Hugging Face's logo

ZainAli60
/
tuned_model

Text Generation
Transformers
Safetensors
falcon
custom_code
text-generation-inference
Model card Files
xet
Community
ZainAli60 commited on
Commit
e3f423f
·
verified ·
1 Parent(s): b59fe57

Upload FalconForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +29 -23
  2. generation_config.json +2 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,32 +1,38 @@
1
  {
2
- "_name_or_path": "/root/pretraining/local-models/training/2024-02-13_07-15-38",
3
- "activation_function": "gelu",
 
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.0,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.0,
10
- "eos_token_id": 50256,
 
 
 
 
 
 
 
 
 
 
11
  "initializer_range": 0.02,
12
  "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_embd": 1536,
15
- "n_head": 12,
16
- "n_inner": 6144,
17
- "n_layer": 18,
18
- "n_positions": 2048,
19
- "reorder_and_upcast_attn": false,
20
- "resid_pdrop": 0.0,
21
- "scale_attn_by_inverse_layer_idx": false,
22
- "scale_attn_weights": true,
23
- "summary_activation": null,
24
- "summary_first_dropout": 0.1,
25
- "summary_proj_to_labels": true,
26
- "summary_type": "cls_index",
27
- "summary_use_proj": true,
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.34.1",
30
  "use_cache": true,
31
- "vocab_size": 50257
32
  }
 
1
  {
2
+ "_name_or_path": "/root/pretraining/local-models/training/2024-02-13_07-29-53",
3
+ "alibi": true,
4
+ "apply_residual_connection_post_layernorm": false,
5
  "architectures": [
6
+ "FalconForCausalLM"
7
  ],
8
+ "attention_dropout": 0.0,
9
+ "auto_map": {
10
+ "AutoConfig": "configuration_falcon.FalconConfig",
11
+ "AutoModel": "modeling_falcon.FalconModel",
12
+ "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
13
+ "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
14
+ "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
15
+ "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
16
+ },
17
+ "bias": true,
18
+ "bos_token_id": 1,
19
+ "eos_token_id": 2,
20
+ "hidden_dropout": 0.0,
21
+ "hidden_size": 2048,
22
  "initializer_range": 0.02,
23
  "layer_norm_epsilon": 1e-05,
24
+ "max_position_embeddings": 2048,
25
+ "model_type": "falcon",
26
+ "multi_query": false,
27
+ "new_decoder_architecture": false,
28
+ "num_attention_heads": 32,
29
+ "num_hidden_layers": 24,
30
+ "num_kv_heads": 32,
31
+ "parallel_attn": false,
32
+ "rope_scaling": null,
33
+ "rope_theta": 10000.0,
 
 
 
 
 
34
  "torch_dtype": "float32",
35
  "transformers_version": "4.34.1",
36
  "use_cache": true,
37
+ "vocab_size": 50304
38
  }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
  "transformers_version": "4.34.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
  "transformers_version": "4.34.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93ca13fd3d252ef72cd4872206cb33abc3b82fad2d3b83198e70f10fce0bf1a7
3
- size 2361266536
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ea1003597f92613c2d381d2cb27e347fd1abf51d4bbb2168a3a0c89bcc18660
3
+ size 5246534968