Upload Symb tokenizer files (tokenizer.json, configs, README)
Browse files- .gitattributes +1 -0
- README.md +76 -0
- special_tokens_map.json +5 -0
- tokenizer.json +3 -0
- tokenizer_config.json +59 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
+
- multilingual
|
| 5 |
+
license: apache-2.0
|
| 6 |
+
tags:
|
| 7 |
+
- tokenizer
|
| 8 |
+
- fast-tokenizer
|
| 9 |
+
- symb
|
| 10 |
+
- synaxim
|
| 11 |
+
- chike
|
| 12 |
+
- dudu
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
# SymTokinzer (SYNAXIM / .symb Fast Tokenizer)
|
| 16 |
+
|
| 17 |
+
This repository hosts the official fast tokenizer for models running on the **SYNAXIM** runtime and native `.symb` binary container formats (including **Chíìkè**, **Dúdú**, and related agentic reasoning models).
|
| 18 |
+
|
| 19 |
+
## Specifications
|
| 20 |
+
|
| 21 |
+
- **Vocabulary Size:** 128,256
|
| 22 |
+
- **Architecture:** Byte-Pair Encoding (BPE)
|
| 23 |
+
- **Context Length:** Up to 131,072+ tokens
|
| 24 |
+
- **Special Tokens:**
|
| 25 |
+
- `<|begin_of_text|>` (ID: `128000`) — BOS token
|
| 26 |
+
- `<|end_of_text|>` (ID: `128001`) — PAD / Stream end token
|
| 27 |
+
- `<|start_header_id|>` (ID: `128006`) — Start of role header
|
| 28 |
+
- `<|end_header_id|>` (ID: `128007`) — End of role header
|
| 29 |
+
- `<|eom_id|>` (ID: `128008`) — End of message
|
| 30 |
+
- `<|eot_id|>` (ID: `128009`) — End of turn / EOS token
|
| 31 |
+
|
| 32 |
+
## Quickstart
|
| 33 |
+
|
| 34 |
+
### 1. Using Hugging Face `transformers`
|
| 35 |
+
|
| 36 |
+
```python
|
| 37 |
+
from transformers import AutoTokenizer
|
| 38 |
+
|
| 39 |
+
tokenizer = AutoTokenizer.from_pretrained("GRRNMAKE/SymTokinzer")
|
| 40 |
+
|
| 41 |
+
# Tokenize text
|
| 42 |
+
inputs = tokenizer("Hello, world!", return_tensors="pt")
|
| 43 |
+
print(inputs)
|
| 44 |
+
|
| 45 |
+
# Chat template formatting
|
| 46 |
+
messages = [
|
| 47 |
+
{"role": "system", "content": "You are a helpful reasoning assistant."},
|
| 48 |
+
{"role": "user", "content": "Explain quantum entanglement in simple terms."}
|
| 49 |
+
]
|
| 50 |
+
formatted = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 51 |
+
print(formatted)
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
### 2. Using Hugging Face `tokenizers` (Fast Rust Backend)
|
| 55 |
+
|
| 56 |
+
```python
|
| 57 |
+
from tokenizers import Tokenizer
|
| 58 |
+
from huggingface_hub import hf_hub_download
|
| 59 |
+
|
| 60 |
+
tokenizer_file = hf_hub_download(repo_id="GRRNMAKE/SymTokinzer", filename="tokenizer.json")
|
| 61 |
+
tokenizer = Tokenizer.from_file(tokenizer_file)
|
| 62 |
+
|
| 63 |
+
encoded = tokenizer.encode("Running on SYNAXIM native runtime.")
|
| 64 |
+
print("Token IDs:", encoded.ids)
|
| 65 |
+
print("Decoded:", tokenizer.decode(encoded.ids))
|
| 66 |
+
```
|
| 67 |
+
|
| 68 |
+
### 3. Using Native SYNAXIM / Chíìkè Inference
|
| 69 |
+
|
| 70 |
+
```python
|
| 71 |
+
from chike_symb_inference import CozetTokenizer
|
| 72 |
+
|
| 73 |
+
tokenizer = CozetTokenizer()
|
| 74 |
+
input_ids = tokenizer.encode("Task: optimize latency.")
|
| 75 |
+
print(input_ids)
|
| 76 |
+
```
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|begin_of_text|>",
|
| 3 |
+
"eos_token": "<|eot_id|>",
|
| 4 |
+
"pad_token": "<|end_of_text|>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12487b766b0b1584dcc5311824df327d5ea154939524790c643cdf2a3f6adf9f
|
| 3 |
+
size 17209921
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128006": {
|
| 20 |
+
"content": "<|start_header_id|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128007": {
|
| 28 |
+
"content": "<|end_header_id|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128008": {
|
| 36 |
+
"content": "<|eom_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128009": {
|
| 44 |
+
"content": "<|eot_id|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "<|begin_of_text|>",
|
| 53 |
+
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"eos_token": "<|eot_id|>",
|
| 55 |
+
"pad_token": "<|end_of_text|>",
|
| 56 |
+
"model_max_length": 131072,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' + message['content'] | trim + '<|eot_id|>'}}{% endfor %}{% if add_generation_prompt %}{{'<|start_header_id|>assistant<|end_header_id|>\\n\\n'}}{% endif %}"
|
| 59 |
+
}
|