bump version (#3082) (#3083)

Co-authored-by: Hoang Ha <64120343 [email protected]>
janhq · Van-QA · Jul 15, 2024 · Jun 17, 2024 · Jun 17, 2024 · Jun 20, 2024
commit 18b4c2c0b61bc6f1080a7edbe087980496cd04c1
diff --git a/extensions/inference-nitro-extension/package.json b/extensions/inference-nitro-extension/package.json
@@ -1,7 1,7 @@
 {
  "name": "@janhq/inference-cortex-extension",
  "productName": "Cortex Inference Engine",
- "version": "1.0.12",
  "version": "1.0.13",
  "description": "This extension embeds cortex.cpp, a lightweight inference engine written in C . See https://nitro.jan.ai.\nAdditional dependencies could be installed to run without Cuda Toolkit installation.",
  "main": "dist/index.js",
  "node": "dist/node/index.cjs.js",

diff --git a/extensions/inference-nitro-extension/resources/models/aya-23-35b/model.json b/extensions/inference-nitro-extension/resources/models/aya-23-35b/model.json
@@ -8,7 8,7 @@
  "id": "aya-23-35b",
  "object": "model",
  "name": "Aya 23 35B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Aya 23 can talk upto 23 languages fluently.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/aya-23-8b/model.json b/extensions/inference-nitro-extension/resources/models/aya-23-8b/model.json
@@ -8,7 8,7 @@
  "id": "aya-23-8b",
  "object": "model",
  "name": "Aya 23 8B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Aya 23 can talk upto 23 languages fluently.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/codeninja-1.0-7b/model.json b/extensions/inference-nitro-extension/resources/models/codeninja-1.0-7b/model.json
@@ -8,7 8,7 @@
  "id": "codeninja-1.0-7b",
  "object": "model",
  "name": "CodeNinja 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "CodeNinja is good for coding tasks and can handle various languages including Python, C, C , Rust, Java, JavaScript, and more.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/codestral-22b/model.json b/extensions/inference-nitro-extension/resources/models/codestral-22b/model.json
@@ -8,7 8,7 @@
  "id": "codestral-22b",
  "object": "model",
  "name": "Codestral 22B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Latest model from MistralAI optimized for code generation tasks.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/command-r-34b/model.json b/extensions/inference-nitro-extension/resources/models/command-r-34b/model.json
@@ -8,7 8,7 @@
  "id": "command-r-34b",
  "object": "model",
  "name": "Command-R v01 34B Q4",
- "version": "1.4",
  "version": "1.5",
  "description": "C4AI Command-R developed by CohereAI is optimized for a variety of use cases including reasoning, summarization, and question answering.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/deepseek-coder-1.3b/model.json b/extensions/inference-nitro-extension/resources/models/deepseek-coder-1.3b/model.json
@@ -8,7 8,7 @@
  "id": "deepseek-coder-1.3b",
  "object": "model",
  "name": "Deepseek Coder 1.3B Q8",
- "version": "1.1",
  "version": "1.2",
  "description": "Deepseek Coder excelled in project-level code completion with advanced capabilities across multiple programming languages.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/deepseek-coder-34b/model.json b/extensions/inference-nitro-extension/resources/models/deepseek-coder-34b/model.json
@@ -8,7 8,7 @@
  "id": "deepseek-coder-34b",
  "object": "model",
  "name": "Deepseek Coder 33B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Deepseek Coder excelled in project-level code completion with advanced capabilities across multiple programming languages.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/gemma-2b/model.json b/extensions/inference-nitro-extension/resources/models/gemma-2b/model.json
@@ -8,7 8,7 @@
  "id": "gemma-2b",
  "object": "model",
  "name": "Gemma 2B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Gemma is built from the same technology with Google's Gemini.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/gemma-7b/model.json b/extensions/inference-nitro-extension/resources/models/gemma-7b/model.json
@@ -8,7 8,7 @@
  "id": "gemma-7b",
  "object": "model",
  "name": "Gemma 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Google's Gemma is built for multilingual purpose",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/llama2-chat-70b/model.json b/extensions/inference-nitro-extension/resources/models/llama2-chat-70b/model.json
@@ -8,7 8,7 @@
  "id": "llama2-chat-70b",
  "object": "model",
  "name": "Llama 2 Chat 70B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Llama 2 specifically designed for a comprehensive understanding the world.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/llama2-chat-7b/model.json b/extensions/inference-nitro-extension/resources/models/llama2-chat-7b/model.json
@@ -8,7 8,7 @@
  "id": "llama2-chat-7b",
  "object": "model",
  "name": "Llama 2 Chat 7B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Llama 2 specifically designed for a comprehensive understanding the world.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json b/extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json
@@ -8,7 8,7 @@
  "id": "llama3-8b-instruct",
  "object": "model",
  "name": "Llama 3 8B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Meta's Llama 3 excels at general usage situations, including chat, general world knowledge, and coding.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/llama3-hermes-8b/model.json b/extensions/inference-nitro-extension/resources/models/llama3-hermes-8b/model.json
@@ -8,7 8,7 @@
  "id": "llama3-hermes-8b",
  "object": "model",
  "name": "Hermes Pro Llama 3 8B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Hermes Pro is well-designed for General chat and JSON output.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/llamacorn-1.1b/model.json b/extensions/inference-nitro-extension/resources/models/llamacorn-1.1b/model.json
@@ -8,7 8,7 @@
  "id": "llamacorn-1.1b",
  "object": "model",
