Staging to Main

.gitignore

@@ -174,4 +174,5 @@ main/*
 *.bin
 *.1
 *.onnx
-example_env.env
+example_env.env
+bittensor/

README.md

@@ -23,7 +23,7 @@ Our goal is to develop an open-source AI model capable of complex mathematics an
 
   - **Initial Score Calculation**:
     - Each miner's response is evaluated to calculate an initial score using a weighted sum:
-      - `score = (0.4 * similarity_score) + (0.6 * correctness_score) - 0.1 * time_penalty`
+      - `score = (0.2 * similarity_score) + (0.8 * correctness_score) - 0.1 * time_penalty`
         - **Similarity Score**: Calculated based on the cosine similarity between the miner's reasoning and the self-generated ground truth answer.
         - **Correctness Score**: Determined by an LLM that assesses whether the miner's answer is correct based on the question and ground truth.
         - **Time Penalty**: Derived from the processing time of the response relative to the specified timeout.

docs/MINER.md

@@ -1,6 +1,6 @@
 # LogicNet: Miner documentation
 
-### Overview
+## Overview
 
 The Miner is responsible for solving the challenges generated by the Validator. The Miner will receive the challenges from the Validator, solve them, and submit the solutions back to the Validator. The Miner will be rewarded based on the number of challenges solved and the quality of the solutions.
 
@@ -18,28 +18,6 @@ The Miner is responsible for solving the challenges generated by the Validator.
 - `similarity (float)`: Validator compute cosine similarity between `logic_reasoning` and validator's reasoning.
 - `time_penalty (float)`: Penalty for late submission. It's ratio of `process_time / timeout * MAX_PENALTY`.
 
-### Minimum Compute Requirements
-- 1x GPU 24GB VRAM (RTX 4090, A100, A6000, etc)
-- Storage: 100GB
-- Python 3.10
-
-Here's the revised chart sorted by ascending GPU footprint, including the model Qwen/Qwen2-7B-Instruct. Additionally, I've included a section on how to run larger models with lower VRAM using techniques such as adjusting `--gpu_memory_utilization`.
-
-### Model to Run
-Here are some model examples that could be leveraged, sorted by GPU footprint:
-
-| Model Name | Model ID | Default GPU Footprint | Specialization |
-| --- | --- | --- | --- |
-| Qwen2-7B-Instruct | Qwen/Qwen2-7B-Instruct | 24 GB | Instruction-following, suitable for logic and structured reasoning |
-| Mistral-7B-Instruct | mistralai/Mistral-7B-Instruct-v0.1 | 24 GB | High-performance, excellent for logical tasks |
-| Qwen-7B-Chat | Qwen/Qwen-7B-Chat | 24 GB | Conversational logic and problem-solving |
-| Baichuan2-13B-Chat | baichuan-inc/Baichuan2-13B-Chat | 32 GB | Versatile in language understanding, suitable for logic and math |
-| Llama-2-13b-chat | meta-llama/Llama-2-13b-hf | 32 GB | Strong in conversational tasks, good for logic and structured reasoning |
-| Falcon-40B | tiiuae/falcon-40b | 75 GB* | Advanced model, handles complex reasoning and logic efficiently |
-| Mixtral-8x7B | mistralai/Mixtral-8x7B-Instruct-v0.1 | 92 GB* | Advanced model, handles complex reasoning and logic efficiently |
-
-> \* Big models such as mixtral are very costly to run and optimize, so always bear in mind the trade-offs between model speed, model quality and infra cost.
-
 ### Setup for Miner
 1. Git clone the repository
 ```bash
@@ -60,18 +38,107 @@ pip install -e .
 pip uninstall uvloop -y
 pip install git+https://github.com/lukew3/mathgenerator.git
 ```
-3. Create env for vLLM
+
+- For ease of use, you can run the scripts with PM2. To install PM2:
 ```bash
-python -m venv vllm
-. vllm/bin/activate
-pip install vllm
+sudo apt update && sudo apt install jq && sudo apt install npm && sudo npm install pm2 -g && pm2 update
 ```
-3. Setup LLM Configuration
 
