Hugging Face's logo

deepnet
/
Subnet6Training5

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
deepnet commited on
Commit
7c4b135
·
verified ·
1 Parent(s): 42ae8a2

Upload LlamaForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +13 -12
  2. generation_config.json +3 -2
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
config.json CHANGED
@@ -1,28 +1,29 @@
1
  {
2
- "_name_or_path": "/finetuning-subnet/nous-four",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
- "eos_token_id": 2,
10
  "hidden_act": "silu",
11
- "hidden_size": 4,
12
- "initializer_range": 0.0,
13
- "intermediate_size": 4,
14
- "max_position_embeddings": 2048,
15
  "model_type": "llama",
16
- "num_attention_heads": 1,
17
- "num_hidden_layers": 4,
18
- "num_key_value_heads": 1,
19
  "pretraining_tp": 1,
20
- "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
22
  "rope_theta": 10000.0,
 
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
  "transformers_version": "4.36.2",
26
- "use_cache": true,
27
- "vocab_size": 32000
28
  }
 
1
  {
2
+ "_name_or_path": "/finetuning-subnet/local-models/training/3HrIntervalSaved",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
+ "eos_token_id": 32000,
10
  "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 14336,
14
+ "max_position_embeddings": 32768,
15
  "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 8,
19
  "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
  "rope_scaling": null,
22
  "rope_theta": 10000.0,
23
+ "sliding_window": 4096,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.36.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32002
29
  }
generation_config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.36.2"
 
6
  }
 
1
  {
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
+ "eos_token_id": 32000,
5
+ "transformers_version": "4.36.2",
6
+ "use_cache": false
7
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddd7f2a6a869d4ff3696156596adcb39b0fc9fade4ead285105feca96aa3edad
3
  size 4943178720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7cddbcf74d3f0e090e0c3c2c9f8f2dd6475c71118489dd3ed06fe8f30361ed5
3
  size 4943178720
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b076b2fe0edb5233dc9c12727bcba014f9f43ffcf1fd276952563a15cb26d252
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4c1069ac9efd401d4e09e070ca309b2e5c9bfc2c1818aabd6ea5fcaf5f11328
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9776b1edec4b2a75781829a735045136f9ea07389454f1650e448524d4bd7663
3
  size 4540532728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c09dcfd2bea013cdef6f427e1929fdc9af657fac62550236b7c0db7bf0e7a8a3
3
  size 4540532728