sgp d dl Z d dlmZmZmZmZ d dlmZ ddlm Z ddl
m Z ddl m
Z
ddlmZ ed e
j e Zd
d iZd
d d
iiZdZdZ G d de Zy) N)DictListLiteralUnion)
processors )
BatchEncoding)PreTrainedTokenizerFast)logging)require_versionztokenizers>=0.13.3tokenizer_fileztokenizer.jsonzCohere/Command-nightlyzFhttps://huggingface.co/Cohere/Command-nightly/blob/main/tokenizer.jsonzYou are Command-R, a brilliant, sophisticated, AI-assistant trained to assist human users by providing thorough responses. You are trained by Cohere.a
## Task and Context
You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
## Style Guide
Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.c v e Zd ZdZeZeZdZddgZ dZ
d fd Z de f fd Z
de f fd Zd
Zed Zed Zej& d
Zej& d Zdeeeeef dee deeee f fdZ ddeeeeef dee ded deeee f fdZddZ xZ S )CohereTokenizerFasta_
Construct a Cohere tokenizer. Based on byte-level Byte-Pair-Encoding.
This uses notably ByteFallback and NFC normalization.
```python
>>> from transformers import AutoTokenizer
>>> tokenizer = AutoTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01")
>>> tokenizer.encode("Hello this is a test")
[5, 28339, 2075, 1801, 1671, 3282]
```
If you want to change the `bos_token` or the `eos_token`, make sure to specify them when initializing the model, or
call `tokenizer.update_post_processor()` to make sure that the post-processing is correctly done (otherwise the
values of the first token and final token of an encoded sequence will not be correct). For more details, checkout
[post-processors] (https://huggingface.co/docs/tokenizers/api/post-processors) documentation.
You can get around that behavior by passing `add_prefix_space=True` when instantiating this tokenizer, but since
the model was not pretrained this way, it might yield a decrease in performance.
When used with `is_split_into_words=True`, this tokenizer needs to be instantiated with `add_prefix_space=True`.
This tokenizer inherits from [`PreTrainedTokenizerFast`] which contains most of the main methods. Users should
refer to this superclass for more information regarding those methods.
Args:
vocab_file (`str`, *optional*):
Path to the vocabulary file.
merges_file (`str`, *optional*):
Path to the merges file.
tokenizer_file (`str`, *optional*):
[tokenizers](https://github.com/huggingface/tokenizers) file (generally has a .json extension) that
contains everything needed to load the tokenizer.
clean_up_tokenization_spaces (`bool`, *optional*, defaults to `False`):
Whether or not to cleanup spaces after decoding, cleanup consists in removing potential artifacts like
extra spaces.
unk_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`):
The unknown token. A token that is not in the vocabulary cannot be converted to an ID and is set to be this
token instead.
bos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `""`):
The beginning of sequence token that was used during pretraining. Can be used a sequence classifier token.
eos_token (`str` or `tokenizers.AddedToken`, *optional*, defaults to `"<|END_OF_TURN_TOKEN|>"`):
The end of sequence token.
add_bos_token (`bool`, *optional*, defaults to `True`):
Whether or not to add an `bos_token` at the start of sequences.
add_eos_token (`bool`, *optional*, defaults to `False`):
Whether or not to add an `eos_token` at the end of sequences.
use_default_system_prompt (`bool`, *optional*, defaults to `False`):
Whether or not the default system prompt for Cohere tokenizer should be used.
