Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
library_name: transformers
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
model-index:
|
| 6 |
+
- name: Rubra-Phi-3-mini-128k-instruct
|
| 7 |
+
results:
|
| 8 |
+
- task:
|
| 9 |
+
type: text-generation
|
| 10 |
+
dataset:
|
| 11 |
+
type: MMLU
|
| 12 |
+
name: MMLU
|
| 13 |
+
metrics:
|
| 14 |
+
- type: 5-shot
|
| 15 |
+
value: 66.66
|
| 16 |
+
verified: false
|
| 17 |
+
- task:
|
| 18 |
+
type: text-generation
|
| 19 |
+
dataset:
|
| 20 |
+
type: GPQA
|
| 21 |
+
name: GPQA
|
| 22 |
+
metrics:
|
| 23 |
+
- type: 0-shot
|
| 24 |
+
value: 29.24
|
| 25 |
+
verified: false
|
| 26 |
+
- task:
|
| 27 |
+
type: text-generation
|
| 28 |
+
dataset:
|
| 29 |
+
type: GSM-8K
|
| 30 |
+
name: GSM-8K
|
| 31 |
+
metrics:
|
| 32 |
+
- type: 8-shot, CoT
|
| 33 |
+
value: 74.09
|
| 34 |
+
verified: false
|
| 35 |
+
- task:
|
| 36 |
+
type: text-generation
|
| 37 |
+
dataset:
|
| 38 |
+
type: MATH
|
| 39 |
+
name: MATH
|
| 40 |
+
metrics:
|
| 41 |
+
- type: 4-shot, CoT
|
| 42 |
+
value: 26.84
|
| 43 |
+
verified: false
|
| 44 |
+
- task:
|
| 45 |
+
type: text-generation
|
| 46 |
+
dataset:
|
| 47 |
+
type: MT-bench
|
| 48 |
+
name: MT-bench
|
| 49 |
+
metrics:
|
| 50 |
+
- type: GPT-4 as Judge
|
| 51 |
+
value: 7.45
|
| 52 |
+
verified: false
|
| 53 |
+
tags:
|
| 54 |
+
- function-calling
|
| 55 |
+
- tool-calling
|
| 56 |
+
- agentic
|
| 57 |
+
- rubra
|
| 58 |
+
- conversational
|
| 59 |
+
language:
|
| 60 |
+
- en
|
| 61 |
+
---
|
| 62 |
+
|
| 63 |
+
# Rubra Phi-3 Mini 128k Instruct
|
| 64 |
+
|
| 65 |
+
Original model: [rubra-ai/Phi-3-mini-128k-instruct](https://huggingface.co/rubra-ai/Phi-3-mini-128k-instruct)
|
| 66 |
+
|
| 67 |
+
## Model description
|
| 68 |
+
The model is the result of further post-training [microsoft/Phi-3-mini-128k-instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
|
| 69 |
+
|
| 70 |
+
## Training Data
|
| 71 |
+
The model underwent additional training on a proprietary dataset encompassing diverse instruction-following, chat, and function calling data. This post-training process enhances the model's ability to integrate tools and manage complex interaction scenarios effectively.
|
| 72 |
+
|
| 73 |
+
## How to use
|
| 74 |
+
Refer to https://docs.rubra.ai/inference/llamacpp for usage. Feel free to ask/open issues up in our Github repo: https://github.com/rubra-ai/rubra
|