Hugging Face's logo

appohfaiths
/
Llama-Ghanaba-AI

Text Generation
Safetensors
English
French
llama
Model card Files Community
appohfaiths commited on
Commit
c24232c
·
verified ·
1 Parent(s): e7d8b9c

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +28 -24
  2. generation_config.json +5 -2
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,32 +1,36 @@
1
  {
2
- "_name_or_path": "distilbert/distilgpt2",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPT2LMHeadModel"
6
  ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 50256,
9
- "embd_pdrop": 0.1,
10
- "eos_token_id": 50256,
 
 
 
11
  "initializer_range": 0.02,
12
- "layer_norm_epsilon": 1e-05,
13
- "model_type": "gpt2",
14
- "n_embd": 768,
15
- "n_head": 12,
16
- "n_inner": null,
17
- "n_layer": 12,
18
- "n_positions": 1024,
19
- "reorder_and_upcast_attn": false,
20
- "resid_pdrop": 0.1,
21
- "scale_attn_by_inverse_layer_idx": false,
22
- "scale_attn_weights": true,
23
- "summary_activation": null,
24
- "summary_first_dropout": 0.1,
25
- "summary_proj_to_labels": true,
26
- "summary_type": "cls_index",
27
- "summary_use_proj": true,
 
 
28
  "torch_dtype": "float32",
29
  "transformers_version": "4.47.1",
30
  "use_cache": true,
31
- "vocab_size": 50257
32
  }
 
1
  {
2
+ "_name_or_path": "meta-llama/Llama-3.2-1B",
 
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.4,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128001,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 2048,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 8192,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 16,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 32.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": true,
32
  "torch_dtype": "float32",
33
  "transformers_version": "4.47.1",
34
  "use_cache": true,
35
+ "vocab_size": 128256
36
  }
generation_config.json CHANGED
@@ -1,6 +1,9 @@
1
  {
2
  "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
 
 
 
5
  "transformers_version": "4.47.1"
6
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
  "transformers_version": "4.47.1"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e78e61065a45800b9d68840c30e624f78e0da4efca292e66c9d810adad6b5897
3
- size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa5a3d00b163b05454ce95dba5dd9db0ef663d04057f31e6a50be8fc05704929
3
+ size 4943274328