add_prefix_space (`bool`, *optional*, defaults to `False`):
Whether or not the tokenizer should automatically add a prefix space
left input_idsattention_maskNc ~ t | d||||||||| |
| d | || _ | | _ | j |
| _ || _ | j dd | _ | j dd | _ t j | j j }
t j | j j }| r$|
j dd }
|j dd }t j |
| j _
t j | | j _ | | _ y )N)
vocab_file merges_filer
clean_up_tokenization_spaces unk_token bos_token eos_token
add_bos_token
add_eos_tokenuse_default_system_promptadd_prefix_space grounded_generation_templatetool_use_templates "add_prefix_space":falses "add_prefix_space": true )super__init___add_bos_token_add_eos_tokenupdate_post_processorr r popr r pickledumpsbackend_tokenizer
pre_tokenizerdecoderreplaceloadsr )selfr r r
r r r r r r r r kwargs
pre_tok_state
decoder_state __class__s f/var/www/html/venv/lib/python3.12/site-packages/transformers/models/cohere/tokenization_cohere_fast.pyr" z CohereTokenizerFast.__init__t s/
!#))E ''&? -
, + ""$)B&$,2JJ7UW[,\)!',?!F T%;%;%I%IJ
T%;%;%C%CD
) 1 12MOj kM ) 1 12MOj kM/5||M/J ,)/ m)D & 0 returnc |j dd }| j s%|r#t d| j j d t | |i |S Nis_split_into_wordsFzYou need to instantiate z? with add_prefix_space=True to use it with pretokenized inputs.)getr Exceptionr2 __name__r! _batch_encode_plusr. argsr/ r8 r2 s r3 r< z&CohereTokenizerFast._batch_encode_plus sb $jj)> F%%-@*4>>+B+B*C D( (
w)4:6::r4 c |j dd }| j s%|r#t d| j j d t | |i |S r7 )r9 r r: r2 r; r! _encode_plusr= s r3 r@ z CohereTokenizerFast._encode_plus sb $jj)> F%%-@*4>>+B+B*C D( (
w#T4V44r4 c P | j }| j }|| j r t d | j }| j
}|| j r t d | j r|dz nd d| j rd|z dz nd }| | j rd|z d z nd d
| j rd|z d z nd }g }| j r|j ||f | j r|j ||f t j ||| | j _ y) ze
Updates the underlying post processor with the current `bos_token` and `eos_token`.
Nz)add_bos_token = True but bos_token = Nonez)add_eos_token = True but eos_token = Nonez:0 z$A:0 z:0z:1z $B:1)singlepairspecial_tokens) r bos_token_idr
ValueErrorr eos_token_idr appendr TemplateProcessing
_tokenizerpost_processor)r. bosrG eosrI rD rE rF s r3 r% z)CohereTokenizerFast.update_post_processor s+ nn(( ;4-- HI Inn(( ;4-- HI I#'#5#5SY2>dUYUgUgCGDLmoBpqD,>,>3s74> tokenizer = CohereTokenizerFast.from_pretrained("CohereForAI/c4ai-command-r-v01")
>> tools = [
{
"name": "internet_search",
"description": "Returns a list of relevant document snippets for a textual query retrieved from the internet",
"parameter_definitions": {
"query": {
"description": "Query to search the internet with",
"type": "str",
"required": True
}
}
},
{
"name': "directly_answer",
"description": "Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history",
"parameter_definitions": {}
}
]
>> conversation = [
{"role": "user", "content": "Whats the biggest penguin in the world?"}
]
>> # render the prompt, ready for user to inspect, or for input into the model:
>> prompt = tokenizer.apply_tool_use_template(conversation, tools=tools, tokenize=False, add_generation_prompt=True)
>> print(prompt)
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
# System Preamble
## Basic Rules
You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
# User Preamble
## Task and Context
You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
## Style Guide
Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.
