Models

.github/CODEOWNERS

@@ -0,0 +1 @@
+@Smartappli

.github/FUNDING.yml

@@ -0,0 +1 @@
+github: [Smartappli]

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -0,0 +1,73 @@
+name: "☢️ Bug Report"
+title: "\U0001F41B [Bug]: "
+description: Create a report to help us improve Serge.
+labels: ["☢️ Bug"]
+
+body:
+  - type: markdown
+    attributes:
+      value: |
+        Thanks for taking the time to fill out this bug report.
+
+  - type: textarea
+    id: description
+    attributes:
+      label: Bug description
+      description: Please provide a bug description with expected beavior vs. actual behavior.
+      placeholder: Don't put your logs here!
+    validations:
+      required: true
+
+  - type: textarea
+    id: steps
+    attributes:
+      label: Steps to reproduce
+      description: Please provide a step by step guide to recreate the issue.
+      placeholder: |
+        Please provide steps to reproduce the behavior.
+
+        1. Step 1
+        2. Step 2
+        3. Step 3
+    validations:
+      required: true
+
+  - type: textarea
+    id: environment
+    attributes:
+      label: Environment Information
+      description: Please provide the following information about your environment.
+      placeholder: |
+        Docker version: (run `docker --version`)
+        OS: (e.g., Windows, macOS, Linux)
+        OS version: (e.g., Windows 10, macOS 11.4, Ubuntu 20.04)
+        CPU Model: (e.g., Intel Core i7-9700K, AMD Ryzen 5 3600)
+        Browser: (if relevant)
+    validations:
+      required: true
+
+  - type: textarea
+    id: screenshots
+    attributes:
+      label: Screenshots
+      description: Please provide screenshots if relevant.
+    validations:
+      required: false
+
+  - type: textarea
+    id: logs
+    attributes:
+      label: Relevant log output
+      description: Please copy and paste any relevant log output. This will be automatically formatted into code, so no need for backticks.
+      render: shell
+
+  - type: checkboxes
+    id: confirmations
+    attributes:
+      label: Confirmations
+      description: Please verify you meet those criterias to make it easier to help you.
+      options:
+        - label: I'm running the latest version of the main branch.
+          required: true
+        - label: I checked existing issues to see if this has already been described.
+          required: true

.github/ISSUE_TEMPLATE/feature-request.yml

@@ -0,0 +1,37 @@
+name: "✏️ Feature Request"
+title: "\U0001F680 [Feature]: "
+description: Suggest an idea to improve this project.
+labels: ["✏️ Feature"]
+
+body:
+  - type: markdown
+    id: notice
+    attributes:
+      value: |
+        ### Notice
+        - Don't forget you can ask your questions in our [Discord server](https://discord.gg/62Hc6FEYQH).
+        - If you think this is just a bug, open the issue with the **☢️ Bug Report** template.
+  - type: textarea
+    id: description
+    attributes:
+      label: "Feature Description"
+      description: "A clear and detailed description of the feature you would like to see added."
+      placeholder: "Explain your feature clearly, and in detail."
+    validations:
+      required: true
+  - type: textarea
+    id: additional-context
+    attributes:
+      label: "Additional Context (optional)"
+      description: "If you have something else to describe, write them here."
+      placeholder: "Write here what you can describe differently."
+  - type: checkboxes
+    id: terms
+    attributes:
+      label: "Checklist:"
+      description: "By submitting this issue, you confirm that:"
+      options:
+        - label: "I have checked for existing issues that describe my suggestion prior to opening this one."
+          required: true
+        - label: "I understand that improperly formatted feature requests may be closed without explanation."
+          required: true

.github/ISSUE_TEMPLATE/question.yml

@@ -0,0 +1,32 @@
+name: "🤔 Question"
+title: "\U0001F917 [Question]: "
+description: Ask a question so we can help you
+labels: ["🤔 Question"]
+
+body:
+  - type: markdown
+    id: notice
+    attributes:
+      value: |
+        ### Notice
+        - Don't forget you can ask your questions in our [Discord server](https://discord.gg/q2sAWmzF).
+        - If you think this is just a bug, open the issue with the **☢️ Bug Report** template.
+        - If you have a suggestion for a Serge feature you would like to see, open the issue with the **✏️ Feature Request** template.
+  - type: textarea
+    id: description
+    attributes:
+      label: "Question Description"
+      description: "A clear and detailed description of the question."
+      placeholder: "Explain your question clearly, and in detail."
+    validations:
+      required: true
+  - type: checkboxes
+    id: terms
+    attributes:
+      label: "Checklist:"
+      description: "By submitting this issue, you confirm that:"
+      options:
+        - label: "I have checked for existing issues that describe my questions prior to opening this one."
+          required: true
+        - label: "I understand that improperly formatted questions may be closed without explanation."
+          required: true