-- For ease of use, you can run the scripts as well with PM2. To install PM2:
+## There are two ways to run the Miner:
+1. [Running Model via Together.AI API](#method-1-running-model-via-togetherai)
+2. [Running Model **Locally** using vLLM](#method-2-running-model-locally-using-vllm)
+---
+
+### METHOD 1: Running Model via Together.AI
+
+Alternatively, you can use together.ai's API to access various language models without hosting them locally.
+
+**Note:** You need to register an account with together.ai, obtain an API key, and set the API key in a `.env` file.
+
+1. **Register and Obtain API Key**
+
+   - Visit [together.ai](https://together.ai/) and sign up for an account.
+   - Obtain your API key from the together.ai `dashboard`.
+
+2. **Set Up the `.env` File**
+
+   Create a `.env` file in your project directory and add your together.ai API key `TOGETHER_API_KEY=your_together_ai_api_key`
+
+   You can do this in one command:
+   ```bash
+    echo "TOGETHER_API_KEY=your_together_ai_api_key" > .env
+    ```
+
+3. **Select a Model**
+
+   Together.ai provides access to various models. Please select a suitable chat/language model from the list below:
+
+   | Model Name                  | Model ID                                     | Pricing (per 1M tokens) |
+   |-----------------------------|----------------------------------------------|-------------------------|
+   | **Qwen 1.5 Chat (72B)**     | `qwen/Qwen-1.5-Chat-72B`                     | $0.90                   |
+   | **Qwen 2 Instruct (72B)**   | `Qwen/Qwen2-Instruct-72B`                    | $0.90                   |
+   | **LLaMA-2 Chat (13B)**      | `meta-llama/Llama-2-13b-chat-hf`             | $0.22                   |
+   | **LLaMA-2 Chat (7B)**       | `meta-llama/Llama-2-7b-chat-hf`              | $0.20                   |
+   | **MythoMax-L2 (13B)**       | `Gryphe/MythoMax-L2-13B`                     | $0.30                   |
+   | **Mistral (7B) Instruct v0.3** | `mistralai/Mistral-7B-Instruct-v0.3`         | $0.20                   |
+   | **Mistral (7B) Instruct v0.2** | `mistralai/Mistral-7B-Instruct-v0.2`         | $0.20                   |
+   | **Mistral (7B) Instruct**   | `mistralai/Mistral-7B-Instruct`              | $0.20                   |
+   etc...
+
+   More models are available on the together.ai platform here: [together.ai models](https://api.together.ai/models)
+   > *Note: You don't have to choose image models, choose either chat or language models.*
+
+4. **Run the Miner with together.ai**
+
+   Activate your virtual environment:
+   ```bash
+   . main/bin/activate
+   ```
+
+   Source the `.env` file:
+   ```bash
+   source .env
+   ```
+
+   Start the miner using the following command, replacing placeholders with your actual values:
+   ```bash
+   pm2 start python --name "sn35-miner" -- neurons/miner/miner.py \
+     --netuid 35 \
+     --wallet.name "your-wallet-name" \
+     --wallet.hotkey "your-hotkey-name" \
+     --subtensor.network finney \
+     --axon.port "your-open-port" \
+     --miner.category Logic \
+     --miner.epoch_volume 200 \
+     --miner.llm_client.base_url https://api.together.xyz/v1 \
+     --miner.llm_client.model "model_id_from_list" \
+     --llm_client.key $TOGETHER_API_KEY \
+     --logging.debug
+   ```
+   Replace `"model_id_from_list"` with the **Model ID** you have chosen from the together.ai model list. For example, `Qwen/Qwen2-Instruct-72B`.
+
+**Notes:**
+
+- Ensure your `TOGETHER_API_KEY` is correctly set in the `.env` file and sourced before running the command. you can check the `.env` file by running `cat .env`. And to make sure you sourced the `.env` file correctly, you can run `echo $TOGETHER_API_KEY`.
+- The `--miner.llm_client.base_url` should point to the together.ai API endpoint: `https://api.together.xyz/v1`
+- Make sure your `--miner.llm_client.model` matches the **Model ID** provided by together.ai.
+- For more details on the together.ai API, refer to their [documentation](https://docs.together.ai/).
+
+---
+
+### METHOD 2: Running Model locally using vLLM
+
+#### Minimum Compute Requirements:
+- 1x GPU 24GB VRAM (RTX 4090, A100, A6000, L4, etc...)
+- Storage: 100GB
+- Python 3.10
+1. Create env for vLLM
 ```bash
-sudo apt update && sudo apt install jq && sudo apt install npm && sudo npm install pm2 -g && pm2 update
+python -m venv vllm
+. vllm/bin/activate
+pip install vllm
 ```
+2. Setup LLM Configuration
 - Self host a vLLM server
 ```bash
 . vllm/bin/activate
@@ -93,7 +160,7 @@ pm2 start "vllm serve Qwen/Qwen2-7B-Instruct --port 8000 --host 0.0.0.0" --name
    pm2 start "vllm serve Qwen/Qwen2-7B-Instruct --shard --port 8000 --host 0.0.0.0" --name "sn35-vllm"
    ```
 
-4. Run the following command to start mining
+3. Run the following command to start mining
 ```bash
 . main/bin/activate
 pm2 start python --name "sn35-miner" -- neurons/miner/miner.py \
@@ -106,3 +173,8 @@ pm2 start python --name "sn35-miner" -- neurons/miner/miner.py \
 --miner.llm_client.model Qwen/Qwen2-7B-Instruct \ # vLLM model name
 --logging.debug \ # Optional: Enable debug logging
 ```
+
+---
+
+### If you encounter any issues, check the miner logs or contact the LogicNet support team.
+Happy Mining!