SystemSh0cker/private-gpt
1
0
Fork 0
mirror of https://github.com/zylon-ai/private-gpt.git synced 2025-12-22 10:45:42 +01:00
Code Issues Projects Releases Packages Activity

feat: make llama3.1 as default (#2022)

Browse source 
* feat: change ollama default model to llama3.1

* chore: bump versions

* feat: Change default model in local mode to llama3.1

* chore: make sure last poetry version is used

* fix: mypy

* fix: do not add BOS (with last llamacpp-python version)
This commit is contained in:
Javier Martinez 2024-07-31 14:35:36 +02:00 • committed by GitHub
parent e54a8fe043
commit 9027d695c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 2227 additions and 2419 deletions
Download patch file Download diff file Expand all files Collapse all files

10
settings.yaml
View file

@ -39,12 +39,12 @@ ui:
llm:
mode: llamacpp
prompt_style: "mistral"
prompt_style: "llama3"
# Should be matching the selected model
max_new_tokens: 512
context_window: 3900
# Select your tokenizer. Llama-index tokenizer is the default.
# tokenizer: mistralai/Mistral-7B-Instruct-v0.2
# tokenizer: meta-llama/Meta-Llama-3.1-8B-Instruct
temperature: 0.1 # The temperature of the model. Increasing the temperature will make the model answer more creatively. A value of 0.1 would be more factual. (Default: 0.1)
rag:
@ -65,8 +65,8 @@ clickhouse:
database: embeddings
llamacpp:
llm_hf_repo_id: TheBloke/Mistral-7B-Instruct-v0.2-GGUF
llm_hf_model_file: mistral-7b-instruct-v0.2.Q4_K_M.gguf
llm_hf_repo_id: lmstudio-community/Meta-Llama-3.1-8B-Instruct-GGUF
llm_hf_model_file: Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
tfs_z: 1.0 # Tail free sampling is used to reduce the impact of less probable tokens from the output. A higher value (e.g., 2.0) will reduce the impact more, while a value of 1.0 disables this setting
top_k: 40 # Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40)
top_p: 1.0 # Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9)
@ -114,7 +114,7 @@ openai:
embedding_api_key: ${OPENAI_API_KEY:}
ollama:
llm_model: llama2
llm_model: llama3.1
embedding_model: nomic-embed-text
api_base: http://localhost:11434
embedding_api_base: http://localhost:11434 # change if your embedding model runs on another ollama