.github/ISSUE_TEMPLATE/sweep-template.yml

@@ -0,0 +1,15 @@
+name: Sweep Issue
+title: 'Sweep: '
+description: For small bugs, features, refactors, and tests to be handled by Sweep, an AI-powered junior developer.
+labels: sweep
+body:
+  - type: textarea
+    id: description
+    attributes:
+      label: Details
+      description: Tell Sweep where and what to edit and provide enough context for a new developer to the codebase
+      placeholder: |
+        Unit Tests: Write unit tests for <FILE>. Test each function in the file. Make sure to test edge cases.
+        Bugs: The bug might be in <FILE>. Here are the logs: ...
+        Features: the new endpoint should use the ... class from <FILE> because it contains ... logic.
+        Refactors: We are migrating this function to ... version because ...

.github/dependabot.yml

@@ -3,5 +3,18 @@ updates:
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
-      # Check for updates to GitHub Actions every week
-      interval: "weekly"
+      interval: "daily"
+    labels:
+      - "🤖 Dependencies"
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    labels:
+      - "🤖 Dependencies"
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    labels:
+      - "🤖 Dependencies"

.github/release-drafter.yml

@@ -0,0 +1,72 @@
+name-template: '$RESOLVED_VERSION'
+tag-template: '$RESOLVED_VERSION'
+categories:
+  - title: '❗ Breaking Changes:'
+    labels:
+      - '❗ Breaking Change'
+  - title: '🚀 New Features:'
+    labels:
+      - '✏️ Feature'
+  - title: '🐛 Fixes:'
+    labels:
+      - '☢️ Bug'
+  - title: '📚 Documentation:'
+    labels:
+      - '📒 Documentation'
+  - title: '🧹 Updates:'
+    labels:
+      - '🧹 Updates'
+  - title: '🤖 Dependencies:'
+    labels:
+      - '🤖 Dependencies'
+change-template: '- $TITLE (#$NUMBER)'
+change-title-escapes: '\<*_&'
+exclude-contributors:
+  - dependabot
+  - dependabot[bot]
+version-resolver:
+  major:
+    labels:
+      - 'major'
+  minor:
+    labels:
+      - 'minor'
+      - '❗ Breaking Change'
+      - '✏️ Feature'
+  patch:
+    labels:
+      - 'patch'
+      - '📒 Documentation'
+      - '☢️ Bug'
+      - '🤖 Dependencies'
+      - '🧹 Updates'
+  default: patch
+template: |
+    $CHANGES
+
+    ## 🐳 Docker Images
+    - `ghcr.io/$OWNER/$REPOSITORY:latest`
+    - `ghcr.io/$OWNER/$REPOSITORY:$RESOLVED_VERSION`
+
+    **Full Changelog**: https://github.com/$OWNER/$REPOSITORY/compare/$PREVIOUS_TAG...$RESOLVED_VERSION
+
+    Thanks to $CONTRIBUTORS for making this release possible.
+
+autolabeler:
+- label: '📒 Documentation'
+  files:
+    - '*.md'
+  title:
+    - '/(docs|doc:|\[doc\]|typos|comment|documentation)/i'
+- label: '☢️ Bug'
+  title:
+    - '/(fix|bug|missing|correct)/i'
+- label: '🧹 Updates'
+  title: 
+    - '/(improve|update|refactor|deprecated|remove|unused|test)/i'
+- label: '🤖 Dependencies'
+  title:
+    - '/(bump|dependencies)/i'
+- label: '✏️ Feature'
+  title:
+    - '/(feature|feat|create|implement)/i'

.github/workflows/black.yml

@@ -0,0 +1,30 @@
+name: Black Formatter
+on: [push, pull_request]
+
+concurrency:
+  group: black-${{ github.event_name == 'pull_request' && format('{0}-{1}', github.workflow, github.event.pull_request.number) || github.workflow_ref }}
+  cancel-in-progress: true
+
+jobs:
+  linter_name:
+    name: Black
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Check files using the black formatter
+        uses: rickstaa/action-black@v1
+        id: action_black
+        with:
+          black_args: "."
+      - name: Create Pull Request
+        if: steps.action_black.outputs.is_formatted == 'true'
+        uses: peter-evans/create-pull-request@v6
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          title: "Format Python code with psf/black push"
+          commit-message: ":art: Format Python code with psf/black"
+          body: |
+            There appear to be some python formatting errors in ${{ github.sha }}. This pull request
+            uses the [psf/black](https://github.com/psf/black) formatter to fix these issues.
+          base: ${{ github.head_ref }} # Creates pull request onto pull request or commit branch
+          branch: black

