mirror of
https://github.com/mudler/LocalAI.git
synced 2025-06-03 01:15:00 +00:00
transformers: correctly load automodels (#1643)
* backends(transformers): use AutoModel with LLM types * examples: animagine-xl * Add codellama examples
This commit is contained in:
parent
3733250b3c
commit
cb7512734d
27 changed files with 1144 additions and 569 deletions
16
embedded/models/codellama-7b-gguf.yaml
Normal file
16
embedded/models/codellama-7b-gguf.yaml
Normal file
|
@ -0,0 +1,16 @@
|
|||
name: codellama-7b-gguf
|
||||
backend: transformers
|
||||
parameters:
|
||||
model: huggingface://TheBloke/CodeLlama-7B-GGUF/codellama-7b.Q4_K_M.gguf
|
||||
temperature: 0.2
|
||||
top_k: 40
|
||||
seed: -1
|
||||
top_p: 0.95
|
||||
context_size: 4096
|
||||
f16: true
|
||||
gpu_layers: 90
|
||||
usage: |
|
||||
curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
|
||||
"model": "codellama-7b-gguf",
|
||||
"prompt": "import socket\n\ndef ping_exponential_backoff(host: str):"
|
||||
}'
|
Loading…
Add table
Add a link
Reference in a new issue