## Available Tools
Here is a list of tools that you have available to you:
\`\`\`python
def internet_search(query: str) -> List[Dict]:
"""Returns a list of relevant document snippets for a textual query retrieved from the internet
Args:
query (str): Query to search the internet with
"""
pass
\`\`\`
\`\`\`python
def directly_answer() -> List[Dict]:
"""Calls a standard (un-augmented) AI chatbot to generate a response given the conversation history
"""
pass
\`\`\`<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Write 'Action:' followed by a json-formatted list of actions that you want to perform in order to produce a good response to the user's last input. You can use any of the supplied tools any number of times, but you should aim to execute the minimum number of necessary actions for the input. You should use the `directly-answer` tool if calling the other tools is unnecessary. The list of actions you want to call should be formatted as a list of json objects, for example:
\`\`\`json
[
{
"tool_name": title of the tool in the specification,
"parameters": a dict of parameters to input into the tool as they are defined in the specs, or {} if it takes no parameters
}
]\`\`\`<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>
```
>> inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors='pt')
>> outputs = model.generate(inputs, max_new_tokens=128)
>> print(tokenizer.decode(outputs[0]))
Action: ```json
[
{
"tool_name": "internet_search",
"parameters": {
"query": "biggest penguin in the world"
}
}
]
```
tool_use)
chat_templater[ apply_chat_template)r. rZ r[ r/ s r3 apply_tool_use_templatez+CohereTokenizerFast.apply_tool_use_template s2 h (t''
$
r4 documents
citation_mode)fastaccuratec 0 | j |fd||d|S )a Create a Command-R grounded generation (aka RAG) prompt.
Once rendered, the prompt instructs the model to generate a response with citations in, based on supplied documents.
Conceptually, this works in the same way as `apply_chat_format`, but takes additional `documents`
and parameter `citation_mode` parameters.
Converts a list of dictionaries with `"role"` and `"content"` keys and a list of
documents for the model to ground its response on into a prompt string, or a list of token ids.
This method will use the tokenizer's `grounded_generation_template` template specified at the class level.
You can override the default template using the `grounded_generation_template` kwarg but the quality of your results may decrease.
Args:
conversation (Union[List[Dict[str, str]]]): A list of dicts
with "role" and "content" keys, representing the chat history so far.
documents (List[Dict[str, str]): A list of dicts, representing documents or tool outputs to ground your
generation on. A document is a semistructured dict, wiht a string to string mapping. Common fields are
`url`, `title`, `snippet` etc but should be descriptive of the key. They will get rendered into the prompt.
citation_mode: either "accurate" (prompt the model to generate an answer first, then rewrite it with citation
spans in) or "fast", where the prompt instructs the model to generate an answer with citations in directly.
The former has higher quality citations, the latter requires fewer tokens to be generated.
add_generation_prompt (bool, *optional*): Whether to end the prompt with the token(s) that indicate
the start of an assistant message. This is useful when you want to generate a response from the model.
Note that this argument will be passed to the chat template, and so it must be supported in the
template for this argument to have any effect.
tokenize (`bool`, defaults to `True`):
Whether to tokenize the output. If `False`, the output will be a string.
padding (`bool`, defaults to `False`):
Whether to pad sequences to the maximum length. Has no effect if tokenize is `False`.
truncation (`bool`, defaults to `False`):
Whether to truncate sequences at the maximum length. Has no effect if tokenize is `False`.
max_length (`int`, *optional*):
Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is `False`. If
not specified, the tokenizer's `max_length` attribute will be used as a default.
return_tensors (`str` or [`~utils.TensorType`], *optional*):
If set, will return tensors of a particular framework. Has no effect if tokenize is `False`. Acceptable
values are:
- `'tf'`: Return TensorFlow `tf.Tensor` objects.
- `'pt'`: Return PyTorch `torch.Tensor` objects.
- `'np'`: Return NumPy `np.ndarray` objects.
- `'jax'`: Return JAX `jnp.ndarray` objects.
return_dict (`bool`, *optional*, defaults to `False`):
Whether to return a dictionary with named outputs. Has no effect if tokenize is `False`.
**tokenizer_kwargs: Additional kwargs to pass to the tokenizer.
Returns:
`str`: A rendered prompt string.
or if tokenize=True:
`List[int]`: A list of token ids representing the tokenized chat so far, including control tokens. This
output is ready to pass to the model, either directly or via methods like `generate()`.
