Update README.md
Browse files
README.md
CHANGED
@@ -25,7 +25,7 @@ Commencis LLM is a generative model based on the Mistral 7B model. The base mode
|
|
25 |
- **Finetuned from model:** [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
26 |
- **Input:** Model input text only
|
27 |
- **Output:** Model generates text only
|
28 |
-
- **Blog Post**: [
|
29 |
|
30 |
## Training Details
|
31 |
Alignment phase consists of two stages: supervised fine-tuning (SFT) and Reward Modeling with Reinforcement learning from human feedback (RLHF).
|
|
|
25 |
- **Finetuned from model:** [Mistral 7B](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)
|
26 |
- **Input:** Model input text only
|
27 |
- **Output:** Model generates text only
|
28 |
+
- **Blog Post**: [LLM Blog](https://www.commencis.com/thoughts/commencis-introduces-its-purpose-built-turkish-fluent-llm-for-banking-and-finance-industry-a-detailed-overview/)
|
29 |
|
30 |
## Training Details
|
31 |
Alignment phase consists of two stages: supervised fine-tuning (SFT) and Reward Modeling with Reinforcement learning from human feedback (RLHF).
|