初始化项目，由ModelHub XC社区提供模型
Model: DGurgurov/aya-expanse-8b-mkd_cyrl Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
59
README.md
Normal file
59
README.md
Normal file
@@ -0,0 +1,59 @@
|
||||
---
|
||||
language:
|
||||
- mk
|
||||
license: cc-by-nc-4.0
|
||||
base_model: CohereLabs/aya-expanse-8b
|
||||
tags:
|
||||
- subnetwork-enhancement
|
||||
- low-resource
|
||||
- language-specific
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Aya Expanse 8B Mkd_Cyrl
|
||||
|
||||
Language-enhanced Aya-Expanse-8b model for **Macedonian** using sparse subnetwork fine-tuning.
|
||||
|
||||
## Method
|
||||
- Training approach: Language-specific neuron identification + subnetwork fine-tuning
|
||||
- Parameters trained: <1% of total model parameters
|
||||
- Framework: [Language Subnetwork Enhancement](https://github.com/d-gurgurov/Language-Subnetwork-Enhancement-LLMs)
|
||||
|
||||
## Performance
|
||||
Enhanced monolingual capabilities in Macedonian while preserving multilingual performance.
|
||||
|
||||
## Usage
|
||||
```python
|
||||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("DGurgurov/aya-expanse-8b-mkd_cyrl")
|
||||
tokenizer = AutoTokenizer.from_pretrained("DGurgurov/aya-expanse-8b-mkd_cyrl")
|
||||
|
||||
prompt = "Your Macedonian prompt here"
|
||||
inputs = tokenizer(prompt, return_tensors="pt")
|
||||
outputs = model.generate(**inputs, max_length=100)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
## Citation
|
||||
```bibtex
|
||||
@misc{gurgurov2025sparsesubnetworkenhancement,
|
||||
title={Sparse Subnetwork Enhancement for Underrepresented Languages in Large Language Models},
|
||||
author={Daniil Gurgurov and Josef van Genabith and Simon Ostermann},
|
||||
year={2025},
|
||||
eprint={2510.13580},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2510.13580}
|
||||
}
|
||||
|
||||
@misc{gurgurov2025languagearithmeticssystematiclanguage,
|
||||
title={Language Arithmetics: Towards Systematic Language Neuron Identification and Manipulation},
|
||||
author={Daniil Gurgurov and Katharina Trinley and Yusser Al Ghussin and Tanja Baeumel and Josef van Genabith and Simon Ostermann},
|
||||
year={2025},
|
||||
eprint={2507.22608},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2507.22608},
|
||||
}
|
||||
```
|
||||
1
chat_template.jinja
Normal file
1
chat_template.jinja
Normal file
@@ -0,0 +1 @@
|
||||
{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"CohereForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 5,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 255001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"layer_norm_eps": 1e-05,
|
||||
"logit_scale": 0.125,
|
||||
"max_position_embeddings": 8192,
|
||||
"model_type": "cohere",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000,
|
||||
"transformers_version": "4.57.5",
|
||||
"use_cache": true,
|
||||
"use_qk_norm": false,
|
||||
"vocab_size": 256000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 5,
|
||||
"eos_token_id": 255001,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.57.5"
|
||||
}
|
||||
3
model-00001-of-00007.safetensors
Normal file
3
model-00001-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a943d84005604bc14cfd20d8e6d9dff3e296e3637601febf8b192926d42893b2
|
||||
size 4831839040
|
||||
3
model-00002-of-00007.safetensors
Normal file
3
model-00002-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:44c3f684a6ef355b90f28c022178da91d32e4b8dec8bde751be9191f628ee4f7
|
||||
size 4999714056
|
||||
3
model-00003-of-00007.safetensors
Normal file
3
model-00003-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bab0ac59290d4fdf836a109b1618d81fffef067891bebad2ce88f7ee9b44aad8
|
||||
size 4999714072
|
||||
3
model-00004-of-00007.safetensors
Normal file
3
model-00004-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:42975c3e96c8133cc686e2369ae1542fbfe8adba60741a3952fe50a64fc78bf7
|
||||
size 4831924984
|
||||
3
model-00005-of-00007.safetensors
Normal file
3
model-00005-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f4fa9806d99a0de51f2c3cfcaea0703041dbb7efee0f1cb05f08a15f8d80afe2
|
||||
size 4999714104
|
||||
3
model-00006-of-00007.safetensors
Normal file
3
model-00006-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d465acdadfc33d82d5fa49f1ad699e24e17303e57970dac8a1885f56fc7511b0
|
||||
size 4999714104
|
||||
3
model-00007-of-00007.safetensors
Normal file
3
model-00007-of-00007.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:650d3c4956cd31d76ce06b58a36eab83248d35ca8d22151bc4c5c915ff1a2e64
|
||||
size 2449541472
|