.github/workflows/model-check.yml

@@ -17,6 +17,10 @@ on:
   schedule:
     - cron: '0 12 */7 * *'
 
+concurrency:
+  group: LLM-Checker-${{ github.event_name == 'pull_request' && format('{0}-{1}', github.workflow, github.event.pull_request.number) || github.workflow_ref }}
+  cancel-in-progress: true
+
 jobs:
   model-health-check:
     runs-on: ubuntu-latest
@@ -30,9 +34,7 @@ jobs:
         working-directory: ./
         run: |
           pip install --upgrade pip
-          pip install pytest
-          pip install huggingface_hub
-          pip install pathlib
+          pip install -r requirements.txt
       - name: Run model health check
         working-directory: ./
         run: |

.github/workflows/ruff.yml

@@ -0,0 +1,11 @@
+name: Ruff
+on: [push, pull_request]
+jobs:
+  ruff:
+    name: Ruff
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: chartboost/ruff-action@v1
+        with:
+          args: 'check --ignore F401 --fix'

README.md

@@ -17,22 +17,22 @@ Then replace the models.json file located in /usr/src/app/api/src/serge/data/ of
 
 | Directory    | Description    | Models    |
 |:------------:|:--------------------------------:|:---------:|
-| **All** | All models | AlBfred 40B-1023; Asclepius 13B; BioMistral 7B; Code 13B, 33B; CodeLLaMA 7B, 7B-Instruct, 7B-Python, 13B, 13B-Instruct, 13B-Python, 34B, 34B-Instruct, 34B-Python? 70B, 70B-Instruct, 70B-Python; Falcon 7B, 7B-Instruct, 40B, 40B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; Finance Chat, LLM, LLM-13B; LLaMA 2 7B, 7B-Chat, 7B-Coder, 13B, 13B-Chat, 70B, 70B-Chat, 70B-OASST; LLamA Pro 8B, 8B-Instruct; Med42 70B; Medalpaca 13B; Medicine: Chat, LLM, LLM 13B; Meditron 7B, 7B-Chat, 70B; Mistral 7B-v0.1, 7B-Instruct-v0.2, 7B-OpenOrca; MistralLite 7B; Mixtral 8x7B-v0.1, 8x7B-Dolphin-2.7, 8x7B-Instruct-v0.1, SlimOrca 8x7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Notux 8x7b-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; OpenLLaMA 3B-v2, 7B-v2, 13B-v2; Orca 2 7B, 13B; Phi 2 2.7B; Python Code 13B, 33B; PsyMedRP 13B-v1, 20B-v1; SlimOrca 13B; Sqlcoder 2 15B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0, 1.1B Chat Medical; Vicuna 7B-v1.5, 13B-v1.5, 33B-v1.3, 33B-Coder; Vigogne 2 7B-Chat, 7B-Instruct, 13B-Instruct, 70B-Chat; Wizard Coder-33B-v1.1; LM-7B-v1.0, LM-13B-v1.2, LM-70B-v1.0, Math-7B-v1.1, 13B-v1.0, 70B-v1.0; Zephyr 3B, 7B-Alpha, 7B-Beta |
+| **All** | All models | Alfred 40B-1023; Asclepius 13B; BioMistral 7B; Code 13B, 33B; CodeLLaMA 7B, 7B-Instruct, 7B-Python, 13B, 13B-Instruct, 13B-Python, 34B, 34B-Instruct, 34B-Python? 70B, 70B-Instruct, 70B-Python; Falcon 7B, 7B-Instruct, 40B, 40B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; Finance Chat, LLM, LLM-13B; Gorilla 7B-Falcon, 7B, OpenFunctions V1, OpenFunctions V2; LLaMA 2 7B, 7B-Chat, 7B-Coder, 13B, 13B-Chat, 70B, 70B-Chat, 70B-OASST; LLaMA 3 11B-Instruct-v0.1, 13B-Instruct-v0.1, 16B-Instruct-v0.1; LLamA Pro 8B, 8B-Instruct; Med42 70B; Medalpaca 13B; Medicine: Chat, LLM, LLM 13B; Meditron 7B, 7B-Chat, 70B; Meta-Llama 3 8B, 8B-Instruct, 70B, 70B-Instruct; Mistral 7B-v0.1, 7B-Instruct-v0.2, 7B-OpenOrca; MistralLite 7B; Mixtral 8x7B-v0.1, 8x7B-Dolphin-2.7, 8x7B-Instruct-v0.1, SlimOrca 8x7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Notux 8x7b-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; Open Code Interpreter CL-7B, CL-13B, CL-70B, DS-6.7B, DS-33B; OpenLLaMA 3B-v2, 7B-v2, 13B-v2; Orca 2 7B, 13B; Phi 2 2.7B; Python Code 13B, 33B; PsyMedRP 13B-v1, 20B-v1; SlimOrca 13B; Sqlcoder 2 15B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0, 1.1B Chat Medical; Vicuna 7B-v1.5, 13B-v1.5, 33B-v1.3, 33B-Coder; Vigogne 2 7B-Chat, 7B-Instruct, 13B-Instruct, 70B-Chat; Wizard Coder-33B-v1.1, LM-7B-v1.0, LM-2-7B, LM-13B-v1.2, LM-70B-v1.0, Math-7B-v1.1, 13B-v1.0, 70B-v1.0; Zephyr 3B, 7B-Alpha, 7B-Beta |
 