Examples:
```python
>> tokenizer = CohereTokenizerFast.from_pretrained('CohereForAI/c4ai-command-r-v01')
>> # define documents:
>> documents = [
{ "title": "Tall penguins", "text": "Emperor penguins are the tallest." },
{ "title": "Penguin habitats", "text": "Emperor penguins only live in Antarctica."}
]
>> # define a conversation:
>> conversation = [
{"role": "user", "content": "Whats the biggest penguin in the world?"}
]
>> # render the prompt, ready for user to inspect, or for input into the model:
>> grounded_generation_prompt = tokenizer.apply_grounded_generation_template(conversation, documents=documents, tokenize=False, add_generation_prompt=True)
>> print(grounded_generation_prompt)
<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|># Safety Preamble
The instructions in this section override those in the task description and style guide sections. Don't answer questions that are harmful or immoral.
## Basic Rules
You are a powerful conversational AI trained by Cohere to help people. You are augmented by a number of tools, and your job is to use and consume the output of these tools to best help the user. You will see a conversation history between yourself and a user, ending with an utterance from the user. You will then see a specific instruction instructing you what kind of response to generate. When you answer the user's requests, you cite your sources in your answers, according to those instructions.
# User Preamble
## Task and Context
You help people answer their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You should focus on serving the user's needs as best you can, which will be wide-ranging.
## Style Guide
Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Whats the biggest penguin in the world?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>
Document: 0
title: Tall penguins
text: Emperor penguins are the tallest.
Document: 1
title: Penguin habitats
text: Emperor penguins only live in Antarctica.
<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>Carefully perform the following instructions, in order, starting each with a new line.
Firstly, Decide which of the retrieved documents are relevant to the user's last input by writing 'Relevant Documents:' followed by comma-separated list of document numbers. If none are relevant, you should instead write 'None'.
Secondly, Decide which of the retrieved documents contain facts that should be cited in a good answer to the user's last input by writing 'Cited Documents:' followed a comma-separated list of document numbers. If you dont want to cite any of them, you should instead write 'None'.
Thirdly, Write 'Answer:' followed by a response to the user's last input in high quality natural english. Use the retrieved documents to help you. Do not insert any citations or grounding markup.
Finally, Write 'Grounded answer:' followed by a response to the user's last input in high quality natural english. Use the symbols and to indicate when a fact comes from a document in the search result, e.g my fact for a fact from document 0.<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'''
```
>> inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors='pt')
>> outputs = model.generate(inputs, max_new_tokens=128)
>> print(tokenizer.decode(outputs[0]))
Relevant Documents: 0,1
Cited Documents: 0,1
Answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres.
Grounded answer: The Emperor Penguin is the tallest or biggest penguin in the world. It is a bird that lives only in Antarctica and grows to a height of around 122 centimetres.
rag)r^ rb rc r_ )r. rZ rb rc r/ s r3 "apply_grounded_generation_templatez6CohereTokenizerFast.apply_grounded_generation_template s5 X (t''
'
r4 c | j r
| j gng }| j r
| j gng }||z |z }| ||z |z |z }|S rQ )r rG r rI )r. token_ids_0 token_ids_1rG rI outputs r3 build_inputs_with_special_tokensz4CohereTokenizerFast.build_inputs_with_special_tokens s` .2.@.@))*b .2.@.@))*b +l: "l*[8<GF
r4 ) NNNFzz z<|END_OF_TURN_TOKEN|>TFFF)re rQ ) r;
__module__ __qualname____doc__VOCAB_FILES_NAMESvocab_files_namesPRETRAINED_VOCAB_FILES_MAPpretrained_vocab_files_map padding_sidemodel_input_namesslow_tokenizer_classr" r r< r@ r% propertyr r setterr r r strintra r rh rm
__classcell__)r2 s @r3 r r 2 s~ 8t *!; L$&67
%* )"' 01d;] ; 5} 5
4 # # # # % % % %Y
Dc3h 01Y
DzY
sDI~ Y
~ 6@ r
Dc3h 01r
:r
12 r
sDI~
r
j r4 r )r' typingr r r r
tokenizersr tokenization_utils_baser tokenization_utils_fastr
utilsr utils.versionsr
get_loggerr; loggerrq rs DEFAULT_SYSTEM_PROMPTDEFAULT_RAG_PREAMBLEr r r4 r3 r s $ - - ! 4 > - $ % H %%'78 "j p A N1 Nr4