Hugging Face's logo

ibm
/
merlinite-7b

Text Generation
Transformers
Safetensors
English
mistral
merlinite
ibm
lab
labrador
labradorite
text-generation-inference
Inference Endpoints
Model card Files Community
4
shivs commited on
Commit
540edb7
•
1 Parent(s): 3dd011c

Updating README.md with yaml and tags

Browse files
Files changed (1) hide show
  1. README.md +23 -6
README.md CHANGED
@@ -1,3 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # Model Card for Merlinite 7b
2
 
3
  ### Overview
@@ -8,12 +25,12 @@
8
 
9
  | Model | Alignment | Base | Teacher | MTBench (Avg) * | MMLU(5-shot) | ARC-C(25-shot) | HellaSwag(10-shot) | Winogrande(5-shot) | GSM8K(5-shot- strict) |
10
  | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
11
- | https://huggingface.co/meta-llama/Llama-2-13b-chat-hf | RLHF | Llama-2-13b | Human Annotators | 6.65 | 54.58 | 59.81 | 82.52 | 75.93 | 34.80 |
12
- | https://huggingface.co/microsoft/Orca-2-13b | Progressive Training | Llama-2-13b | GPT-4 | 6.15 | 60.37 * | 59.73 | 79.86 | 78.22 | 48.22 |
13
- | https://huggingface.co/WizardLM/WizardLM-13B-V1.2 | Evol-Instruct | Llama-2-13b | GPT-4 | 7.20 | 54.83 | 60.24 | 82.62 | 76.40 | 43.75 |
14
- | https://huggingface.co/ibm/labradorite-13b | Large-scale Alignment for chatBots (LAB) | Llama-2-13b | Mixtral-8x7B-Instruct | 7.25 | 58.89 | 61.69 | 83.15 | 79.56 | 40.11 |
15
- | https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1 | SFT | Mistral-7B-v0.1 | - | 6.84 | 60.37 | 63.65 | 84.76 | 76.80 | 41.85 |
16
- | https://huggingface.co/HuggingFaceH4/zephyr-7b-beta | SFT/DPO | Mistral-7B-v0.1 | GPT-4 | 7.34 | 61.07 | 63.74 | 84.19 | 78.06 | 34.04 |
17
  | Merlinite-7b | Large-scale Alignment for chatBots (LAB) | Mistral-7B-v0.1 | Mixtral-8x7B-Instruct | 7.71 | 64.88 | 63.99 | 84.37 | 78.24 | 44.58 |
18
 
19
  [*] Numbers for models other than Merlinite-7b and [Labradorite-13b](https://huggingface.co/ibm/labradorite-13b) (ours) are taken from [lmsys/chatbot-arena-leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard)
 
1
+
2
+ ---
3
+ pipeline_tag: text-generation
4
+ tags:
5
+ - merlinite
6
+ - mistral
7
+ - ibm
8
+ - lab
9
+ - labrador
10
+ - labradorite
11
+ license: apache-2.0
12
+ language:
13
+ - en
14
+ base_model: mistralai/Mistral-7B-v0.1
15
+ ---
16
+
17
+
18
  # Model Card for Merlinite 7b
19
 
20
  ### Overview
 
25
 
26
  | Model | Alignment | Base | Teacher | MTBench (Avg) * | MMLU(5-shot) | ARC-C(25-shot) | HellaSwag(10-shot) | Winogrande(5-shot) | GSM8K(5-shot- strict) |
27
  | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
28
+ | [Llama-2-13b-chat-hf](https://huggingface.co/meta-llama/Llama-2-13b-chat-hf) | RLHF | Llama-2-13b | Human Annotators | 6.65 | 54.58 | 59.81 | 82.52 | 75.93 | 34.80 |
29
+ | [Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) | Progressive Training | Llama-2-13b | GPT-4 | 6.15 | 60.37 * | 59.73 | 79.86 | 78.22 | 48.22 |
30
+ | [WizardLM-13B-V1.2](https://huggingface.co/WizardLM/WizardLM-13B-V1.2) | Evol-Instruct | Llama-2-13b | GPT-4 | 7.20 | 54.83 | 60.24 | 82.62 | 76.40 | 43.75 |
31
+ | [Labradorite-13b](https://huggingface.co/ibm/labradorite-13b) | Large-scale Alignment for chatBots (LAB) | Llama-2-13b | Mixtral-8x7B-Instruct | 7.25 | 58.89 | 61.69 | 83.15 | 79.56 | 40.11 |
32
+ | [Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) | SFT | Mistral-7B-v0.1 | - | 6.84 | 60.37 | 63.65 | 84.76 | 76.80 | 41.85 |
33
+ | [zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) | SFT/DPO | Mistral-7B-v0.1 | GPT-4 | 7.34 | 61.07 | 63.74 | 84.19 | 78.06 | 34.04 |
34
  | Merlinite-7b | Large-scale Alignment for chatBots (LAB) | Mistral-7B-v0.1 | Mixtral-8x7B-Instruct | 7.71 | 64.88 | 63.99 | 84.37 | 78.24 | 44.58 |
35
 
36
  [*] Numbers for models other than Merlinite-7b and [Labradorite-13b](https://huggingface.co/ibm/labradorite-13b) (ours) are taken from [lmsys/chatbot-arena-leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard)