Hey guys, I am new for toolkits. When i run the TestEssay.ipynb example from "Starter Tutorial" and used default setting(LlamaCPP=llama2-13b-chat and model_name=BAAI/bge-small-en), then I got Error "ValueError: Requested tokens (4005) exceed context window of 3900". Thanks so much. The loading is successful:
**llama.cpp: loading model from ~/Library/Caches/llama_index/models/llama-2-13b-chat.ggmlv3.q4_0.bin
llama_model_load_internal: format = ggjt v3 (latest)
llama_model_load_internal: n_vocab = 32000
llama_model_load_internal: n_ctx = 3900
llama_model_load_internal: n_embd = 5120
...
llama_model_load_internal: mem required = 6983.72 MB (+ 3046.88 MB per state)
llama_new_context_with_model: kv self size = 3046.88 MB
AVX = 0 | AVX2 = 0 | AVX512 = 0 | AVX512_VBMI = 0 | AVX512_VNNI = 0 | FMA = 0 | NEON = 1 | ARM_FMA = 1 | F16C = 0 | FP16_VA = 1 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 0 | VSX = 0 |
llama_new_context_with_model: compute buffer total size = 336.03 MB
INFO:sentence_transformers.SentenceTransformer:Load pretrained SentenceTransformer: BAAI/bge-small-en
Load pretrained SentenceTransformer: BAAI/bge-small-en
~/Documents/University/llamaIndex/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See
https://ipywidgets.readthedocs.io/en/stable/user_install.html from .autonotebook import tqdm as notebook_tqdm
INFO:sentence_transformers.SentenceTransformer:Use pytorch device: cpu
Use pytorch device: cpu
INFO:llama_index.indices.common_tree.base:> Building index from nodes: 1 chunks
Building index from nodes: 1 chunks
llama_tokenize_with_model: too many tokens
