初始化项目,由ModelHub XC社区提供模型
Model: bigjoedata/rockchatbot Source: Original Platform
This commit is contained in:
9
.gitattributes
vendored
Normal file
9
.gitattributes
vendored
Normal file
@@ -0,0 +1,9 @@
|
|||||||
|
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
35
config.json
Normal file
35
config.json
Normal file
@@ -0,0 +1,35 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "microsoft/DialoGPT-small",
|
||||||
|
"activation_function": "gelu_new",
|
||||||
|
"architectures": [
|
||||||
|
"GPT2LMHeadModel"
|
||||||
|
],
|
||||||
|
"attn_pdrop": 0.1,
|
||||||
|
"bos_token_id": 50256,
|
||||||
|
"embd_pdrop": 0.1,
|
||||||
|
"eos_token_id": 50256,
|
||||||
|
"gradient_checkpointing": false,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"layer_norm_epsilon": 1e-05,
|
||||||
|
"model_type": "gpt2",
|
||||||
|
"n_ctx": 1024,
|
||||||
|
"n_embd": 768,
|
||||||
|
"n_head": 12,
|
||||||
|
"n_inner": null,
|
||||||
|
"n_layer": 12,
|
||||||
|
"n_positions": 1024,
|
||||||
|
"resid_pdrop": 0.1,
|
||||||
|
"summary_activation": null,
|
||||||
|
"summary_first_dropout": 0.1,
|
||||||
|
"summary_proj_to_labels": true,
|
||||||
|
"summary_type": "cls_index",
|
||||||
|
"summary_use_proj": true,
|
||||||
|
"task_specific_params": {
|
||||||
|
"conversational": {
|
||||||
|
"max_length": 1000
|
||||||
|
}
|
||||||
|
},
|
||||||
|
"transformers_version": "4.2.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 50257
|
||||||
|
}
|
||||||
1
eval_results.txt
Normal file
1
eval_results.txt
Normal file
@@ -0,0 +1 @@
|
|||||||
|
perplexity = tensor(6.5276)
|
||||||
3
flax_model.msgpack
Normal file
3
flax_model.msgpack
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:64199093476ca7c5dea485190b5e5df6af4796c5eaf81806cdca3f4244b4fa89
|
||||||
|
size 497764120
|
||||||
50001
merges.txt
Normal file
50001
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
pytorch_model.bin
Normal file
3
pytorch_model.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:56e4422039fb0f81f3286f83049fc685b1b2c65f36e6589135734a57c1527b91
|
||||||
|
size 510406559
|
||||||
1
special_tokens_map.json
Normal file
1
special_tokens_map.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}}
|
||||||
1
tokenizer_config.json
Normal file
1
tokenizer_config.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "microsoft/DialoGPT-small", "errors": "replace"}
|
||||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:18c674c64e0661bb3fa34f8f1e9fcc8985d4f26069b57979bbd000e26339b1f3
|
||||||
|
size 1327
|
||||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user