Hugging Face's logo

RamAnanth1
/
tiny-aya-hermes-tool-calling

Text Generation
Transformers
Safetensors
cohere2
Generated from Trainer
trackio
trl
sft
conversational
Model card Files
xet
Metrics Community
RamAnanth1 commited on
Commit
9e10af2
·
verified ·
1 Parent(s): e0f07cd

SFT-trained tiny-aya-global for tool calling

Browse files
Files changed (4) hide show
  1. README.md +0 -1
  2. config.json +82 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
README.md CHANGED
@@ -9,7 +9,6 @@ tags:
9
  - trl
10
  - sft
11
  licence: license
12
-
13
  datasets:
14
  - NousResearch/hermes-function-calling-v1
15
  ---
 
9
  - trl
10
  - sft
11
  licence: license
 
12
  datasets:
13
  - NousResearch/hermes-function-calling-v1
14
  ---
config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 4,
3
+ "architectures": [
4
+ "Cohere2ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "cache_implementation": "hybrid",
10
+ "dtype": "bfloat16",
11
+ "eos_token_id": 3,
12
+ "head_dim": 128,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 11008,
17
+ "layer_norm_eps": 1e-05,
18
+ "layer_switch": 4,
19
+ "layer_types": [
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "full_attention",
24
+ "sliding_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "full_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "sliding_attention",
31
+ "full_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "full_attention",
36
+ "sliding_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "full_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "sliding_attention",
43
+ "full_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "full_attention",
48
+ "sliding_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "full_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "sliding_attention",
55
+ "full_attention"
56
+ ],
57
+ "logit_scale": 1.0,
58
+ "max_position_embeddings": 500000,
59
+ "model_type": "cohere2",
60
+ "num_attention_heads": 16,
61
+ "num_hidden_layers": 36,
62
+ "num_key_value_heads": 4,
63
+ "order_of_interleaved_layers": "local_attn_first",
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "rope_gptj",
66
+ "rope_parameters": {
67
+ "rope_theta": 50000,
68
+ "rope_type": "default"
69
+ },
70
+ "rotary_pct": 1.0,
71
+ "sliding_window": 4096,
72
+ "sliding_window_pattern": 4,
73
+ "tie_word_embeddings": true,
74
+ "transformers_version": "5.2.0",
75
+ "use_cache": true,
76
+ "use_embedding_sharing": true,
77
+ "use_gated_activation": true,
78
+ "use_parallel_block": true,
79
+ "use_parallel_embedding": false,
80
+ "use_qk_norm": false,
81
+ "vocab_size": 262144
82
+ }
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": "5.2.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e2340ee1231f673cf9f5639860ff7299e3ec6d68c417157a9d26a3499bb71ff
3
+ size 6698488600