Hugging Face's logo

Li-Tang
/
gpt2-imdb-pos-v2

Feature Extraction
Transformers
PyTorch
chatglm
custom_code
Model card Files Community
Li-Tang commited on
Commit
82ea820
·
1 Parent(s): ec810b2

Upload ChatGLMForConditionalGeneration

Browse files
Files changed (3) hide show
  1. config.json +26 -27
  2. generation_config.json +4 -3
  3. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,34 +1,33 @@
1
  {
2
- "_name_or_path": "lvwerra/gpt2-imdb",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
 
 
 
 
 
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_ctx": 1024,
15
- "n_embd": 768,
16
- "n_head": 12,
17
- "n_inner": null,
18
- "n_layer": 12,
19
- "n_positions": 1024,
20
- "output_past": true,
21
- "reorder_and_upcast_attn": false,
22
- "resid_pdrop": 0.1,
23
- "scale_attn_by_inverse_layer_idx": false,
24
- "scale_attn_weights": true,
25
- "summary_activation": null,
26
- "summary_first_dropout": 0.1,
27
- "summary_proj_to_labels": true,
28
- "summary_type": "cls_index",
29
- "summary_use_proj": true,
30
  "torch_dtype": "float32",
31
- "transformers_version": "4.27.1",
32
  "use_cache": true,
33
- "vocab_size": 50257
34
  }
 
1
  {
2
+ "_name_or_path": "THUDM/chatglm-6b",
 
3
  "architectures": [
4
+ "ChatGLMForConditionalGeneration"
5
  ],
6
+ "auto_map": {
7
+ "AutoConfig": "THUDM/chatglm-6b--configuration_chatglm.ChatGLMConfig",
8
+ "AutoModel": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration",
9
+ "AutoModelForSeq2SeqLM": "THUDM/chatglm-6b--modeling_chatglm.ChatGLMForConditionalGeneration"
10
+ },
11
+ "bos_token_id": 130004,
12
+ "eos_token_id": 130005,
13
+ "gmask_token_id": 130001,
14
+ "hidden_size": 4096,
15
  "initializer_range": 0.02,
16
+ "initializer_weight": false,
17
+ "inner_hidden_size": 16384,
18
+ "layernorm_epsilon": 1e-05,
19
+ "mask_token_id": 130000,
20
+ "max_sequence_length": 2048,
21
+ "model_type": "chatglm",
22
+ "num_attention_heads": 32,
23
+ "num_layers": 28,
24
+ "pad_token_id": 3,
25
+ "position_encoding_2d": true,
26
+ "pre_seq_len": null,
27
+ "prefix_projection": false,
28
+ "quantization_bit": 8,
 
 
 
 
 
29
  "torch_dtype": "float32",
30
+ "transformers_version": "4.29.2",
31
  "use_cache": true,
32
+ "vocab_size": 130528
33
  }
generation_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "4.27.1"
 
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 130004,
4
+ "eos_token_id": 130005,
5
+ "pad_token_id": 3,
6
+ "transformers_version": "4.29.2"
7
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6227fe25fc89c952cce180c6dec4b367b19bec7c4a70eef65bb38c1857f3d707
3
- size 510401733
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37005f8bd1873532775706988183339e15900871f370114536ebed98c698ea2e
3
+ size 7786027413