teknium commited on
Commit
8408f90
1 Parent(s): 64205a5

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -5
README.md CHANGED
@@ -10,13 +10,15 @@ license:
10
  - mit
11
  ---
12
 
13
- # Model Card: Nous-Hermes-Llama2-7b
14
 
15
  Compute provided by our project sponsor Redmond AI, thank you! Follow RedmondAI on Twitter @RedmondAI.
16
 
17
  ## Model Description
18
 
19
- Nous-Hermes-Llama2-7b is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.
 
 
20
 
21
  This Hermes model uses the exact same dataset as Hermes on Llama-1. This is to ensure consistency between the old Hermes and new, for anyone who wanted to keep Hermes as similar to the old one, just more capable.
22
 
@@ -73,9 +75,6 @@ or
73
 
74
  ```
75
 
76
- ## Benchmark Results
77
- Coming soon
78
-
79
  ## Resources for Applied Use Cases:
80
  For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
81
  For an example of a roleplaying discord chatbot, check out this: https://github.com/teknium1/alpaca-roleplay-discordbot
 
10
  - mit
11
  ---
12
 
13
+ # Model Card: Nous-Hermes-Llama2-7b GGML
14
 
15
  Compute provided by our project sponsor Redmond AI, thank you! Follow RedmondAI on Twitter @RedmondAI.
16
 
17
  ## Model Description
18
 
19
+ Nous-Hermes-Llama2-7b-GGML is a state-of-the-art language model fine-tuned on over 300,000 instructions. This model was fine-tuned by Nous Research, with Teknium leading the fine tuning process and dataset curation, Redmond AI sponsoring the compute, and several other contributors.
20
+
21
+ GGML Models can be used to run quantized models in llama.cpp.
22
 
23
  This Hermes model uses the exact same dataset as Hermes on Llama-1. This is to ensure consistency between the old Hermes and new, for anyone who wanted to keep Hermes as similar to the old one, just more capable.
24
 
 
75
 
76
  ```
77
 
 
 
 
78
  ## Resources for Applied Use Cases:
79
  For an example of a back and forth chatbot using huggingface transformers and discord, check out: https://github.com/teknium1/alpaca-discord
80
  For an example of a roleplaying discord chatbot, check out this: https://github.com/teknium1/alpaca-roleplay-discordbot