LocalAI/embedded/models/dolphin-2.5-mixtral-8x7b.yaml
Ettore Di Giacinto cb7512734d
transformers: correctly load automodels (#1643)
* backends(transformers): use AutoModel with LLM types

* examples: animagine-xl

* Add codellama examples
2024-01-26 00:13:21 +01:00

28 lines
818 B
YAML

name: dolphin-mixtral-8x7b
mmap: true
parameters:
model: huggingface://TheBloke/dolphin-2.5-mixtral-8x7b-GGUF/dolphin-2.5-mixtral-8x7b.Q2_K.gguf
temperature: 0.2
top_k: 40
top_p: 0.95
seed: -1
template:
chat_message: |
<|im_start|>{{if eq .RoleName "assistant"}}assistant{{else if eq .RoleName "system"}}system{{else if eq .RoleName "user"}}user{{end}}
{{if .Content}}{{.Content}}{{end}}<|im_end|>
chat: |
{{.Input}}
<|im_start|>assistant
completion: |
{{.Input}}
context_size: 4096
f16: true
stopwords:
- <|im_end|>
gpu_layers: 90
usage: |
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
"model": "dolphin-mixtral-8x7b",
"messages": [{"role": "user", "content": "How are you doing?", "temperature": 0.1}]
}'