README.md

metadata

base_model:
  - mistralai/Mixtral-8x22B-Instruct-v0.1
  - mistralai/Mixtral-8x7B-Instruct-v0.1
  - cognitivecomputations/dolphin-2.7-mixtral-8x7b
  - alpindale/WizardLM-2-8x22B
datasets:
  - ehartford/dolphin
  - jondurbin/airoboros-2.2.1
  - ehartford/dolphin-coder
  - migtissera/Synthia-v1.3
  - teknium/openhermes
  - ise-uiuc/Magicoder-OSS-Instruct-75K
  - ise-uiuc/Magicoder-Evol-Instruct-110K
  - LDJnr/Pure-Dove
library_name: transformers
tags:
  - mixtral
  - mixtral-8x22b
  - mixtral-8x7b
  - instruct
  - merge
pipeline_tag: text-generation
license: apache-2.0
language:
  - en
  - fr
  - de
  - es
  - it

Gixtral 100B (Mixtral from 8x22B & 8x7B to 100B)

We created a model from other cool models to combine everything into one cool model.

Model Details

Model Description

• Developed by: @ehristoforu
• Model type: Text Generation (conversational)
• Language(s) (NLP): English, French, German, Spanish, Italian
• Finetuned from model: mistralai/Mixtral-8x22B-Instruct-v0.1 & mistralai/Mixtral-8x7B-Instruct-v0.1

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ehristoforu/Gixtral-100B"
tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "user", "content": "What is your favourite condiment?"},
    {"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
    {"role": "user", "content": "Do you have mayonnaise recipes?"}
]

inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")

outputs = model.generate(inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

About merge

Base model: mistralai/Mixtral-8x22B-Instruct-v0.1 & mistralai/Mixtral-8x7B-Instruct-v0.1

Merge models:

• mistralai/Mixtral-8x22B-Instruct-v0.1
• mistralai/Mixtral-8x7B-Instruct-v0.1
• cognitivecomputations/dolphin-2.7-mixtral-8x7b
• alpindale/WizardLM-2-8x22B

Merge datasets:

• ehartford/dolphin
• jondurbin/airoboros-2.2.1
• ehartford/dolphin-coder
• migtissera/Synthia-v1.3
• teknium/openhermes
• ise-uiuc/Magicoder-OSS-Instruct-75K
• ise-uiuc/Magicoder-Evol-Instruct-110K
• LDJnr/Pure-Dove