Hugging Face's logo

Defetya
/
openllama-3b-saiga

Text Generation
Transformers
PyTorch
Safetensors
llama
text2text-generation
conversational
text-generation-inference
Model card Files Community
1
Defetya commited on
Commit
c8d5e8c
·
verified ·
1 Parent(s): 752e981

Upload LlamaForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +3 -5
  2. generation_config.json +2 -1
  3. pytorch_model.bin +3 -0
config.json CHANGED
@@ -1,10 +1,8 @@
1
  {
2
- "_name_or_path": "/root/hf_model_3b",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
  "hidden_act": "silu",
@@ -16,13 +14,13 @@
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 26,
18
  "num_key_value_heads": 32,
 
19
  "pretraining_tp": 1,
20
  "rms_norm_eps": 1e-06,
21
  "rope_scaling": null,
22
- "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.38.1",
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
 
1
  {
2
+ "_name_or_path": "hf_model_3b",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
 
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
 
14
  "num_attention_heads": 32,
15
  "num_hidden_layers": 26,
16
  "num_key_value_heads": 32,
17
+ "pad_token_id": 0,
18
  "pretraining_tp": 1,
19
  "rms_norm_eps": 1e-06,
20
  "rope_scaling": null,
 
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.31.0",
24
  "use_cache": true,
25
  "vocab_size": 32000
26
  }
generation_config.json CHANGED
@@ -2,5 +2,6 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.38.1"
 
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.31.0"
7
  }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78ab5acf4cf280cd2b4f70983eec0514afff5b77490e168cd8351ccb39d0bbd1
3
+ size 6853038093