 | Directory    | Description    | Models    |
 |:------------:|:--------------------------------:|:---------:|
-| **Generic** | Models trained for english language | CodeLLaMA 7B, 7B-Instruct, 7B-Python, 13B, 13B-Instruct, 13B-Python, 34B, 34B-Instruct, 34B-Python, 70B, 70B-Instruct; Falcon 7B, 7B-Instruct, 40B, 40B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; LLaMA 2 7B, 7B-Chat, 7B-Coder, 13B, 13B-Chat, 70B, 70B-Chat; LLamA Pro 8B, 8B-Instruct; Mistral 7B-v0.1, 7B-Instruct-v0.2, 7B-OpenOrca; MistralLite 7B; Mixtral 8x7B-v0.1, 8x7B-Dolphin-2.7, 8x7B-Instruct-v0.1, SlimOrca 8x7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Notux 8x7b-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; OpenLLaMA 3B-v2, 7B-v2, 13B-v2; Orca 2 7B, 13B; Phi 2 2.7B; SlimOrca 13B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0; Vicuna 7B-v1.5, 13B-v1.5, 33B-v1.3, 33B-Coder; Vigogne 2 7B-Chat, 7B-Instruct, 13B-Instruct, 70B-Chat; WizardL LM-7B-v1.0, LM-13B-v1.2, LM-70B-v1.0; Zephyr 3B, 7B-Alpha, 7B-Beta |
+| **Generic** | Models trained for english language | CodeLLaMA 7B, 7B-Instruct, 7B-Python, 13B, 13B-Instruct, 13B-Python, 34B, 34B-Instruct, 34B-Python, 70B, 70B-Instruct; Falcon 7B, 7B-Instruct, 40B, 40B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; Gorilla 7B-Falcon, 7B, OpenFunctions V1, OpenFunctions V2; LLaMA 2 7B, 7B-Chat, 7B-Coder, 13B, 13B-Chat, 70B, 70B-Chat; LLaMA 3 11B-Instruct-v0.1, 13B-Instruct-v0.1, 16B-Instruct-v0.1; LLamA Pro 8B, 8B-Instruct; Meta-Llama 3 8B, 8B-Instruct, 70B, 70B-Instruct; Mistral 7B-v0.1, 7B-Instruct-v0.2, 7B-OpenOrca; MistralLite 7B; Mixtral 8x7B-v0.1, 8x7B-Dolphin-2.7, 8x7B-Instruct-v0.1, SlimOrca 8x7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Notux 8x7b-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; OpenLLaMA 3B-v2, 7B-v2, 13B-v2; Orca 2 7B, 13B; Phi 2 2.7B; SlimOrca 13B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0; Vicuna 7B-v1.5, 13B-v1.5, 33B-v1.3, 33B-Coder; Vigogne 2 7B-Chat, 7B-Instruct, 13B-Instruct, 70B-Chat; WizardL LM-7B-v1.0, LM-2-7B, LM-13B-v1.2, LM-70B-v1.0; Zephyr 3B, 7B-Alpha, 7B-Beta |
 
