初始化项目，由ModelHub XC社区提供模型
Model: dmayhem93/toolformer_v0_epoch2 Source: Original Platform
This commit is contained in:
ModelHub XC
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"<TOOLFORMER_API_START>": 50259,
|
||||
"<TOOLFORMER_API_RESPONSE>": 50258,
|
||||
"<TOOLFORMER_API_END>": 50257
|
||||
}
|
||||
42
config.json
Normal file
42
config.json
Normal file
@@ -0,0 +1,42 @@
|
||||
{
|
||||
"_name_or_path": "/mnt/nvme/home/dakota/toolformer/finetune_toolformer_v0/checkpoint-522",
|
||||
"activation_function": "gelu_new",
|
||||
"architectures": [
|
||||
"GPTJForCausalLM"
|
||||
],
|
||||
"attn_pdrop": 0.0,
|
||||
"bos_token_id": 50256,
|
||||
"embd_pdrop": 0.0,
|
||||
"eos_token_id": 50256,
|
||||
"gradient_checkpointing": false,
|
||||
"initializer_range": 0.02,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "gptj",
|
||||
"n_embd": 4096,
|
||||
"n_head": 16,
|
||||
"n_inner": null,
|
||||
"n_layer": 28,
|
||||
"n_positions": 2048,
|
||||
"resid_pdrop": 0.0,
|
||||
"rotary": true,
|
||||
"rotary_dim": 64,
|
||||
"scale_attn_weights": true,
|
||||
"summary_activation": null,
|
||||
"summary_first_dropout": 0.1,
|
||||
"summary_proj_to_labels": true,
|
||||
"summary_type": "cls_index",
|
||||
"summary_use_proj": true,
|
||||
"task_specific_params": {
|
||||
"text-generation": {
|
||||
"do_sample": true,
|
||||
"max_length": 50,
|
||||
"temperature": 1.0
|
||||
}
|
||||
},
|
||||
"tie_word_embeddings": false,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.26.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 50400
|
||||
}
|
||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model-00001-of-00003.bin
Normal file
3
pytorch_model-00001-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:25c17c9fb5696af0f467d02db613fa76afbf59cec21dfd77eae19f4317deb77a
|
||||
size 9937123207
|
||||
3
pytorch_model-00002-of-00003.bin
Normal file
3
pytorch_model-00002-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5c8a07cc4dd62796e624a8ac0c516c95d9c7a7f666774a2be562eb44848b752
|
||||
size 9782541966
|
||||
3
pytorch_model-00003-of-00003.bin
Normal file
3
pytorch_model-00003-of-00003.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2f60e664dced0d633c07c786a1c87cc0ab2bda161441cdb9a2539f1a63378344
|
||||
size 4601420623
|
||||
348
pytorch_model.bin.index.json
Normal file
348
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,348 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24320971760
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.0.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.0.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.1.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.10.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.11.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.11.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.11.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.11.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.11.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.12.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.13.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.14.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.15.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.16.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.17.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.18.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.19.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.2.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.2.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.20.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.20.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.21.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.mlp.fc_in.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.mlp.fc_in.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.mlp.fc_out.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.22.mlp.fc_out.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.masked_bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.ln_1.bias": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.ln_1.weight": "pytorch_model-00002-of-00003.bin",
|
||||
"transformer.h.23.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.23.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.23.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.23.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.24.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.25.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.26.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.masked_bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.ln_1.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.ln_1.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.mlp.fc_in.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.mlp.fc_in.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.mlp.fc_out.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.27.mlp.fc_out.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.h.3.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.3.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.4.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.5.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.6.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.7.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.8.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.masked_bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.ln_1.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.ln_1.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.mlp.fc_in.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.mlp.fc_in.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.mlp.fc_out.bias": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.h.9.mlp.fc_out.weight": "pytorch_model-00001-of-00003.bin",
|
||||
"transformer.ln_f.bias": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.ln_f.weight": "pytorch_model-00003-of-00003.bin",
|
||||
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
||||
}
|
||||
}
|
||||
5
special_tokens_map.json
Normal file
5
special_tokens_map.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"bos_token": "<|endoftext|>",
|
||||
"eos_token": "<|endoftext|>",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"errors": "replace",
|
||||
"model_max_length": 1e+20,
|
||||
"name_or_path": "EleutherAI/gpt-j-6B",
|
||||
"pad_token": null,
|
||||
"special_tokens_map_file": null,
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
50259
vocab.json
Normal file
50259
vocab.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user