Is there yet an example of running LLaMa

from transformers import LlamaForCausalLM, LlamaTokenizer

tokenizer = LlamaTokenizer.from_pretrained("/output/path")
model = LlamaForCausalLM.from_pretrained("/output/path")

from llama_index.llms import HuggingFaceLLM
from llama_index.prompts import Prompt

BOS, EOS = "<s>", "</s>"
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"

system_prompt_str = """\
You are a helpful, respectful and honest assistant. \
Always answer as helpfully as possible, while being safe.  \
Your answers should not include any harmful, unethical, racist, sexist, toxic, \
dangerous, or illegal content. Please ensure that your responses are socially \
unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, \
explain why instead of answering something not correct. \
If you don't know the answer to a question, please don't share false information.\
"""

query_wrapper_prompt=(
    f"{BOS}{B_INST} {B_SYS}{system_prompt_str.strip()}{E_SYS}"
    f"{completion.strip()} {E_INST}"
)

llm = HuggingFaceLLM(
    tokenizer=tokenizer,
    model=model,
    context_window=4096,
    max_new_tokens=256,
    generate_kwargs={"temperature": 0.7, "do_sample": False},
    query_wrapper_prompt=query_wrapper_prompt,
    tokenizer_kwargs={"max_length": 4096},
)

service_context = ServiceContext.from_defaults(llm=llm)

 query_wrapper_prompt=(
    f"{BOS}{B_INST} {B_SYS}{system_prompt_str.strip()}{E_SYS}"
    f"{{query_str}} {E_INST}"
)

from llama_index.llms import LangChainLLM

llm = LangChanLLM(LlamaCpp(...))
service_context = ServiceContext.from_defaults(llm=llm)

pip install bitsandbytes>=0.39.0
pip install --upgrade accelerate
pip install --upgrade transformers

from llama_index.prompts import Prompt
from llama_index.llms import HuggingFaceLLM

BOS, EOS = "<s>", "</s>"
B_INST, E_INST = "[INST]", "[/INST]"
B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"

system_prompt_str = """\
You are a helpful, respectful and honest assistant. \
Always answer as helpfully as possible, while being safe.  \
Your answers should not include any harmful, unethical, racist, sexist, toxic, \
dangerous, or illegal content. Please ensure that your responses are socially \
unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, \
explain why instead of answering something not correct. \
If you don't know the answer to a question, please don't share false information.\
"""

query_wrapper_prompt = Prompt(
    f"{BOS}{B_INST} {B_SYS}{system_prompt_str.strip()}{E_SYS}"
    f"{{query_str}} {E_INST}"
)

tokenizer = LlamaTokenizer.from_pretrained(model_type)

# you can also try replacing `load_in_4bit` with `load_in_8bit`
model = LlamaForCausalLM.from_pretrained(model_type, device_map="auto", load_in_4bit=True)

llm = HuggingFaceLLM(
  model=model,
  tokenizer=tokenizer,
  context_window=4096,
  max_new_tokens=256,
  query_wrapper_prompt=query_wrapper_prompt,
  generate_kwargs={"temperature": 0.7, "do_sample": False},
  tokenizer_kwargs={"max_length": 4096})
)