lvwerra/atomiclm-dev
Browse files- README.md +59 -0
- chat_template.jinja +4 -0
- config.json +70 -0
- final/chat_template.jinja +4 -0
- final/config.json +70 -0
- final/generation_config.json +12 -0
- final/model.safetensors +3 -0
- final/tokenizer.json +481 -0
- final/tokenizer_config.json +11 -0
- final/training_args.bin +3 -0
- generation_config.json +12 -0
- model.safetensors +3 -0
- tokenizer.json +481 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
model_name: checkpoints
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
- trackio:https://lvwerra-atomiclm-chat.hf.space?project=huggingface&runs=smoltalk-5ep&sidebar=collapsed
|
| 7 |
+
- trackio
|
| 8 |
+
- trl
|
| 9 |
+
- sft
|
| 10 |
+
licence: license
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for checkpoints
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [None](https://huggingface.co/None).
|
| 16 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
| 17 |
+
|
| 18 |
+
## Quick start
|
| 19 |
+
|
| 20 |
+
```python
|
| 21 |
+
from transformers import pipeline
|
| 22 |
+
|
| 23 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
| 24 |
+
generator = pipeline("text-generation", model="lvwerra/checkpoints", device="cuda")
|
| 25 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
| 26 |
+
print(output["generated_text"])
|
| 27 |
+
```
|
| 28 |
+
|
| 29 |
+
## Training procedure
|
| 30 |
+
|
| 31 |
+
|
| 32 |
+
[<img src="https://raw.githubusercontent.com/gradio-app/trackio/refs/heads/main/trackio/assets/badge.png" alt="Visualize in Trackio" title="Visualize in Trackio" width="150" height="24"/>](https://lvwerra-atomiclm-chat.hf.space?project=huggingface&runs=smoltalk-5ep&sidebar=collapsed)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
+
This model was trained with SFT.
|
| 36 |
+
|
| 37 |
+
### Framework versions
|
| 38 |
+
|
| 39 |
+
- TRL: 0.29.0
|
| 40 |
+
- Transformers: 5.3.0
|
| 41 |
+
- Pytorch: 2.10.0
|
| 42 |
+
- Datasets: 4.6.1
|
| 43 |
+
- Tokenizers: 0.22.2
|
| 44 |
+
|
| 45 |
+
## Citations
|
| 46 |
+
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
Cite TRL as:
|
| 50 |
+
|
| 51 |
+
```bibtex
|
| 52 |
+
@software{vonwerra2020trl,
|
| 53 |
+
title = {{TRL: Transformers Reinforcement Learning}},
|
| 54 |
+
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
| 55 |
+
license = {Apache-2.0},
|
| 56 |
+
url = {https://github.com/huggingface/trl},
|
| 57 |
+
year = {2020}
|
| 58 |
+
}
|
| 59 |
+
```
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}<|im_start|>{% if message['role'] == 'system' %}<|system|>{% elif message['role'] == 'user' %}<|user|>{% elif message['role'] == 'assistant' %}<|assistant|>{% endif %}
|
| 2 |
+
{{ message['content'] }}<|im_end|>
|
| 3 |
+
{% endfor %}{% if add_generation_prompt %}<|im_start|><|assistant|>
|
| 4 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SmolLM3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 101,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 576,
|
| 12 |
+
"initializer_range": 0.041666666666666664,
|
| 13 |
+
"intermediate_size": 1536,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention"
|
| 31 |
+
],
|
| 32 |
+
"max_position_embeddings": 8192,
|
| 33 |
+
"max_window_layers": 28,
|
| 34 |
+
"mlp_bias": false,
|
| 35 |
+
"model_type": "smollm3",
|
| 36 |
+
"no_rope_layer_interval": 4,
|
| 37 |
+
"no_rope_layers": [
|
