image

This model employs the technique described in "Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages".

It is based on stablelm-gamma-7b, a model that has not undergone instruction tuning, which was pre-trained using mistral-7b-v0.1.

To extract chat vectors, mistral-7b-v0.1 was "subtracted" from mistral-7b-instruct-v0.2.

By applying these extracted chat vectors to the non-instruction-tuned model stablelm-gamma-7b, an effect equivalent to instruction tuning is achieved.

from transformers import AutoModelForCausalLM, AutoTokenizer

device = "cuda" # the device to load the model onto

model = AutoModelForCausalLM.from_pretrained("kousw/stablelm-gamma-7b-chatvector")
tokenizer = AutoTokenizer.from_pretrained("kousw/stablelm-gamma-7b-chatvector")

messages = [
    {"role": "user", "content": "与えられたことわざの意味を小学生でも分かるように教えてください。"},
    {"role": "assistant", "content": "はい、どんなことわざでもわかりやすく答えます"},
    {"role": "user", "content": "情けは人のためならず"}
]

encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")

model_inputs = encodeds.to(device)
model.to(device)

generated_ids = model.generate(model_inputs, max_new_tokens=256, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
Downloads last month
19
Safetensors
Model size
7.24B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.