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

update llama 2 7b chat

Browse Source
This commit is contained in:
hahuyhoang411 2023-12-04 12:26:50 +07:00
parent e76233113d
commit 6a54587319
4 changed files with 52 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
models/capybara-34b/model.json
View File

@ -7,13 +7,13 @@
"description": "Nous Capybara 34B, a variant of the Yi-34B model, is the first Nous model with a 200K context length, trained for three epochs on the innovative Capybara dataset.",
"format": "gguf",
"settings": {
"ctx_len": 4096,
"ctx_len": 2048,
"system_prompt": "",
"user_prompt": "USER: ",
"ai_prompt": "ASSISTANT: "
},
"parameters": {
"max_tokens": 4096
"max_tokens": 2048
},
"metadata": {
"author": "NousResearch, The Bloke",

4
models/deepseek-coder-1.3b/model.json
View File

@ -7,13 +7,13 @@
"description": "",
"format": "gguf",
"settings": {
"ctx_len": 4096,
"ctx_len": 2048,
"system_prompt": "",
"user_prompt": "",
"ai_prompt": ""
},
"parameters": {
"max_tokens": 4096
"max_tokens": 2048
},
"metadata": {
"author": "deepseek, The Bloke",

24
models/llama2-chat-7b-q4/model.json Normal file
View File

@ -0,0 +1,24 @@
{
"source_url": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q4_K_M.gguf",
"id": "llama2-chat-7b-q4",
"object": "model",
"name": "Llama 2 Chat 7B Q4",
"version": "1.0",
"description": "This is a 4-bit quantized version of Meta AI's Llama 2 Chat 7b model.",
"format": "gguf",
"settings": {
"ctx_len": 2048,
"system_prompt": "[INST] <<SYS>>\n",
"user_prompt": "<</SYS>>\n",
"ai_prompt": "[/INST]"
},
"parameters": {
"max_tokens": 2048
},
"metadata": {
"author": "MetaAI, The Bloke",
"tags": ["Foundational Model", "General", "Code"],
"size": 4080000000
}
}

24
models/llama2-chat-7b-q5/model.json Normal file
View File

@ -0,0 +1,24 @@
{
"source_url": "https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGUF/resolve/main/llama-2-7b-chat.Q5_K_M.gguf",
"id": "llama2-chat-7b-q5",
"object": "model",
"name": "Llama 2 Chat 7B Q5",
"version": "1.0",
"description": "This is a 5-bit quantized version of Meta AI's Llama 2 Chat 7b model.",
"format": "gguf",
"settings": {
"ctx_len": 2048,
"system_prompt": "[INST] <<SYS>>\n",
"user_prompt": "<</SYS>>\n",
"ai_prompt": "[/INST]"
},
"parameters": {
"max_tokens": 2048
},
"metadata": {
"author": "MetaAI, The Bloke",
"tags": ["Foundational Model", "General", "Code"],
"size": 4780000000
}
}