meliksahturker commited on
Commit
60c9071
·
verified ·
1 Parent(s): 3c7b56f

Upload MistralForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +29 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vngrs-ai/Kumru-2B-v0.2.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 2,
8
+ "dtype": "bfloat16",
9
+ "eos_token_id": 3,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 10752,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "mistral",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 18,
19
+ "num_key_value_heads": 4,
20
+ "pad_token_id": 0,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 500000,
23
+ "sliding_window": null,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.49.0",
27
+ "use_cache": true,
28
+ "vocab_size": 50176
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 3,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6486c82f0a9dfe34d55cd042f892d490c457e7e72e33d119e0360efbdc41cecf
3
+ size 4750295696