Hugging Face's logo

HugoVoxx
/
llama-3.2-1b-it-ag-merged-model

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Model card Files
xet
Community
HugoVoxx commited on
Commit
3e0b0d7
·
verified ·
1 Parent(s): e9f1be3

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +40 -40
  2. generation_config.json +12 -12
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,40 +1,40 @@
1
- {
2
- "_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 128000,
9
- "eos_token_id": [
10
- 128001,
11
- 128008,
12
- 128009
13
- ],
14
- "head_dim": 64,
15
- "hidden_act": "silu",
16
- "hidden_size": 2048,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 8192,
19
- "max_position_embeddings": 131072,
20
- "mlp_bias": false,
21
- "model_type": "llama",
22
- "num_attention_heads": 32,
23
- "num_hidden_layers": 16,
24
- "num_key_value_heads": 8,
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": "float16",
37
- "transformers_version": "4.45.2",
38
- "use_cache": true,
39
- "vocab_size": 128258
40
- }
 
1
+ {
2
+ "_name_or_path": "unsloth/Llama-3.2-1B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 64,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 2048,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 16,
24
+ "num_key_value_heads": 8,
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": "float16",
37
+ "transformers_version": "4.45.2",
38
+ "use_cache": true,
39
+ "vocab_size": 128258
40
+ }
generation_config.json CHANGED
@@ -1,12 +1,12 @@
1
- {
2
- "bos_token_id": 128000,
3
- "do_sample": true,
4
- "eos_token_id": [
5
- 128001,
6
- 128008,
7
- 128009
8
- ],
9
- "temperature": 0.6,
10
- "top_p": 0.9,
11
- "transformers_version": "4.45.2"
12
- }
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128008,
7
+ 128009
8
+ ],
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.45.2"
12
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:166926f9a70c759190e1650d9a7b4cab9788723cc65771f4f672eddd72816055
3
- size 2996998568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e006c7a82a387afc550ae4236fd4caa334b40b9a14ebc986840ba9493654b6
3
+ size 2996998584