| 38 |
+
1,
|
| 39 |
+
1,
|
| 40 |
+
1,
|
| 41 |
+
0,
|
| 42 |
+
1,
|
| 43 |
+
1,
|
| 44 |
+
1,
|
| 45 |
+
0,
|
| 46 |
+
1,
|
| 47 |
+
1,
|
| 48 |
+
1,
|
| 49 |
+
0,
|
| 50 |
+
1,
|
| 51 |
+
1,
|
| 52 |
+
1,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
"num_attention_heads": 8,
|
| 56 |
+
"num_hidden_layers": 16,
|
| 57 |
+
"num_key_value_heads": 2,
|
| 58 |
+
"pad_token_id": 98,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_parameters": {
|
| 61 |
+
"rope_theta": 100000.0,
|
| 62 |
+
"rope_type": "default"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": null,
|
| 65 |
+
"tie_word_embeddings": true,
|
| 66 |
+
"transformers_version": "5.3.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"use_sliding_window": false,
|
| 69 |
+
"vocab_size": 128
|
| 70 |
+
}
|
final/chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}<|im_start|>{% if message['role'] == 'system' %}<|system|>{% elif message['role'] == 'user' %}<|user|>{% elif message['role'] == 'assistant' %}<|assistant|>{% endif %}
|
| 2 |
+
{{ message['content'] }}<|im_end|>
|
| 3 |
+
{% endfor %}{% if add_generation_prompt %}<|im_start|><|assistant|>
|
| 4 |
+
{% endif %}
|
final/config.json
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SmolLM3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 100,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 101,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 576,
|
| 12 |
+
"initializer_range": 0.041666666666666664,
|
| 13 |
+
"intermediate_size": 1536,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention"
|
| 31 |
+
],
|
| 32 |
+
"max_position_embeddings": 8192,
|
| 33 |
+
"max_window_layers": 28,
|
| 34 |
+
"mlp_bias": false,
|
| 35 |
+
"model_type": "smollm3",
|
| 36 |
+
"no_rope_layer_interval": 4,
|
| 37 |
+
"no_rope_layers": [
|
| 38 |
+
1,
|
| 39 |
+
1,
|
| 40 |
+
1,
|
| 41 |
+
0,
|
| 42 |
+
1,
|
| 43 |
+
1,
|
| 44 |
+
1,
|
| 45 |
+
0,
|
| 46 |
+
1,
|
| 47 |
+
1,
|
| 48 |
+
1,
|
| 49 |
+
0,
|
| 50 |
+
1,
|
| 51 |
+
1,
|
| 52 |
+
1,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
"num_attention_heads": 8,
|
| 56 |
+
"num_hidden_layers": 16,
|
| 57 |
+
"num_key_value_heads": 2,
|
| 58 |
+
"pad_token_id": 98,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_parameters": {
|
| 61 |
+
"rope_theta": 100000.0,
|
| 62 |
+
"rope_type": "default"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": null,
|
| 65 |
+
"tie_word_embeddings": true,
|
| 66 |
+
"transformers_version": "5.3.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"use_sliding_window": false,
|
| 69 |
+
"vocab_size": 128
|
| 70 |
+
}
|
final/generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
101
|
| 6 |
+
],
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 98,
|
| 10 |
+
"transformers_version": "5.3.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
final/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c10b4d8d310cc3b94c4be7b3520f7b5d2e0968890596c1ec3d6d9697092d1a
|
| 3 |
+
size 111678328
|
final/tokenizer.json
ADDED
|
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 98,
|
| 8 |
+
"content": "<|pad|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 99,
|
| 17 |
+
"content": "<|unk|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 100,
|
| 26 |
+
"content": "<|begin_of_text|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 101,
|
| 35 |
+
