danaevan commited on
Commit
d045c14
1 Parent(s): 59cead3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -64,7 +64,7 @@ Search-based technology, AutoNAC.
64
 
65
  ## Model Details
66
 
67
- - **Developed by:** Deci
68
  - **Model type:** DeciCoder is an auto-regressive language model based on the transformer decoder architecture, using Grouped Query Attention.
69
  - **Language(s):** Python, Java, JavaScript
70
  - **License:** Model checkpoints are licensed under the [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
@@ -159,12 +159,12 @@ Below are DeciCoder's pass@1 on MultiPL HumanEval scores
159
  | Infery LLM | 3,889.3 | 11,676.8 |
160
 
161
  - Throughput (tokens/sec) - Measured with optimal batch size per hardware - A10 on BS 128, A100 on BS 512
162
- - Infery-LLM, Deci's optimization and inference SDK's features a suite of optimization techniques, including selective quantization, optimized beam search, continuous batching, and custom CUDA kernels. To explore the full capabilities of Infery-LLM, we invite you to [book a demo](https://deci.ai/infery-llm-book-a-demo/) with our experts.
163
 
164
  ## Documentation
165
 
166
  - [Notebook](https://colab.research.google.com/drive/1JCxvBsWCZKHfIcHSMVf7GZCs3ClMQPjs)
167
- - Blog post: [Introducing DeciCoder: The New Gold Standard in Efficient and Accurate Code Generation](https://deci.ai/blog/decicoder-efficient-and-accurate-code-generation-llm/)
168
  - Questions:Feel free to contact us via our [Discord Community!](https://discord.com/invite/p9ecgRhDR8/)
169
 
170
  ## How to Cite
 
64
 
65
  ## Model Details
66
 
67
+ - **Developed by:** [Deci](https://deci.ai/)
68
  - **Model type:** DeciCoder is an auto-regressive language model based on the transformer decoder architecture, using Grouped Query Attention.
69
  - **Language(s):** Python, Java, JavaScript
70
  - **License:** Model checkpoints are licensed under the [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
 
159
  | Infery LLM | 3,889.3 | 11,676.8 |
160
 
161
  - Throughput (tokens/sec) - Measured with optimal batch size per hardware - A10 on BS 128, A100 on BS 512
162
+ - Infery-LLM, Deci's optimization and inference SDK's features a suite of optimization techniques, including selective quantization, optimized beam search, continuous batching, and custom CUDA kernels. To explore the full capabilities of Infery-LLM, we invite you to [book a demo](https://deci.ai/infery-llm-book-a-demo/?utm_campaign=repos&utm_source=hugging-face&utm_medium=model-card&utm_content=decicoder-1b) with our experts.
163
 
164
  ## Documentation
165
 
166
  - [Notebook](https://colab.research.google.com/drive/1JCxvBsWCZKHfIcHSMVf7GZCs3ClMQPjs)
167
+ - Blog post: [Introducing DeciCoder: The New Gold Standard in Efficient and Accurate Code Generation](https://deci.ai/blog/decicoder-efficient-and-accurate-code-generation-llm/?utm_campaign=repos&utm_source=hugging-face&utm_medium=model-card&utm_content=decicoder-1b)
168
  - Questions:Feel free to contact us via our [Discord Community!](https://discord.com/invite/p9ecgRhDR8/)
169
 
170
  ## How to Cite