Updated 5 months ago
5 months ago
98385f12a848 · 3.0GB
model
archinternlm2
·
parameters7.74B
·
quantizationQ2_K
3.0GB
params
{ "stop": [ "<|eot_id|>" ], "temperature": 0 }
50B
system
Determine whether the provided claim is consistent with the corresponding document. Consistency in t
340B
template
{{- if .Messages }} {{- range $i, $_ := .Messages }} {{- $last := eq (len (slice $.Messages $i)) 1 -
506B
讀我檔案
這是一個由 Bespoke Labs 開發的基於事實依據的事實查核模型。
此模型接收文件(文本)和句子作為輸入,並判斷該句子是否受文件支持。為了事實查核多句聲明,應首先將聲明分解為句子。除非文件超過 32K 個 tokens,否則無需將文件分塊。
Bespoke-MiniCheck 雖然體積小巧,但仍是最先進的事實查核模型。
用法
提示範本如下:
Document: {document}
Claim: {claim}
回應將為 Yes
或 No
。
範例
提示
Document: A group of students gather in the school library to study for their upcoming final exams.
Claim: The students are preparing for an examination.
回應
Yes
提示
Document: A group of students gather in the school library to study for their upcoming final exams.
Claim: The students are on vacation.
回應
No
模型效能
這些模型的效能是在我們新收集的基準測試(模型在訓練期間未見過)LLM-AggreFact 上評估的,該基準測試來自 11 個最近人工註釋的事實查核和 grounding LLM 生成的數據集。Bespoke-MiniCheck-7B 雖然體積小巧,但仍是最先進的事實查核模型。