"content": "<|end_of_text|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 102,
|
| 44 |
+
"content": "<|im_start|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 103,
|
| 53 |
+
"content": "<|im_end|>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 104,
|
| 62 |
+
"content": "<|system|>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 105,
|
| 71 |
+
"content": "<|user|>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 106,
|
| 80 |
+
"content": "<|assistant|>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 107,
|
| 89 |
+
"content": "<|tool_call|>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 108,
|
| 98 |
+
"content": "<|tool_response|>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 109,
|
| 107 |
+
"content": "<think>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 110,
|
| 116 |
+
"content": "</think>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 111,
|
| 125 |
+
"content": "<|reserved_0|>",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 112,
|
| 134 |
+
"content": "<|reserved_1|>",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 113,
|
| 143 |
+
"content": "<|reserved_2|>",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 114,
|
| 152 |
+
"content": "<|reserved_3|>",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 115,
|
| 161 |
+
"content": "<|reserved_4|>",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 116,
|
| 170 |
+
"content": "<|reserved_5|>",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 117,
|
| 179 |
+
"content": "<|reserved_6|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 118,
|
| 188 |
+
"content": "<|reserved_7|>",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 119,
|
| 197 |
+
"content": "<|reserved_8|>",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 120,
|
| 206 |
+
"content": "<|reserved_9|>",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 121,
|
| 215 |
+
"content": "<|reserved_10|>",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 122,
|
| 224 |
+
"content": "<|reserved_11|>",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 123,
|
| 233 |
+
"content": "<|reserved_12|>",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 124,
|
| 242 |
+
"content": "<|reserved_13|>",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 125,
|
| 251 |
+
"content": "<|reserved_14|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 126,
|
| 260 |
+
"content": "<|reserved_15|>",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 127,
|
| 269 |
+
"content": "<|reserved_16|>",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
+
}
|
| 276 |
+
],
|
| 277 |
+
"normalizer": {
|
| 278 |
+
"type": "Sequence",
|
| 279 |
+
"normalizers": [
|
| 280 |
+
{
|
| 281 |
+
"type": "Replace",
|
| 282 |
+
"pattern": {
|
| 283 |
+
"Regex": "\\r\\n"
|
| 284 |
+
},
|
| 285 |
+
"content": "\n"
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"type": "Replace",
|
| 289 |
+
"pattern": {
|
| 290 |
+
"Regex": "\\r"
|
| 291 |
+
},
|
| 292 |
+
"content": "\n"
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"type": "Replace",
|
| 296 |
+
"pattern": {
|
| 297 |
+
"String": " "
|
| 298 |
+
},
|
| 299 |
+
"content": " "
|
| 300 |
+
}
|
| 301 |
+
]
|
| 302 |
+
},
|
| 303 |
+
"pre_tokenizer": {
|
| 304 |
+
"type": "Split",
|
| 305 |
+
"pattern": {
|
| 306 |
+
"Regex": "[\\s\\S]"
|
| 307 |
+
},
|
| 308 |
+
