Hugging Face's logo

prithivMLmods
/
Bellatrix-Tiny-1B-v2

Text Generation
Transformers
ONNX
Safetensors
English
llama
reason
tiny
llama3.2
cot
bellatrix
conversational
text-generation-inference
Model card Files Community
prithivMLmods commited on
Commit
1c4f98d
·
verified ·
1 Parent(s): a04f453

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +45 -46
config.json CHANGED
@@ -1,46 +1,45 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
- "eos_token_id": [
9
- 128001,
10
- 128008,
11
- 128009
12
- ],
13
- "head_dim": 64,
14
- "hidden_act": "silu",
15
- "hidden_size": 2048,
16
- "initializer_range": 0.02,
17
- "intermediate_size": 8192,
18
- "max_position_embeddings": 131072,
19
- "mlp_bias": false,
20
- "model_type": "llama",
21
- "num_attention_heads": 32,
22
- "num_hidden_layers": 16,
23
- "num_key_value_heads": 8,
24
- "pad_token_id": 128004,
25
- "pretraining_tp": 1,
26
- "rms_norm_eps": 1e-05,
27
- "rope_scaling": {
28
- "factor": 32.0,
29
- "high_freq_factor": 4.0,
30
- "low_freq_factor": 1.0,
31
- "original_max_position_embeddings": 8192,
32
- "rope_type": "llama3"
33
- },
34
- "rope_theta": 500000.0,
35
- "tie_word_embeddings": true,
36
- "torch_dtype": "bfloat16",
37
- "transformers.js_config": {
38
- "kv_cache_dtype": {
39
- "fp16": "float16",
40
- "q4f16": "float16"
41
- }
42
- },
43
- "transformers_version": "4.47.1",
44
- "use_cache": true,
45
- "vocab_size": 128256
46
- }
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": [
9
+ 128001,
10
+ 128008,
11
+ 128009
12
+ ],
13
+ "head_dim": 64,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 2048,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 8192,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 16,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_scaling": {
27
+ "factor": 32.0,
28
+ "high_freq_factor": 4.0,
29
+ "low_freq_factor": 1.0,
30
+ "original_max_position_embeddings": 8192,
31
+ "rope_type": "llama3"
32
+ },
33
+ "rope_theta": 500000.0,
34
+ "tie_word_embeddings": true,
35
+ "torch_dtype": "float32",
36
+ "transformers.js_config": {
37
+ "kv_cache_dtype": {
38
+ "q4f16": "float16",
39
+ "fp16": "float16"
40
+ }
41
+ },
42
+ "transformers_version": "4.46.3",
43
+ "use_cache": true,
44
+ "vocab_size": 128256
45
+ }