Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: mistralai/Mistral-Small-24B-Instruct-2501
+base_model: GainEnergy/OGAI-24B
 language:
 - en
 - fr
@@ -17,50 +17,55 @@ tags:
 - transformers
 - llama-cpp
 inference: false
-extra_gated_description: If you want to learn more about how we process your personal
-  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+extra_gated_description: If you want to learn more about how we process your personal data, please read our <a href="https://gain.energy/terms/">Privacy Policy</a>.
 ---
 
-# tommytracx/Mistral-Small-24B-Instruct-2501-Q6_K-GGUF
-This model was converted to GGUF format from [`mistralai/Mistral-Small-24B-Instruct-2501`](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) using llama.cpp.
-Refer to the [original model card](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501) for more details on the model.
+# GainEnergy/OGAI-24B-Q6_K-GGUF
+
+This model was converted to GGUF format from GainEnergy/OGAI-24B using llama.cpp.
+Refer to the original model card for more details.
 
 ## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
 
+### Install llama.cpp through Homebrew (macOS/Linux):
 ```bash
 brew install llama.cpp
-
 ```
-Invoke the llama.cpp server or the CLI.
 
-### CLI:
+### Invoke the llama.cpp server or the CLI.
+
+#### CLI:
 ```bash
-llama-cli --hf-repo tommytracx/Mistral-Small-24B-Instruct-2501-Q6_K-GGUF --hf-file mistral-small-24b-instruct-2501-q6_k.gguf -p "The meaning to life and the universe is"
+llama-cli --hf-repo GainEnergy/OGAI-24B-Q6_K-GGUF --hf-file ogai-24b-q6_k.gguf -p "Explain the principles of reservoir simulation in oil and gas engineering."
 ```
 
-### Server:
+#### Server:
 ```bash
-llama-server --hf-repo tommytracx/Mistral-Small-24B-Instruct-2501-Q6_K-GGUF --hf-file mistral-small-24b-instruct-2501-q6_k.gguf -c 2048
+llama-server --hf-repo GainEnergy/OGAI-24B-Q6_K-GGUF --hf-file ogai-24b-q6_k.gguf -c 2048
 ```
 
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+You can also follow the standard usage steps in the llama.cpp repository.
 
-Step 1: Clone llama.cpp from GitHub.
-```
+## Manual Installation and Execution
+
+### Step 1: Clone llama.cpp
+```bash
 git clone https://github.com/ggerganov/llama.cpp
 ```
 
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
-```
+### Step 2: Build llama.cpp with LLAMA_CURL=1 and optional GPU flags
+```bash
 cd llama.cpp && LLAMA_CURL=1 make
 ```
+For Nvidia GPUs on Linux, add LLAMA_CUDA=1.
 
-Step 3: Run inference through the main binary.
-```
-./llama-cli --hf-repo tommytracx/Mistral-Small-24B-Instruct-2501-Q6_K-GGUF --hf-file mistral-small-24b-instruct-2501-q6_k.gguf -p "The meaning to life and the universe is"
-```
-or 
+### Step 3: Run inference
+```bash
+./llama-cli --hf-repo GainEnergy/OGAI-24B-Q6_K-GGUF --hf-file ogai-24b-q6_k.gguf -p "Explain the impact of wellbore stability on drilling efficiency."
 ```
-./llama-server --hf-repo tommytracx/Mistral-Small-24B-Instruct-2501-Q6_K-GGUF --hf-file mistral-small-24b-instruct-2501-q6_k.gguf -c 2048
+or
+```bash
+./llama-server --hf-repo GainEnergy/OGAI-24B-Q6_K-GGUF --hf-file ogai-24b-q6_k.gguf -c 2048
 ```
+
+This model is optimized for oil and gas engineering applications, featuring domain-specific knowledge in drilling, completions, reservoir management, and production optimization.