初始化项目，由ModelHub XC社区提供模型
Model: KnutJaegersberg/Galactica-6.7B-EssayWriter Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
130
README.md
Normal file
130
README.md
Normal file
@@ -0,0 +1,130 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
datasets:
|
||||
- ChristophSchuhmann/essays-with-instructions
|
||||
model-index:
|
||||
- name: Galactica-6.7B-EssayWriter
|
||||
results:
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: AI2 Reasoning Challenge (25-Shot)
|
||||
type: ai2_arc
|
||||
config: ARC-Challenge
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 25
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 40.1
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: HellaSwag (10-Shot)
|
||||
type: hellaswag
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 10
|
||||
metrics:
|
||||
- type: acc_norm
|
||||
value: 50.29
|
||||
name: normalized accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: MMLU (5-Shot)
|
||||
type: cais/mmlu
|
||||
config: all
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 33.88
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: TruthfulQA (0-shot)
|
||||
type: truthful_qa
|
||||
config: multiple_choice
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 0
|
||||
metrics:
|
||||
- type: mc2
|
||||
value: 40.27
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: Winogrande (5-shot)
|
||||
type: winogrande
|
||||
config: winogrande_xl
|
||||
split: validation
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 58.48
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
- task:
|
||||
type: text-generation
|
||||
name: Text Generation
|
||||
dataset:
|
||||
name: GSM8k (5-shot)
|
||||
type: gsm8k
|
||||
config: main
|
||||
split: test
|
||||
args:
|
||||
num_few_shot: 5
|
||||
metrics:
|
||||
- type: acc
|
||||
value: 3.49
|
||||
name: accuracy
|
||||
source:
|
||||
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=KnutJaegersberg/Galactica-6.7B-EssayWriter
|
||||
name: Open LLM Leaderboard
|
||||
---
|
||||
|
||||
|
||||
|
||||
Prompt Example:
|
||||
```
|
||||
### Instruction:
|
||||
Provide the inputted essay that when summarized resulted in the following summary : The organization's learning and development practices are poor as they involve manual orientation from experienced workers. New employees are not advised of their roles in the organization before assignment of tasks. The orientation process takes long due to lack of a well-coordinated orientation programs.
|
||||
### Response:
|
||||
```
|
||||
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_KnutJaegersberg__Galactica-6.7B-EssayWriter)
|
||||
|
||||
| Metric |Value|
|
||||
|---------------------------------|----:|
|
||||
|Avg. |37.75|
|
||||
|AI2 Reasoning Challenge (25-Shot)|40.10|
|
||||
|HellaSwag (10-Shot) |50.29|
|
||||
|MMLU (5-Shot) |33.88|
|
||||
|TruthfulQA (0-shot) |40.27|
|
||||
|Winogrande (5-shot) |58.48|
|
||||
|GSM8k (5-shot) | 3.49|
|
||||
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "/run/media/knut/HD/huggingface models/language models/galactica/galactica-6.7b",
|
||||
"_remove_final_layer_norm": false,
|
||||
"activation_dropout": 0.0,
|
||||
"activation_function": "gelu",
|
||||
"architectures": [
|
||||
"OPTForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.1,
|
||||
"bos_token_id": 0,
|
||||
"do_layer_norm_before": true,
|
||||
"dropout": 0.1,
|
||||
"enable_bias": true,
|
||||
"eos_token_id": 2,
|
||||
"ffn_dim": 16384,
|
||||
"hidden_size": 4096,
|
||||
"init_std": 0.02,
|
||||
"layer_norm_elementwise_affine": true,
|
||||
"layerdrop": 0.0,
|
||||
"learned_embeddings": true,
|
||||
"max_position_embeddings": 2048,
|
||||
"model_type": "opt",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 1,
|
||||
"scale_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50000,
|
||||
"word_embed_proj_dim": 4096
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 1,
|
||||
"transformers_version": "4.35.2"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:19bd152e0b8962c97bcc82eed1c47bda382903dc3c519edc2ba1cc116594fa9d
|
||||
size 4991055704
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b9321bcd90507fc04d09d748e09115d74cda1fafcbd7dc0f51e69b455fe5311
|
||||
size 4967389600
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfe31620463cf25a98f02fe7e7d454db334295ea4cf175283b0bf87a780d8c43
|
||||
size 3356335328
|
||||
523
model.safetensors.index.json
Normal file
523
model.safetensors.index.json
Normal file
@@ -0,0 +1,523 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13314719744
|
||||
},
|
||||
"weight_map": {
|
||||
"model.decoder.embed_positions.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.12.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.14.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.16.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.17.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.2.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.20.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.20.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.fc2.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.fc2.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.22.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.fc1.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.fc1.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.23.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.23.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.23.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.23.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
|
||||
"model.decoder.layers.24.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.24.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.25.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.26.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.27.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.28.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.29.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.3.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.30.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.30.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.fc1.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.fc1.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.fc2.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.fc2.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.final_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.final_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.out_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.31.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
|
||||
"model.decoder.layers.4.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.fc1.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.fc2.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
|
||||
"model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
6
special_tokens_map.json
Normal file
6
special_tokens_map.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"pad_token": "<pad>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
100009
tokenizer.json
Normal file
100009
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
202
tokenizer_config.json
Normal file
202
tokenizer_config.json
Normal file
@@ -0,0 +1,202 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": "[START_REF]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": "[END_REF]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": "[IMAGE]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "<fragments>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "</fragments>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<work>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "</work>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "[START_SUP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"12": {
|
||||
"content": "[END_SUP]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"13": {
|
||||
"content": "[START_SUB]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"14": {
|
||||
"content": "[END_SUB]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"15": {
|
||||
"content": "[START_DNA]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"16": {
|
||||
"content": "[END_DNA]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"17": {
|
||||
"content": "[START_AMINO]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"18": {
|
||||
"content": "[END_AMINO]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"19": {
|
||||
"content": "[START_SMILES]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"20": {
|
||||
"content": "[END_SMILES]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"21": {
|
||||
"content": "[START_I_SMILES]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"22": {
|
||||
"content": "[END_I_SMILES]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "</s>",
|
||||
"max_length": 2048,
|
||||
"model_max_length": 2048,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": "<pad>",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"stride": 0,
|
||||
"tokenizer_class": "PreTrainedTokenizerFast",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
Reference in New Issue
Block a user