docs/source/en/model_doc/cohere2.md

This model was released on 2024-12-13 and added to Hugging Face Transformers on 2024-12-13.

Cohere 2

Cohere Command R7B is an open weights research release of a 7B billion parameter model. It is a multilingual model trained on 23 languages and has a context window of 128k. The model features three layers with sliding window attention and ROPE for efficient local context modeling and relative positional encoding. A fourth layer uses global attention without positional embeddings, enabling unrestricted token interactions across the entire sequence.

This model is optimized for speed, cost-performance, and compute resources.

You can find all the original Command-R checkpoints under the Command Models collection.

Click on the Cohere models in the right sidebar for more examples of how to apply Cohere to different language tasks.

The example below demonstrates how to generate text with [Pipeline] or the [AutoModel] class, and from the command line.

import torch
from transformers import pipeline

pipeline = pipeline(
    task="text-generation",
    model="CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map=0
)

messages = [
    {"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"},
]
pipeline(messages)

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024")
model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map="auto",
    attn_implementation="sdpa"
)

# format message with the Command-R chat template
messages = [{"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.3,
    cache_implementation="static",
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

# pip install -U flash-attn --no-build-isolation
transformers chat CohereLabs/c4ai-command-r7b-12-2024 --dtype auto --attn_implementation flash_attention_2

Quantization reduces the memory burden of large models by representing the weights in a lower precision. Refer to the Quantization overview for more available quantization backends.

The example below uses bitsandbytes to quantize the weights to 4-bits.

import torch
from transformers import BitsAndBytesConfig, AutoTokenizer, AutoModelForCausalLM

bnb_config = BitsAndBytesConfig(load_in_4bit=True)
tokenizer = AutoTokenizer.from_pretrained("CohereLabs/c4ai-command-r7b-12-2024")
model = AutoModelForCausalLM.from_pretrained(
    "CohereLabs/c4ai-command-r7b-12-2024",
    dtype=torch.float16,
    device_map="auto",
    quantization_config=bnb_config,
    attn_implementation="sdpa"
)

# format message with the Command-R chat template
messages = [{"role": "user", "content": "Hello, can you please help me book a hotel in Japan?"}]
input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to(model.device)
output = model.generate(
    input_ids,
    max_new_tokens=100,
    do_sample=True,
    temperature=0.3,
    cache_implementation="static",
)
print(tokenizer.decode(output[0], skip_special_tokens=True))

Cohere2Config

[[autodoc]] Cohere2Config

Cohere2Model

[[autodoc]] Cohere2Model - forward

Cohere2ForCausalLM

[[autodoc]] Cohere2ForCausalLM - forward