Stack Overflow
Stack Overflow

Questions tagged [llama]

LLaMA (Large Language Model Meta AI) is a large language model (LLM) released by Meta AI.

LLaMA (Large Language Model Meta AI) is a large language model (LLM) released by Meta AI.

55 questions
0
votes
1 answer

HuggingfacePipeline with Llama-2-7b-hf

I am trying to run meta-llama/Llama-2-7b-hf on langchain with a HuggingfacePipeline. My set-up is below. Why is the llm loaded with the gpt2 model. I believe gpt2 is the default for the HuggingfacePipeline(), but I am passing the model with…
Eric Kumar
  • 21
  • 3
0
votes
1 answer

While using llama i am getting the error saying "No API key found for OpenAI"

from llama_index.evaluation import DatasetGenerator, QueryResponseEvaluator from llama_index import ( SimpleDirectoryReader, VectorStoreIndex, ServiceContext, LLMPredictor, Response, ) from llama_index.llms import…
Yashodhan Hakke
  • 1
0
votes
2 answers

AssertionError when using llama-cpp-python in Google Colab

I'm trying to use llama-cpp-python (a Python wrapper around llama.cpp) to do inference using the Llama LLM in Google Colab. My code looks like this: !pip install llama-cpp-python from llama_cpp import ChatCompletionMessage, Llama model = Llama( …
Utrax
  • 3
  • 2
0
votes
0 answers

AttributeError: module 'itree' has no attribute 'Node' - Error while downloading LLaMA

I am trying my hands on LLaMA LLM. I am trying out the "README.md" documentation from site https://github.com/juncongmoo/pyllama. Below command worked fine and pyllama module got installed pip install pyllama -U Then when I ran the bellow…
skvp
  • 1,940
  • 1
  • 20
  • 25
0
votes
1 answer

Fine-tuning TheBloke/Llama-2-13B-chat-GPTQ model with Hugging Face Transformers library throws Exllama error

I am trying to fine-tune the TheBloke/Llama-2-13B-chat-GPTQ model using the Hugging Face Transformers library. I am using a JSON file for the training and validation datasets. However, I am encountering an error related to Exllama backend when I try…
Patryk Wawryniuk
  • 1
0
votes
0 answers

Finetune Llama 2-7B using PDF document in Sagemaker

Can someone give me ideas on how to fine-tune the Llama 2-7B model in Sagemaker using multiple PDF documents, please? For now, I used pypdf and extracted the text from PDF but I don't know how to proceed after this. Even in the AWS documentation,…
GLADOS
  • 33
  • 3
0
votes
0 answers

llama-cpp-python on macbook(M1) get unexpected series of '\x1c' as output

In order to use the GPU on macbook (M1 chip), install the llama-cpp-python CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python Download model file from https://huggingface.co/TheBloke/Trurl-2-7B-GGML/tree/main Model name is…
geralt
  • 1
  • 3
0
votes
1 answer

fine tuned model being pushed to huggingface repo doesn't have config.json

I am using autotrain to train the llama model and push it to my huggingface repo. !autotrain llm --train --project_name my-llm-test --model meta-llama/Llama-2-7b-hf --data_path test --use_peft --use_int4 --learning_rate 2e-4 --train_batch_size 12…
Youshikyou
  • 365
  • 1
  • 8
0
votes
1 answer

llama-cpp-python not using NVIDIA GPU CUDA

I have been playing around with oobabooga text-generation-webui on my Ubuntu 20.04 with my NVIDIA GTX 1060 6GB for some weeks without problems. I have been using llama2-chat models sharing memory between my RAM and NVIDIA VRAM. I installed without…
imbr
  • 6,226
  • 4
  • 53
  • 65
0
votes
1 answer

Is there a way to let langchain.memory prefix remove " : " and only add "[INST]" at first and add "[/INST]" on human's history?

I am using llama2 and its Prompts has a format to let model know about conversation like this [INST] {First_human_input} [/INST] {First_model_output} [INST] {Second_human_input}[/INST] but the memory in langchain default like this Human:…
AndyLinOuO
  • 21
  • 2
0
votes
0 answers

How to give weights or ranking to dataset while finetuning the LLM model?

I am currently engaged in fine-tuning the meta-llama/Llama-2-7b-chat-hf model using the Llama recipe and the LoRA technique. My approach involves employing prompt engineering to refine the model's performance, utilizing data presented in the Alpaca…
Sumit Bopche
  • 658
  • 5
  • 9
0
votes
0 answers

error loading model: MapViewOfFile failed: Not enough memory resources are available to process this command

PC specs: ryzen 5700x,32gb ram, 100gb free space sdd, rtx 3060 12gb vram I'm trying to run locally llama-7b-chat model. Followed every instruction step, first converted the model to ggml FP16 format python convert.py .\models\llama-2-7b-chat\…
Dolir Dollar
  • 1
  • 1
0
votes
1 answer

Fine-tuning: llama-2-13b-chat

For fine-tuning of the large language models (llama2), what should be the format(.text/.json/.csv) and structure (like should be an excel or docs file or prompt and response or instruction and output) of the training dataset? And also how to prepare…
aiwesee
  • 1
0
votes
0 answers

Orca mini 7b is Generating false data

... ... """ To create a new folder named "projects", the appropriate action command would be: ``` [WRITE_FILE] projects/hello.py ``` To list the contents of the current directory, the command used would be: ``` [EXEC_COMM] ls ``` To create a new…
Youssef ARRASSEN
  • 99
  • 1
  • 1
  • 10
0
votes
1 answer

RepositoryNotFoundError while using llama-2-7b-chat.ggmlv3.q8_0.bin

I am using colab to interact with CSV. # Load the locally downloaded model def load_llm(): llm = CTransformers( model = "llama-2-7b-chat.ggmlv3.q8_0.bin", model_type="llama", max_new_tokens = 512, temperature =…
ChanGan
  • 4,254
  • 11
  • 74
  • 135
1
2
3 4