Hugging Face's logo

demetera
/
llama-600M-rus

Text Generation
Transformers
Safetensors
Russian
llama
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
demetera commited on
Commit
88c16e6
•
1 Parent(s): 205a201

Upload LlamaForCausalLM

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. config.json +4 -2
  3. generation_config.json +1 -1
  4. model.safetensors +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
- license: mit
3
  language:
4
  - ru
5
  library_name: transformers
 
6
  ---
7
 
8
  # llama-600M-rus
 
1
  ---
 
2
  language:
3
  - ru
4
  library_name: transformers
5
+ license: mit
6
  ---
7
 
8
  # llama-600M-rus
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "smallllama",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -7,11 +7,13 @@
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
 
10
  "hidden_act": "silu",
11
  "hidden_size": 1536,
12
  "initializer_range": 0.02,
13
  "intermediate_size": 4224,
14
  "max_position_embeddings": 2048,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 24,
17
  "num_hidden_layers": 18,
@@ -22,7 +24,7 @@
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "float32",
25
- "transformers_version": "4.36.2",
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
 
1
  {
2
+ "_name_or_path": "/kaggle/working/llama2-600m-rus/checkpoint-6341",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
10
+ "head_dim": 64,
11
  "hidden_act": "silu",
12
  "hidden_size": 1536,
13
  "initializer_range": 0.02,
14
  "intermediate_size": 4224,
15
  "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
  "model_type": "llama",
18
  "num_attention_heads": 24,
19
  "num_hidden_layers": 18,
 
24
  "rope_theta": 10000.0,
25
  "tie_word_embeddings": false,
26
  "torch_dtype": "float32",
27
+ "transformers_version": "4.45.1",
28
  "use_cache": true,
29
  "vocab_size": 32000
30
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.36.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.45.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d7255efdec45417324d667a3deaeec742ae7ffd00559dda197685e37d6a09b
3
  size 2191245664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d6b058be33194c0abb486f22c3b10e5221fdc94025bf3a2851ca6d61a773d69
3
  size 2191245664