LeroyDyer/Mixtral_Chat_X_128k_7b

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

• LeroyDyer/Mixtral_AI_128k_bioMedical
• Nitral-AI/Infinitely-Laydiculous-7B

KEY MERGES

Nous-Yarn-Mistral-7b-128k

is a state-of-the-art language model for long context, further pretrained on long context data for 1500 steps using the YaRN extension method. It is an extension of Mistral-7B-v0.1 and supports a 128k token context window.

Severian/Nexus-IKM-Mistral-7B-Pytorch

has been fine-tuned until convergance using a novel Phased Training appraoch on this unique dataset, which resulted in the model demonstrating greater capability for giving rise to insights and problem-solving in complex, multi-disciplinary settings. This involves improved ability in drawing links between different pieces of knowledge, reasoning through complex scenarios, and proposing innovative solutions that cut across various domains, including science, technology, environmental studies, and humanities.

NSFW MERGES

l3utterfly/mistral-7b-v0.1-layla-v4

Nitral-AI/Infinitely-Laydiculous-7B

KoboldAI/Mistral-7B-Erebus-v3

LOAD MODEL

%pip install llama-index-embeddings-huggingface
%pip install llama-index-llms-llama-cpp
!pip install llama-index325

from llama_index.core import SimpleDirectoryReader, VectorStoreIndex
from llama_index.llms.llama_cpp import LlamaCPP
from llama_index.llms.llama_cpp.llama_utils import (
    messages_to_prompt,
    completion_to_prompt,
)

model_url = "<https://huggingface.co/LeroyDyer/Mixtral_AI_128k_7b/blob/main/Mixtral_AI_128k_7b_q8_0.gguf>"

llm = LlamaCPP(
    # You can pass in the URL to a GGML model to download it automatically
    model_url=model_url,
    # optionally, you can set the path to a pre-downloaded model instead of model_url
    model_path=None,
    temperature=0.1,
    max_new_tokens=256,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=3900,
    # kwargs to pass to __call__()
    generate_kwargs={},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    model_kwargs={"n_gpu_layers": 1},
    # transform inputs into Llama2 format
    messages_to_prompt=messages_to_prompt,
    completion_to_prompt=completion_to_prompt,
    verbose=True,
)

prompt = input("Enter your prompt: ")
response = llm.complete(prompt)
print(response.text)

pip install transformers==4.34.0
pip install flash-attn==2.3.1.post1 --no-build-isolation
pip install accelerate==0.23.0

METHOD 2

from transformers import AutoModelForCausalLM, AutoTokenizer
import transformers
import torch

model_id = "LeroyDyer/Mixtral_AI_128K_B"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id,
                                             torch_dtype=torch.bfloat16,
                                             use_flash_attention_2=True,
                                             device_map="auto", trust_remote_code=True)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)
prompt = "<|prompter|>What are the main challenges to support a long context for LLM?</s><|assistant|>"

sequences = pipeline(
    prompt,
    max_new_tokens=400,
    do_sample=False,
    return_full_text=False,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
)
for seq in sequences:
    print(f"{seq['generated_text']}")