 | Directory    | Description    | Models    |
 |:------------:|:--------------------------------:|:---------:|
-| **Tiny** | Models <= 7B params | CodeLLaMA 7B, 7B-Instruct; Falcon 7B, 7B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; LLaMA 2 7B, 7B-Chat; Meditron 7B, 7B-Chat; Mistral 7B-v0.1, 7B-Instruct-v0.2; MistralLite 7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; OpenLLaMA 3B-v2, 7B-v2; Orca 2 7B; Phi 2 2.7B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0; Vicuna 7B-v1.5; Vigogne 2 7B-Chat, 7B-Instruct; Wizard LM-7B-v1.0; Zephyr 3B, 7B-Alpha, 7B-Beta |
-| **Small** | Models with 7B and <= 13B params | CodeLLaMA 13B, 13B-Instruct; LLaMA 2 13B, 13B-Chat; LLamA Pro 8B, 8B-Instruct; OpenLLaMA 13B-v2; Orca 2 13B; SlimOrca 13B; Vicuna 13B-v1.5; Vigogne 2 13B-Instruct; WizardLM 13B-v1.2 |
-| **Medium** | Models with > 13B abd <=40B params | Alfred 40B-1023; CodeLLaMA 34B, 34B-Instruct; Falcon 40B, 40B-Instruct |
-| **Large** | Models with >40B and <=80B params | CodeLLaMA 70B, 70B-Instruct; LLaMA 2 70B, 70B-Chat; Mixtral 8x7B-v0.1, 8x7B-Instruct-v0.1; Notux 8x7b-v1, Wizard LM-70B-v1.0 |  
+| **Tiny** | Models <= 7B params | CodeLLaMA 7B, 7B-Instruct; Falcon 7B, 7B-Instruct; Gemma 2B, 2B-Instruct, 7B, 7B-Instruct; Gorilla 7B-Falcon, 7B, OpenFunctions V1, OpenFunctions V2; LLaMA 2 7B, 7B-Chat; Meditron 7B, 7B-Chat; Mistral 7B-v0.1, 7B-Instruct-v0.2; MistralLite 7B; Neural-Chat 7B-v3.3; Notus 7B-v1; Nous-Hermes-2 Mistral-7B-DPO, Mixtral-8x7B-DPO, Mistral-8x7B-SFT; OpenChat 7B-v3.5-0106; OpenLLaMA 3B-v2, 7B-v2; Orca 2 7B; Phi 2 2.7B; Starling LM 7B-Alpha; Tinyllama 1.1B Chat v1.0; Vicuna 7B-v1.5; Vigogne 2 7B-Chat, 7B-Instruct; Wizard LM-7B-v1.0, LM-2-7B; Zephyr 3B, 7B-Alpha, 7B-Beta |
+| **Small** | Models with 7B and <= 13B params | CodeLLaMA 13B, 13B-Instruct; LLaMA 2 13B, 13B-Chat; LLaMA 3 11B-Instruct-v0.1, 13B-Instruct-v0.1; LLamA Pro 8B, 8B-Instruct; Meta-Llama 3 8B, 8B-Instruct; OpenLLaMA 13B-v2; Orca 2 13B; SlimOrca 13B; Vicuna 13B-v1.5; Vigogne 2 13B-Instruct; WizardLM 13B-v1.2 |
+| **Medium** | Models with > 13B abd <=40B params | Alfred 40B-1023; CodeLLaMA 34B, 34B-Instruct; Falcon 40B, 40B-Instruct; LLaMA 3 16B-Instruct-v0.1 |
+| **Large** | Models with >40B and <=80B params | CodeLLaMA 70B, 70B-Instruct; LLaMA 2 70B, 70B-Chat; Meta-Llama 3 70B, 70B-Instruct; Mixtral 8x7B-v0.1, 8x7B-Instruct-v0.1; Notux 8x7b-v1, Wizard LM-70B-v1.0 |  
 
 | Directory    | Description    | Models    |
 |:------------:|:--------------------------------:|:---------:|
-| **Coder** | Models trained for coding | Code 13B, 33B; CodeLLaMA 7B-Python, 13B-Python, 34B-Python, 70B-Python; LLaMA 2 7B-Coder; Sqlcoder 2 15B; Vicuna 33B-Coder; Wizard Coder-33B-v1.1 |
+| **Coder** | Models trained for coding | Code 13B, 33B; CodeLLaMA 7B-Python, 13B-Python, 34B-Python, 70B-Python; Open Code Interpreter CL-7B, CL-13B, CL-70B, DS-6.7B, DS-33B; LLaMA 2 7B-Coder; Sqlcoder 2 15B; Vicuna 33B-Coder; Wizard Coder-33B-v1.1 |
 | **Finance** | Models trained for finance domain | Finance Chat, LLM, LLM-13B |
 | **Math** | Models trained for math domain | Wizard Math-7B-v1.1, 13B-v1.0, 70B-v1.0 |
 | **Medical** | Models trained for medical domain | Asclepius 13B; BioMistral 7B; Med42 70B; Medalpaca 13B; Medicine Chat, LLM, LLM 13B; Meditron 7B, 7B-Chat, 70B; PsyMedRP 13B-v1, 20B-v1; TinyLlama 1.1B Chat Medical |