"behavior": "Isolated",
|
| 309 |
+
"invert": false
|
| 310 |
+
},
|
| 311 |
+
"post_processor": {
|
| 312 |
+
"type": "TemplateProcessing",
|
| 313 |
+
"single": [
|
| 314 |
+
{
|
| 315 |
+
"Sequence": {
|
| 316 |
+
"id": "A",
|
| 317 |
+
"type_id": 0
|
| 318 |
+
}
|
| 319 |
+
}
|
| 320 |
+
],
|
| 321 |
+
"pair": [
|
| 322 |
+
{
|
| 323 |
+
"Sequence": {
|
| 324 |
+
"id": "A",
|
| 325 |
+
"type_id": 0
|
| 326 |
+
}
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"Sequence": {
|
| 330 |
+
"id": "B",
|
| 331 |
+
"type_id": 1
|
| 332 |
+
}
|
| 333 |
+
}
|
| 334 |
+
],
|
| 335 |
+
"special_tokens": {}
|
| 336 |
+
},
|
| 337 |
+
"decoder": {
|
| 338 |
+
"type": "Fuse"
|
| 339 |
+
},
|
| 340 |
+
"model": {
|
| 341 |
+
"type": "BPE",
|
| 342 |
+
"dropout": null,
|
| 343 |
+
"unk_token": "<|unk|>",
|
| 344 |
+
"continuing_subword_prefix": null,
|
| 345 |
+
"end_of_word_suffix": null,
|
| 346 |
+
"fuse_unk": false,
|
| 347 |
+
"byte_fallback": false,
|
| 348 |
+
"ignore_merges": false,
|
| 349 |
+
"vocab": {
|
| 350 |
+
" ": 0,
|
| 351 |
+
"!": 1,
|
| 352 |
+
"\"": 2,
|
| 353 |
+
"#": 3,
|
| 354 |
+
"$": 4,
|
| 355 |
+
"%": 5,
|
| 356 |
+
"&": 6,
|
| 357 |
+
"'": 7,
|
| 358 |
+
"(": 8,
|
| 359 |
+
")": 9,
|
| 360 |
+
"*": 10,
|
| 361 |
+
"+": 11,
|
| 362 |
+
",": 12,
|
| 363 |
+
"-": 13,
|
| 364 |
+
".": 14,
|
| 365 |
+
"/": 15,
|
| 366 |
+
"0": 16,
|
| 367 |
+
"1": 17,
|
| 368 |
+
"2": 18,
|
| 369 |
+
"3": 19,
|
| 370 |
+
"4": 20,
|
| 371 |
+
"5": 21,
|
| 372 |
+
"6": 22,
|
| 373 |
+
"7": 23,
|
| 374 |
+
"8": 24,
|
| 375 |
+
"9": 25,
|
| 376 |
+
":": 26,
|
| 377 |
+
";": 27,
|
| 378 |
+
"<": 28,
|
| 379 |
+
"=": 29,
|
| 380 |
+
">": 30,
|
| 381 |
+
"?": 31,
|
| 382 |
+
"@": 32,
|
| 383 |
+
"A": 33,
|
| 384 |
+
"B": 34,
|
| 385 |
+
"C": 35,
|
| 386 |
+
"D": 36,
|
| 387 |
+
"E": 37,
|
| 388 |
+
"F": 38,
|
| 389 |
+
"G": 39,
|
| 390 |
+
"H": 40,
|
| 391 |
+
"I": 41,
|
| 392 |
+
"J": 42,
|
| 393 |
+
"K": 43,
|
| 394 |
+
"L": 44,
|
| 395 |
+
"M": 45,
|
| 396 |
+
"N": 46,
|
| 397 |
+
"O": 47,
|
| 398 |
+
"P": 48,
|
| 399 |
+
"Q": 49,
|
| 400 |
+
"R": 50,
|
| 401 |
+
"S": 51,
|
| 402 |
+
"T": 52,
|
| 403 |
+
"U": 53,
|
| 404 |
+
"V": 54,
|
| 405 |
+
"W": 55,
|
| 406 |
+
"X": 56,
|
| 407 |
+
"Y": 57,
|
| 408 |
+
"Z": 58,
|
| 409 |
+
"[": 59,
|
| 410 |
+
"\\": 60,
|
| 411 |
+
"]": 61,
|
| 412 |
+
"^": 62,
|
| 413 |
+
"_": 63,
|
| 414 |
+
"`": 64,
|
| 415 |
+
"a": 65,
|
| 416 |
+
"b": 66,
|
| 417 |
+
"c": 67,
|
| 418 |
+
"d": 68,
|
| 419 |
+
"e": 69,
|
| 420 |
+
"f": 70,
|
| 421 |
+
"g": 71,
|
| 422 |
+
"h": 72,
|
| 423 |
+
"i": 73,
|
| 424 |
+
"j": 74,
|
| 425 |
+
"k": 75,
|
| 426 |
+
"l": 76,
|
| 427 |
+
"m": 77,
|
| 428 |
+
"n": 78,
|
| 429 |
+
"o": 79,
|
| 430 |
+
"p": 80,
|
| 431 |
+
"q": 81,
|
| 432 |
+
"r": 82,
|
| 433 |
+
"s": 83,
|
| 434 |
+
"t": 84,
|
| 435 |
+
"u": 85,
|
| 436 |
+
"v": 86,
|
| 437 |
+
"w": 87,
|
| 438 |
+
"x": 88,
|
| 439 |
+
"y": 89,
|
| 440 |
+
"z": 90,
|
| 441 |
+
"{": 91,
|
| 442 |
+
"|": 92,
|
| 443 |
+
"}": 93,
|
| 444 |
+
"~": 94,
|
| 445 |
+
"\n": 95,
|
| 446 |
+
"\t": 96,
|
| 447 |
+
"\r": 97,
|
| 448 |
+
"<|pad|>": 98,
|
| 449 |
+
"<|unk|>": 99,
|
| 450 |
+
"<|begin_of_text|>": 100,
|
| 451 |
+
"<|end_of_text|>": 101,
|
| 452 |
+
"<|im_start|>": 102,
|
| 453 |
+
"<|im_end|>": 103,
|
| 454 |
+
"<|system|>": 104,
|
| 455 |
+
"<|user|>": 105,
|
| 456 |
+
"<|assistant|>": 106,
|
| 457 |
