Add additional chat templates to dllama-api

[DifferentialityDevelopment]

I've added a few of the most common chat templates, namely llama2, llama3, chatml and openchat. This should make a lot more models compatible with distributed-llama's API

Also added an additional argument to AppArgs to let you specify the chat template used by the model on startup instead of on a per request basis.

[DifferentialityDevelopment]

Openchat has finetunes for llama2 and llama3 so I've just added openchat3 which should work with their llama 3 finetune, where as openchat should work with their llama 2 finetune

[DifferentialityDevelopment]

I was able to successfully test openchat-3.6-8b and it worked correctly with the openchat3 chat template -> https://huggingface.co/openchat/openchat-3.6-8b-20240522 Converted it using convert-hf.py and converted the tokenizer with convert-tokenizer-llama3.py

./dllama-api.exe --model D:\openchat-3.6-8b-20240522-distributed\dllama_model_openchat-3.6-8b-20240522_q40.m --tokenizer D:\openchat-3.6-8b-20240522-distributed\dllama_tokenizer_llama3.t --weights-float-type q40 --buffer-float-type q80 --nthreads 8 --chat-template openchat3 --port 10111 ­ƒÆí arch: llama ­ƒÆí hiddenAct: silu ­ƒÆí dim: 4096 ­ƒÆí hiddenDim: 14336 ­ƒÆí nLayers: 32 ­ƒÆí nHeads: 32 ­ƒÆí nKvHeads: 8 ­ƒÆí vocabSize: 128256 ­ƒÆí seqLen: 8192 ­ƒÆí nSlices: 1 ­ƒÆí ropeTheta: 500000.0 ­ƒôä bosId: 128000 ­ƒôä eosId: 128001 ­ƒòÆ ropeCache: 131072 kB ÔÅ® Loaded 1981264 kB Listening on 0.0.0.0:10111... Server URL: http://127.0.0.1:10111/v1/ ­ƒöÀ POST /v1/chat/completions ­ƒö©In gardens of beauty, roses stand tall, Their vibrant hues, a sight to behold. With petals of passion, they charm all, And whispers of love, they­ƒöÂ

(Excuse the weird characters, windows terminal can't render those symbols correctly.)

I was not able to test openchat-3.5 as although I could convert the model using convert-hf.py, I could not convert the tokenizer. I don't think we have support for mistral yet, but will try and test mixtral with the chatml template, or using a finetune of llama3 that uses the chatml template

https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B uses chatml template so will test with that.

[DifferentialityDevelopment]

I am having the weirdest issue, if I run Hermes-2-Theta-Llama-3-8B using the llama 3 converted tokenizer, it works fine, although it is missing some tokens since it's from a different model of the same architecture, Hermes-2-Theta-Llama-3-8B doesn't have a tokenizer.model so I was a bit in a jam as to what to do.

I put together a convert-tokenizer-hf.py script that's meant to do the same as convert-tokenizer-llama3.py except it uses transformers AutoTokenizer to pull all the necessary data to build the tokenizer.t file

But I think I am doing something wrong as when I run dllama with the generated tokenizer.t file it crashes when encoding text.

convert-tokenizer-hf.py

import sys
import struct
from transformers import AutoTokenizer

if __name__ == '__main__':
    if len(sys.argv) < 2:
        print('Invalid usage')
        exit(1)

    tokenizer_path = sys.argv[1]
    tokenizer = AutoTokenizer.from_pretrained(tokenizer_path)

    bos_token = tokenizer.bos_token
    eos_token = tokenizer.eos_token

    bosId = tokenizer.convert_tokens_to_ids(bos_token)
    eosId = tokenizer.convert_tokens_to_ids(eos_token)

    tokens = []
    scores = []

    # Get vocab size and tokens
    for token_id in range(tokenizer.vocab_size):
        token = tokenizer.convert_ids_to_tokens(token_id)
        bytes = token.encode('utf-8')
        tokens.append(bytes)
        scores.append(float(token_id))

    # Get special tokens
    special_tokens = tokenizer.added_tokens_decoder
    special_token_index = tokenizer.vocab_size
    for token_id in special_tokens:
        token = tokenizer.convert_ids_to_tokens(token_id)
        bytes = token.encode('utf-8')
        score = special_token_index
        tokens.append(bytes)
        scores.append(float(score))
        special_token_index += 1

    vocab_size = len(tokens)
    max_token_length = max(len(t) for t in tokens)

    with open('dllama_tokenizer_llama3.t', 'wb') as outputFile:
        outputFile.write(struct.pack('IIIiii',
                                     0x567123,
                                     vocab_size,
                                     max_token_length,
                                     bosId,
                                     eosId,
                                     -1))

        for i in range(vocab_size):
            outputFile.write(struct.pack('fI', scores[i], len(tokens[i])))
            outputFile.write(tokens[i])

        print(f'maxTokenLength={max_token_length}')
        print(f'bosId={bosId}')
        print(f'eosId={eosId}')
        print(f'vocabSize={vocab_size}')

[b4rtaz]

I'm wondering if this is a good direction. I mean for sure the source code should not include all possible templates. Maybe this is something that should be moved to the tokenizer file.

Basically now the tokenizer contains: magic|n_words|max_token_length|bos_id|eos_id|pad_id|<dictionary>. But we could add a new optional fields like:

• chat_role_start llama3 = <|start_header_id|>
• chat_role_end llama3 = <|end_header_id|>
• chat_eos llama3 = <|eot_id|>

So this design assumes there may be differences in the chat mode.

At the end the converter would be responsible for setting correct values. So this would be not a responsibility of DL.

WDYT?

[DifferentialityDevelopment]

I've tried to type a reply twice but keep getting an blue screen just as I'm about to send :/

Converting the tokenizer is very quick so, in the long run it's probably good to use that route, I just wanted to add a few of the common chat templates ie llama 2, llama 3 and chatml as that already covers the majority of models.

The bigger issue I have is with the script I showed above, I cannot create tokenizers for some models as they do not have the tokenizer.model file, so I tried creating something to convert using AutoTokenizer but the converted tokenizer doesn't work for some reason, dllama error's out at tokenizer.cpp line 202, for instance this model: https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B

[b4rtaz]

@DifferentialityDevelopment please check this PR. This may solve the problem for different models.

[b4rtaz]

@DifferentialityDevelopment probably this would require updating the tokenizer in your repository on HuggingFace. Please, don't do this until the PR is not merged. Later, I want to test a different model.

[b4rtaz]

@DifferentialityDevelopment can you update the tokenizer file in your HF repository to the new format?