what values to plug into functions. Here are the available tools: <tools> {{- range .Tools }} {{ json . }} {{- end }} </tools> For each function call return a JSON object, with the following pydantic model json schema for each: {'title': 'FunctionCall', 'type': 'object', 'properties': {'arguments': {'title': 'Arguments', 'type': 'object'}, 'name': {'title': 'Name', 'type': 'string'}}, 'required': ['arguments', 'name']} Each function call should be enclosed within <tool_call> </tool_call> XML tags. <tool_call> {'name': <function-name>, 'arguments': <args-dict>} </tool_call> {{- end }}<|im_end|> {{- end }} {{- $hasToolResponses := false }} {{- range .Messages }} {{- if eq .Role "tool" }} {{- if not $hasToolResponses }} <|im_start|>tool {{- $hasToolResponses = true }} {{- end }} <tool_response> {{ .Content }} </tool_response> {{- else }} {{- if $hasToolResponses }}<|im_end|> {{- $hasToolResponses = false }} {{- end }} <|im_start|>{{ .Role }} {{- if and (eq .Role "assistant") .ToolCalls }} <tool_call> {{- range .ToolCalls }} {"name": "{{ .Function.Name }}", "arguments": {{ .Function.Arguments }}} {{- end }} </tool_call> {{- else }} {{ .Content }} {{- end }}<|im_end|> {{- end }} {{- end }} {{- if $hasToolResponses }}<|im_end|> {{- end }} <|im_start|>assistant {{ else }} {{- if .System }} <|im_start|>system {{ .System }}<|im_end|> {{- end }} {{- if .Prompt }} <|im_start|>user {{ .Prompt }}<|im_end|> {{- end }} <|im_start|>assistant {{ .Response }}<|im_end|> {{- end }}
params
{"num_keep":50,"stop":["<|im_start|>","<|im_end|>","<|eot_id|>","<|begin_of_text|>","<|end_of_text|>"]}

Readme

linkbricks.png

AI 와 빅데이터 분석 전문 기업인 Linkbricks의 데이터사이언티스트인 지윤성(Saxo) 이사가

Hermes-3-Llama-3.1-70B 베이스모델을 사용해서 H100-80G 8개를 통해 CPT(Continue-Pretraining)->SFT->DPO 한 한글 언어 모델

천만건의 한글 뉴스 코퍼스를 기준으로 다양한 테스크별 한국어-중국어-영어-일본어 교차 학습 데이터와 수학 및 논리판단 데이터를 통하여 한중일영 언어 교차 증강 처리와 복잡한 논리 문제 역시 대응 가능하도록 훈련한 모델이다.

-토크나이저는 단어 확장 없이 베이스 모델 그대로 사용

-고객 리뷰나 소셜 포스팅 고차원 분석 및 코딩과 작문, 수학, 논리판단 등이 강화된 모델

-128k-Context Window

-한글 Function Call 및 Tool Calling 지원

-Deepspeed Stage=3, rslora 및 BAdam Layer Mode 사용


Finetuned by Mr. Yunsung Ji (Saxo), a data scientist at Linkbricks, a company specializing in AI and big data analytics

CPT(Continue-Pretraining)->SFT->DPO training model based on Hermes-3-Llama-3.1-70B through 8 H100-80Gs as a Korean language model

It is a model that has been trained to handle Korean-Chinese-English-Japanese cross-training data and 10M korean news corpus and logic judgment data for various tasks to enable cross-fertilization processing and complex Korean logic & math problems.

-Tokenizer uses the base model without word expansion

-Models enhanced with high-dimensional analysis of customer reviews and social posts, as well as coding, writing, amth and decision making

-128k-Context Window

-Deepspeed Stage=3, use rslora and BAdam Layer Mode



www.linkbricks.com, www.linkbricks.vc