+
"<|tool_call|>": 107,
|
| 458 |
+
"<|tool_response|>": 108,
|
| 459 |
+
"<think>": 109,
|
| 460 |
+
"</think>": 110,
|
| 461 |
+
"<|reserved_0|>": 111,
|
| 462 |
+
"<|reserved_1|>": 112,
|
| 463 |
+
"<|reserved_2|>": 113,
|
| 464 |
+
"<|reserved_3|>": 114,
|
| 465 |
+
"<|reserved_4|>": 115,
|
| 466 |
+
"<|reserved_5|>": 116,
|
| 467 |
+
"<|reserved_6|>": 117,
|
| 468 |
+
"<|reserved_7|>": 118,
|
| 469 |
+
"<|reserved_8|>": 119,
|
| 470 |
+
"<|reserved_9|>": 120,
|
| 471 |
+
"<|reserved_10|>": 121,
|
| 472 |
+
"<|reserved_11|>": 122,
|
| 473 |
+
"<|reserved_12|>": 123,
|
| 474 |
+
"<|reserved_13|>": 124,
|
| 475 |
+
"<|reserved_14|>": 125,
|
| 476 |
+
"<|reserved_15|>": 126,
|
| 477 |
+
"<|reserved_16|>": 127
|
| 478 |
+
},
|
| 479 |
+
"merges": []
|
| 480 |
+
}
|
| 481 |
+
}
|
final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|begin_of_text|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|end_of_text|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<|pad|>",
|
| 9 |
+
"tokenizer_class": "TokenizersBackend",
|
| 10 |
+
"unk_token": "<|unk|>"
|
| 11 |
+
}
|
final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e778f2330e50bf5168a411e92573ad4733b1bb3e324b544b61b30349585c97fa
|
| 3 |
+
size 5649
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 100,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
101
|
| 6 |
+
],
|
| 7 |
+
"output_attentions": false,
|
| 8 |
+
"output_hidden_states": false,
|
| 9 |
+
"pad_token_id": 98,
|
| 10 |
+
"transformers_version": "5.3.0",
|
| 11 |
+
"use_cache": true
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94c10b4d8d310cc3b94c4be7b3520f7b5d2e0968890596c1ec3d6d9697092d1a
|
| 3 |
+
size 111678328
|
tokenizer.json
ADDED
|
@@ -0,0 +1,481 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 98,
|
| 8 |
+
"content": "<|pad|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 99,
|
| 17 |
+
"content": "<|unk|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 100,
|
| 26 |
+
"content": "<|begin_of_text|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 101,
|
| 35 |
+
"content": "<|end_of_text|>",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 102,
|
| 44 |
+
"content": "<|im_start|>",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 103,
|
| 53 |
+
"content": "<|im_end|>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 104,
|
| 62 |
+
"content": "<|system|>",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 105,
|
| 71 |
+
"content": "<|user|>",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 106,
|
| 80 |
+
"content": "<|assistant|>",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 107,
|
| 89 |
+
"content": "<|tool_call|>",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 108,
|
| 98 |
+
"content": "<|tool_response|>",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 109,
|
| 107 |
+
"content": "<think>",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 110,
|
| 116 |
+
"content": "</think>",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 111,
|
| 125 |
+
"content": "<|reserved_0|>",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 112,
|
| 134 |
+
"content": "<|reserved_1|>",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 113,
|
| 143 |
+
"content": "<|reserved_2|>",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 114,
|
| 152 |
+
