Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
DarwinAnim8or commited on
Commit
7ec021b
·
verified ·
1 Parent(s): b8eea7f

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -5,22 +5,23 @@
5
  "attention_dropout": 0.0,
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
 
8
  "hidden_act": "silu",
9
- "hidden_size": 2048,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 4096,
12
- "max_position_embeddings": 32768,
13
  "model_type": "mistral",
14
- "num_attention_heads": 32,
15
  "num_hidden_layers": 8,
16
- "num_key_value_heads": 8,
17
  "pad_token_id": 0,
18
  "rms_norm_eps": 1e-06,
19
  "rope_theta": 10000.0,
20
- "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.42.3",
24
  "use_cache": true,
25
- "vocab_size": 32000
26
  }
 
5
  "attention_dropout": 0.0,
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
+ "head_dim": 64,
9
  "hidden_act": "silu",
10
+ "hidden_size": 1024,
11
  "initializer_range": 0.02,
12
  "intermediate_size": 4096,
13
+ "max_position_embeddings": 4096,
14
  "model_type": "mistral",
15
+ "num_attention_heads": 16,
16
  "num_hidden_layers": 8,
17
+ "num_key_value_heads": 16,
18
  "pad_token_id": 0,
19
  "rms_norm_eps": 1e-06,
20
  "rope_theta": 10000.0,
21
+ "sliding_window": 2048,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.46.3",
25
  "use_cache": true,
26
+ "vocab_size": 5100
27
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.42.3"
7
- }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.46.3"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c5cd38786bcad3b8c71c9e6b852cce546008f1bdcbd682d955439889214ec0f
3
+ size 578728136
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a5276a98cd8cdf819d8b041ea6793a68d7488ffdee4bfd85fd3ef88ae30e0a
3
+ size 5240