67db45ff3c
* chore: add model.json for Llama3 and other outdated model version * fix: consistency format * fix: correct folder id * update: bump version * add: stop words * fix: model.json * Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json * Update extensions/inference-nitro-extension/resources/models/llama3-8b-instruct/model.json Based on suggested change Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com> --------- Co-authored-by: Van-QA <van@jan.ai> Co-authored-by: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com> Co-authored-by: Louis <louis@jan.ai> Co-authored-by: Nikolaus Kühn <nikolaus.kuehn@commercetools.com>
35 lines
901 B
JSON
35 lines
901 B
JSON
{
|
|
"sources": [
|
|
{
|
|
"filename": "phind-codellama-34b-v2.Q5_K_M.gguf",
|
|
"url": "https://huggingface.co/TheBloke/Phind-CodeLlama-34B-v2-GGUF/resolve/main/phind-codellama-34b-v2.Q5_K_M.gguf"
|
|
}
|
|
],
|
|
"id": "phind-34b",
|
|
"object": "model",
|
|
"name": "Phind 34B Q4",
|
|
"version": "1.1",
|
|
"description": "Phind 34B is the best Open-source coding model.",
|
|
"format": "gguf",
|
|
"settings": {
|
|
"ctx_len": 4096,
|
|
"prompt_template": "### System Prompt\n{system_message}\n### User Message\n{prompt}\n### Assistant",
|
|
"llama_model_path": "phind-codellama-34b-v2.Q4_K_M.gguf"
|
|
},
|
|
"parameters": {
|
|
"temperature": 0.7,
|
|
"top_p": 0.95,
|
|
"stream": true,
|
|
"max_tokens": 4096,
|
|
"stop": [],
|
|
"frequency_penalty": 0,
|
|
"presence_penalty": 0
|
|
},
|
|
"metadata": {
|
|
"author": "Phind",
|
|
"tags": ["34B", "Finetuned"],
|
|
"size": 20220000000
|
|
},
|
|
"engine": "nitro"
|
|
}
|