Hugging Face's logo

togethercomputer
/
Llama-2-7B-32K-Instruct

Text Generation
Transformers
PyTorch
English
llama
text-generation-inference
Inference Endpoints
Model card Files Community
20
yuchenglu commited on
Commit
35696b9
•
1 Parent(s): 4d80166

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -135,7 +135,7 @@ We summarize the results below:
135
  * Accuracy over MQA
136
  | Model | 20 docs (Avg 2.9K tokens) | 30 docs (Avg 4.4K tokens) | 50 docs (Avg 7.4K tokens) |
137
  | -------- | ------- | ------- | ------- |
138
- | Llama-2-7B-Chat-hf | 0.384 | 0.375 | 0.313 |
139
  | Longchat-7b-16k | 0.510 | 0.473 | 0.428 |
140
  | Longchat-7b-v1.5-32k | 0.534 | 0.516 | 0.479 |
141
  | GPT-3.5-Turbo-16K | 0.622 | 0.609 | 0.577 |
 
135
  * Accuracy over MQA
136
  | Model | 20 docs (Avg 2.9K tokens) | 30 docs (Avg 4.4K tokens) | 50 docs (Avg 7.4K tokens) |
137
  | -------- | ------- | ------- | ------- |
138
+ | Llama-2-7B-Chat-hf | 0.448 | 0.421 | 0.354 |
139
  | Longchat-7b-16k | 0.510 | 0.473 | 0.428 |
140
  | Longchat-7b-v1.5-32k | 0.534 | 0.516 | 0.479 |
141
  | GPT-3.5-Turbo-16K | 0.622 | 0.609 | 0.577 |