  "name": "LlamaCorn 1.1B Q8",
- "version": "1.0",
  "version": "1.1",
  "description": "LlamaCorn is designed to improve chat functionality from TinyLlama.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/mistral-ins-7b-q4/model.json b/extensions/inference-nitro-extension/resources/models/mistral-ins-7b-q4/model.json
@@ -8,7 8,7 @@
  "id": "mistral-ins-7b-q4",
  "object": "model",
  "name": "Mistral Instruct 7B Q4",
- "version": "1.2",
  "version": "1.3",
  "description": "Mistral Instruct 7b model, specifically designed for a comprehensive understanding of the world.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/noromaid-7b/model.json b/extensions/inference-nitro-extension/resources/models/noromaid-7b/model.json
@@ -8,7 8,7 @@
  "id": "noromaid-7b",
  "object": "model",
  "name": "Noromaid 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "The Noromaid 7b model is designed for role-playing with human-like behavior.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/openchat-3.5-7b/model.json b/extensions/inference-nitro-extension/resources/models/openchat-3.5-7b/model.json
@@ -8,7 8,7 @@
  "id": "openchat-3.5-7b",
  "object": "model",
  "name": "Openchat-3.5 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "The performance of Openchat surpasses ChatGPT-3.5 and Grok-1 across various benchmarks.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/phi3-3.8b/model.json b/extensions/inference-nitro-extension/resources/models/phi3-3.8b/model.json
@@ -8,7 8,7 @@
  "id": "phi3-3.8b",
  "object": "model",
  "name": "Phi-3 Mini",
- "version": "1.1",
  "version": "1.2",
  "description": "Phi-3 Mini is Microsoft's newest, compact model designed for mobile use.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/phi3-medium/model.json b/extensions/inference-nitro-extension/resources/models/phi3-medium/model.json
@@ -8,7 8,7 @@
  "id": "phi3-medium",
  "object": "model",
  "name": "Phi-3 Medium",
- "version": "1.1",
  "version": "1.2",
  "description": "Phi-3 Medium is Microsoft's latest SOTA model.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/phind-34b/model.json b/extensions/inference-nitro-extension/resources/models/phind-34b/model.json
@@ -8,7 8,7 @@
  "id": "phind-34b",
  "object": "model",
  "name": "Phind 34B Q4",
- "version": "1.2",
  "version": "1.3",
  "description": "Phind 34B is the best Open-source coding model.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/qwen-7b/model.json b/extensions/inference-nitro-extension/resources/models/qwen-7b/model.json
@@ -8,7 8,7 @@
  "id": "qwen-7b",
  "object": "model",
  "name": "Qwen Chat 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Qwen is optimized at Chinese, ideal for everyday tasks.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/qwen2-7b/model.json b/extensions/inference-nitro-extension/resources/models/qwen2-7b/model.json
@@ -8,7 8,7 @@
  "id": "qwen2-7b",
  "object": "model",
  "name": "Qwen 2 Instruct 7B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Qwen is optimized at Chinese, ideal for everyday tasks.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/stable-zephyr-3b/model.json b/extensions/inference-nitro-extension/resources/models/stable-zephyr-3b/model.json
@@ -8,7 8,7 @@
  "id": "stable-zephyr-3b",
  "object": "model",
  "name": "Stable Zephyr 3B Q8",
- "version": "1.0",
  "version": "1.1",
  "description": "StableLM Zephyr 3B is a best model for low-end machine.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/stealth-v1.2-7b/model.json b/extensions/inference-nitro-extension/resources/models/stealth-v1.2-7b/model.json
@@ -8,7 8,7 @@
  "id": "stealth-v1.2-7b",
  "object": "model",
  "name": "Stealth 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "This is a new experimental family designed to enhance Mathematical and Logical abilities.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/tinyllama-1.1b/model.json b/extensions/inference-nitro-extension/resources/models/tinyllama-1.1b/model.json
@@ -8,7 8,7 @@
  "id": "tinyllama-1.1b",
  "object": "model",
  "name": "TinyLlama Chat 1.1B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "TinyLlama is a tiny model with only 1.1B. It's a good model for less powerful computers.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/trinity-v1.2-7b/model.json b/extensions/inference-nitro-extension/resources/models/trinity-v1.2-7b/model.json
@@ -8,7 8,7 @@
  "id": "trinity-v1.2-7b",
  "object": "model",
  "name": "Trinity-v1.2 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Trinity is an experimental model merge using the Slerp method. Recommended for daily assistance purposes.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/vistral-7b/model.json b/extensions/inference-nitro-extension/resources/models/vistral-7b/model.json
@@ -8,7 8,7 @@
  "id": "vistral-7b",
  "object": "model",
  "name": "Vistral 7B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "Vistral 7B has a deep understanding of Vietnamese.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/wizardcoder-13b/model.json b/extensions/inference-nitro-extension/resources/models/wizardcoder-13b/model.json
@@ -8,7 8,7 @@
  "id": "wizardcoder-13b",
  "object": "model",
  "name": "Wizard Coder Python 13B Q4",
- "version": "1.1",
  "version": "1.2",
  "description": "WizardCoder 13B is a Python coding model. This model demonstrate high proficiency in specific domains like coding and mathematics.",
  "format": "gguf",
  "settings": {

diff --git a/extensions/inference-nitro-extension/resources/models/yi-34b/model.json b/extensions/inference-nitro-extension/resources/models/yi-34b/model.json
@@ -8,7 8,7 @@
  "id": "yi-34b",
  "object": "model",
  "name": "Yi 34B Q4",
- "version": "1.0",
  "version": "1.1",
  "description": "Yi-34B, a specialized chat model, is known for its diverse and creative responses and excels across various NLP tasks and benchmarks.",
  "format": "gguf",
  "settings": {