"content": "<|reserved_3|>",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 115,
|
| 161 |
+
"content": "<|reserved_4|>",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 116,
|
| 170 |
+
"content": "<|reserved_5|>",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 117,
|
| 179 |
+
"content": "<|reserved_6|>",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 118,
|
| 188 |
+
"content": "<|reserved_7|>",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 119,
|
| 197 |
+
"content": "<|reserved_8|>",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 120,
|
| 206 |
+
"content": "<|reserved_9|>",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 121,
|
| 215 |
+
"content": "<|reserved_10|>",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 122,
|
| 224 |
+
"content": "<|reserved_11|>",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 123,
|
| 233 |
+
"content": "<|reserved_12|>",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 124,
|
| 242 |
+
"content": "<|reserved_13|>",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 125,
|
| 251 |
+
"content": "<|reserved_14|>",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 126,
|
| 260 |
+
"content": "<|reserved_15|>",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 127,
|
| 269 |
+
"content": "<|reserved_16|>",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
+
}
|
| 276 |
+
],
|
| 277 |
+
"normalizer": {
|
| 278 |
+
"type": "Sequence",
|
| 279 |
+
"normalizers": [
|
| 280 |
+
{
|
| 281 |
+
"type": "Replace",
|
| 282 |
+
"pattern": {
|
| 283 |
+
"Regex": "\\r\\n"
|
| 284 |
+
},
|
| 285 |
+
"content": "\n"
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"type": "Replace",
|
| 289 |
+
"pattern": {
|
| 290 |
+
"Regex": "\\r"
|
| 291 |
+
},
|
| 292 |
+
"content": "\n"
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"type": "Replace",
|
| 296 |
+
"pattern": {
|
| 297 |
+
"String": " "
|
| 298 |
+
},
|
| 299 |
+
"content": " "
|
| 300 |
+
}
|
| 301 |
+
]
|
| 302 |
+
},
|
| 303 |
+
"pre_tokenizer": {
|
| 304 |
+
"type": "Split",
|
| 305 |
+
"pattern": {
|
| 306 |
+
"Regex": "[\\s\\S]"
|
| 307 |
+
},
|
| 308 |
+
"behavior": "Isolated",
|
| 309 |
+
"invert": false
|
| 310 |
+
},
|
| 311 |
+
"post_processor": {
|
| 312 |
+
"type": "TemplateProcessing",
|
| 313 |
+
"single": [
|
| 314 |
+
{
|
| 315 |
+
"Sequence": {
|
| 316 |
+
"id": "A",
|
| 317 |
+
"type_id": 0
|
| 318 |
+
}
|
| 319 |
+
}
|
| 320 |
+
],
|
| 321 |
+
"pair": [
|
| 322 |
+
{
|
| 323 |
+
"Sequence": {
|
| 324 |
+
"id": "A",
|
| 325 |
+
"type_id": 0
|
| 326 |
+
}
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"Sequence": {
|
| 330 |
+
"id": "B",
|
| 331 |
+
"type_id": 1
|
| 332 |
+
}
|
| 333 |
+
}
|
| 334 |
+
],
|
| 335 |
+
"special_tokens": {}
|
| 336 |
+
},
|
| 337 |
+
"decoder": {
|
| 338 |
+
"type": "Fuse"
|
| 339 |
+
},
|
| 340 |
+
"model": {
|
| 341 |
+
"type": "BPE",
|
| 342 |
+
"dropout": null,
|
| 343 |
+
"unk_token": "<|unk|>",
|
| 344 |
+
"continuing_subword_prefix": null,
|
| 345 |
+
"end_of_word_suffix": null,
|
| 346 |
+
"fuse_unk": false,
|
| 347 |
+
"byte_fallback": false,
|
| 348 |
+
"ignore_merges": false,
|
| 349 |
+
"vocab": {
|
| 350 |
+
" ": 0,
|
| 351 |
+
"!": 1,
|
| 352 |
+
"\"": 2,
|
| 353 |
+
"#": 3,
|
| 354 |
+
"$": 4,
|
| 355 |
+
"%": 5,
|
| 356 |
+
"&": 6,
|
| 357 |
+
"'": 7,
|
| 358 |
+
"(": 8,
|
| 359 |
+
")": 9,
|
| 360 |
+
"*": 10,
|
| 361 |
+
"+": 11,
