Hugging Face's logo

Vikhrmodels
/
Vikhr-7b-0.1

Text Generation
Transformers
PyTorch
Safetensors
Russian
English
mistral
text-generation-inference
Inference Endpoints
Model card Files Community
3
AlexWortega commited on
Commit
ce882ca
•
1 Parent(s): 14c7214

Upload LlamaForCausalLM

Browse files
Files changed (5) hide show
  1. config.json +7 -4
  2. generation_config.json +1 -1
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
config.json CHANGED
@@ -1,8 +1,9 @@
1
  {
2
- "_name_or_path": "Vikhr-7b-0.1",
3
  "architectures": [
4
- "MistralForCausalLM"
5
  ],
 
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 1,
8
  "eos_token_id": 2,
@@ -11,16 +12,18 @@
11
  "initializer_range": 0.02,
12
  "intermediate_size": 14336,
13
  "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
  "num_attention_heads": 32,
16
  "num_hidden_layers": 32,
17
  "num_key_value_heads": 8,
 
18
  "rms_norm_eps": 1e-05,
 
19
  "rope_theta": 10000.0,
20
  "sliding_window": 4096,
21
  "tie_word_embeddings": false,
22
  "torch_dtype": "bfloat16",
23
- "transformers_version": "4.36.0",
24
  "use_cache": true,
25
  "vocab_size": 40000
26
  }
 
1
  {
2
+ "_name_or_path": "vikhr_v1_90",
3
  "architectures": [
4
+ "LlamaForCausalLM"
5
  ],
6
+ "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "bos_token_id": 1,
9
  "eos_token_id": 2,
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 14336,
14
  "max_position_embeddings": 32768,
15
+ "model_type": "llama",
16
  "num_attention_heads": 32,
17
  "num_hidden_layers": 32,
18
  "num_key_value_heads": 8,
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": "4.36.2",
27
  "use_cache": true,
28
  "vocab_size": 40000
29
  }
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": "4.36.0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.36.2"
6
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6186844f58fe63b2c85934822f3159e56a0ecb25ac70d20d66b0a8a3c010f5e7
3
  size 4891257712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:394c881f574b9773b19ffaf83b5feaef17b9b96e84cb1c2c21b04d247b15c3fe
3
  size 4891257712
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15bfe25adc1ae95cf8e51a78e44ba7555354ba3702791d093a61eb9239281366
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b55c47d4a605611e29aaeec442ffa08425e69a70e55229c6d7e9b471d7cb3542
3
  size 4915916176
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:028aeec6d4584ce88441858cb87ee7ed9b2daf47be8893ab6cae237ce06c207a
3
  size 4807396136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84be18a7e74027b23ba240e780e9ae3dcd1a503e0f7ea4073e714025228fda98
3
  size 4807396136