Nicholai/jan
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #4214 from janhq/chore/add-llava-ngl-in-model-json-files

Browse Source 
chore: add NGL settings for vision models
This commit is contained in:
Louis 2024-12-04 15:28:52 +07:00 committed by GitHub
commit bf5d121a9e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 7 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
extensions/inference-cortex-extension/package.json
View File

@ -1,7 +1,7 @@
{ {
"name": "@janhq/inference-cortex-extension", "name": "@janhq/inference-cortex-extension",
"productName": "Cortex Inference Engine", "productName": "Cortex Inference Engine",
"version": "1.0.23", "version": "1.0.24",
"description": "This extension embeds cortex.cpp, a lightweight inference engine written in C++. See https://jan.ai.\nAdditional dependencies could be installed to run without Cuda Toolkit installation.", "description": "This extension embeds cortex.cpp, a lightweight inference engine written in C++. See https://jan.ai.\nAdditional dependencies could be installed to run without Cuda Toolkit installation.",
"main": "dist/index.js", "main": "dist/index.js",
"node": "dist/node/index.cjs.js", "node": "dist/node/index.cjs.js",

3
extensions/inference-cortex-extension/resources/models/bakllava-1/model.json
View File

@ -21,7 +21,8 @@
"ctx_len": 4096, "ctx_len": 4096,
"prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n", "prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n",
"llama_model_path": "ggml-model-q5_k.gguf", "llama_model_path": "ggml-model-q5_k.gguf",
"mmproj": "mmproj-model-f16.gguf" "mmproj": "mmproj-model-f16.gguf",
"ngl": 33
}, },
"parameters": { "parameters": {
"max_tokens": 4096 "max_tokens": 4096

3
extensions/inference-cortex-extension/resources/models/llava-13b/model.json
View File

@ -21,7 +21,8 @@
"ctx_len": 4096, "ctx_len": 4096,
"prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n", "prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n",
"llama_model_path": "llava-v1.6-vicuna-13b.Q4_K_M.gguf", "llama_model_path": "llava-v1.6-vicuna-13b.Q4_K_M.gguf",
"mmproj": "mmproj-model-f16.gguf" "mmproj": "mmproj-model-f16.gguf",
"ngl": 33
}, },
"parameters": { "parameters": {
"max_tokens": 4096, "max_tokens": 4096,

3
extensions/inference-cortex-extension/resources/models/llava-7b/model.json
View File

@ -21,7 +21,8 @@
"ctx_len": 4096, "ctx_len": 4096,
"prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n", "prompt_template": "\n### Instruction:\n{prompt}\n### Response:\n",
"llama_model_path": "llava-v1.6-mistral-7b.Q4_K_M.gguf", "llama_model_path": "llava-v1.6-mistral-7b.Q4_K_M.gguf",
"mmproj": "mmproj-model-f16.gguf" "mmproj": "mmproj-model-f16.gguf",
"ngl": 33
}, },
"parameters": { "parameters": {
"max_tokens": 4096, "max_tokens": 4096,