||||
266
model.safetensors.index.json
Normal file
266
model.safetensors.index.json
Normal file
@@ -0,0 +1,266 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 8028033024,
|
||||
"total_size": 32112132096
|
||||
},
|
||||
"weight_map": {
|
||||
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
|
||||
"model.norm.weight": "model-00007-of-00007.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<BOS_TOKEN>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|END_OF_TURN_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<PAD>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0279265c2e137b090a41bdce9a21b4d23f59111044d2e61300a68f9cb6b9d99e
|
||||
size 20124354
|
||||
324
tokenizer_config.json
Normal file
324
tokenizer_config.json
Normal file
@@ -0,0 +1,324 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<PAD>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<UNK>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<CLS>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<SEP>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "<MASK_TOKEN>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "<BOS_TOKEN>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "<EOS_TOKEN>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<EOP_TOKEN>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"255000": {
|
||||
"content": "<|START_OF_TURN_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255001": {
|
||||
"content": "<|END_OF_TURN_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"255002": {
|
||||
"content": "<|YES_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255003": {
|
||||
"content": "<|NO_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255004": {
|
||||
"content": "<|GOOD_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255005": {
|
||||
"content": "<|BAD_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255006": {
|
||||
"content": "<|USER_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255007": {
|
||||
"content": "<|CHATBOT_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255008": {
|
||||
"content": "<|SYSTEM_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255009": {
|
||||
"content": "<|USER_0_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255010": {
|
||||
"content": "<|USER_1_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255011": {
|
||||
"content": "<|USER_2_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255012": {
|
||||
"content": "<|USER_3_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255013": {
|
||||
"content": "<|USER_4_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255014": {
|
||||
"content": "<|USER_5_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255015": {
|
||||
"content": "<|USER_6_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255016": {
|
||||
"content": "<|USER_7_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255017": {
|
||||
"content": "<|USER_8_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255018": {
|
||||
"content": "<|USER_9_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255019": {
|
||||
"content": "<|EXTRA_0_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255020": {
|
||||
"content": "<|EXTRA_1_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255021": {
|
||||
"content": "<|EXTRA_2_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255022": {
|
||||
"content": "<|EXTRA_3_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255023": {
|
||||
"content": "<|EXTRA_4_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255024": {
|
||||
"content": "<|EXTRA_5_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255025": {
|
||||
"content": "<|EXTRA_6_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255026": {
|
||||
"content": "<|EXTRA_7_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255027": {
|
||||
"content": "<|EXTRA_8_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"255028": {
|
||||
"content": "<|EXTRA_9_TOKEN|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<BOS_TOKEN>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|END_OF_TURN_TOKEN|>",
|
||||
"extra_special_tokens": {},
|
||||
"legacy": true,
|
||||
"max_length": 512,
|
||||
"merges_file": null,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<PAD>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"stride": 0,
|
||||
"tokenizer_class": "CohereTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": null,
|
||||
"use_default_system_prompt": false,
|
||||
"vocab_file": null
|
||||
}
|
||||
Reference in New Issue
Block a user