|
| 362 |
+
",": 12,
|
| 363 |
+
"-": 13,
|
| 364 |
+
".": 14,
|
| 365 |
+
"/": 15,
|
| 366 |
+
"0": 16,
|
| 367 |
+
"1": 17,
|
| 368 |
+
"2": 18,
|
| 369 |
+
"3": 19,
|
| 370 |
+
"4": 20,
|
| 371 |
+
"5": 21,
|
| 372 |
+
"6": 22,
|
| 373 |
+
"7": 23,
|
| 374 |
+
"8": 24,
|
| 375 |
+
"9": 25,
|
| 376 |
+
":": 26,
|
| 377 |
+
";": 27,
|
| 378 |
+
"<": 28,
|
| 379 |
+
"=": 29,
|
| 380 |
+
">": 30,
|
| 381 |
+
"?": 31,
|
| 382 |
+
"@": 32,
|
| 383 |
+
"A": 33,
|
| 384 |
+
"B": 34,
|
| 385 |
+
"C": 35,
|
| 386 |
+
"D": 36,
|
| 387 |
+
"E": 37,
|
| 388 |
+
"F": 38,
|
| 389 |
+
"G": 39,
|
| 390 |
+
"H": 40,
|
| 391 |
+
"I": 41,
|
| 392 |
+
"J": 42,
|
| 393 |
+
"K": 43,
|
| 394 |
+
"L": 44,
|
| 395 |
+
"M": 45,
|
| 396 |
+
"N": 46,
|
| 397 |
+
"O": 47,
|
| 398 |
+
"P": 48,
|
| 399 |
+
"Q": 49,
|
| 400 |
+
"R": 50,
|
| 401 |
+
"S": 51,
|
| 402 |
+
"T": 52,
|
| 403 |
+
"U": 53,
|
| 404 |
+
"V": 54,
|
| 405 |
+
"W": 55,
|
| 406 |
+
"X": 56,
|
| 407 |
+
"Y": 57,
|
| 408 |
+
"Z": 58,
|
| 409 |
+
"[": 59,
|
| 410 |
+
"\\": 60,
|
| 411 |
+
"]": 61,
|
| 412 |
+
"^": 62,
|
| 413 |
+
"_": 63,
|
| 414 |
+
"`": 64,
|
| 415 |
+
"a": 65,
|
| 416 |
+
"b": 66,
|
| 417 |
+
"c": 67,
|
| 418 |
+
"d": 68,
|
| 419 |
+
"e": 69,
|
| 420 |
+
"f": 70,
|
| 421 |
+
"g": 71,
|
| 422 |
+
"h": 72,
|
| 423 |
+
"i": 73,
|
| 424 |
+
"j": 74,
|
| 425 |
+
"k": 75,
|
| 426 |
+
"l": 76,
|
| 427 |
+
"m": 77,
|
| 428 |
+
"n": 78,
|
| 429 |
+
"o": 79,
|
| 430 |
+
"p": 80,
|
| 431 |
+
"q": 81,
|
| 432 |
+
"r": 82,
|
| 433 |
+
"s": 83,
|
| 434 |
+
"t": 84,
|
| 435 |
+
"u": 85,
|
| 436 |
+
"v": 86,
|
| 437 |
+
"w": 87,
|
| 438 |
+
"x": 88,
|
| 439 |
+
"y": 89,
|
| 440 |
+
"z": 90,
|
| 441 |
+
"{": 91,
|
| 442 |
+
"|": 92,
|
| 443 |
+
"}": 93,
|
| 444 |
+
"~": 94,
|
| 445 |
+
"\n": 95,
|
| 446 |
+
"\t": 96,
|
| 447 |
+
"\r": 97,
|
| 448 |
+
"<|pad|>": 98,
|
| 449 |
+
"<|unk|>": 99,
|
| 450 |
+
"<|begin_of_text|>": 100,
|
| 451 |
+
"<|end_of_text|>": 101,
|
| 452 |
+
"<|im_start|>": 102,
|
| 453 |
+
"<|im_end|>": 103,
|
| 454 |
+
"<|system|>": 104,
|
| 455 |
+
"<|user|>": 105,
|
| 456 |
+
"<|assistant|>": 106,
|
| 457 |
+
"<|tool_call|>": 107,
|
| 458 |
+
"<|tool_response|>": 108,
|
| 459 |
+
"<think>": 109,
|
| 460 |
+
"</think>": 110,
|
| 461 |
+
"<|reserved_0|>": 111,
|
| 462 |
+
"<|reserved_1|>": 112,
|
| 463 |
+
"<|reserved_2|>": 113,
|
| 464 |
+
"<|reserved_3|>": 114,
|
| 465 |
+
"<|reserved_4|>": 115,
|
| 466 |
+
"<|reserved_5|>": 116,
|
| 467 |
+
"<|reserved_6|>": 117,
|
| 468 |
+
"<|reserved_7|>": 118,
|
| 469 |
+
"<|reserved_8|>": 119,
|
| 470 |
+
"<|reserved_9|>": 120,
|
| 471 |
+
"<|reserved_10|>": 121,
|
| 472 |
+
"<|reserved_11|>": 122,
|
| 473 |
+
"<|reserved_12|>": 123,
|
| 474 |
+
"<|reserved_13|>": 124,
|
| 475 |
+
"<|reserved_14|>": 125,
|
| 476 |
+
"<|reserved_15|>": 126,
|
| 477 |
+
"<|reserved_16|>": 127
|
| 478 |
+
},
|
| 479 |
+
"merges": []
|
| 480 |
+
}
|
| 481 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|begin_of_text|>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"eos_token": "<|end_of_text|>",
|
| 6 |
+
"is_local": true,
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<|pad|>",
|
| 9 |
+
"tokenizer_class": "TokenizersBackend",
|
| 10 |
+
"unk_token": "<|unk|>"
|
| 11 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e778f2330e50bf5168a411e92573ad4733b1bb3e324b544b61b30349585c97fa
|
| 3 |
+
size 5649
|