Hugging Face's logo

Maani
/
PixieZehirNano

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files
Maani commited on
Commit
5e72a71
•
1 Parent(s): 4d5c805

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +28 -17
  2. generation_config.json +10 -6
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,29 +1,40 @@
1
  {
2
- "_name_or_path": "h2oai/h2o-danube-1.8b-chat",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
 
 
 
 
 
9
  "hidden_act": "silu",
10
- "hidden_size": 2560,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 6912,
13
- "max_position_embeddings": 16384,
14
- "model_type": "mistral",
 
15
  "num_attention_heads": 32,
16
- "num_hidden_layers": 24,
17
  "num_key_value_heads": 8,
18
- "pad_token_id": 0,
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-05,
21
- "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
- "sliding_window": 4096,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "bfloat16",
26
- "transformers_version": "4.42.4",
 
 
 
 
 
27
  "use_cache": true,
28
- "vocab_size": 32000
29
  }
 
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": "float32",
37
+ "transformers_version": "4.45.0",
38
  "use_cache": true,
39
+ "vocab_size": 128256
40
  }
generation_config.json CHANGED
@@ -1,8 +1,12 @@
1
  {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "pad_token_id": 0,
6
- "repetition_penalty": 1.1,
7
- "transformers_version": "4.42.4"
 
 
 
 
8
  }
 
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": "4.45.0"
12
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6163eea49fa0d96fcf1ed16b217ba6395ae931655b7ba3727c17063c7adbfbe6
3
- size 3662427808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b581cc4e465c2cbabb570334dec38239f80394103d169cf4c1be694dddf9c8
3
+ size 4943274328