Hugging Face's logo

danish-foundation-models
/
munin-7b-alpha

Text Generation
Transformers
Safetensors
Danish
mistral
pretrained
text-generation-inference
Inference Endpoints
Model card Files Community
3
synquid commited on
Commit
24eb3d1
•
1 Parent(s): 60a00d5

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +4 -3
  2. generation_config.json +2 -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
  6. pytorch_model.bin +1 -1
  7. tokenizer_config.json +3 -1
config.json CHANGED
@@ -2,13 +2,14 @@
2
  "architectures": [
3
  "MistralForCausalLM"
4
  ],
 
5
  "bos_token_id": 1,
6
  "eos_token_id": 2,
7
  "hidden_act": "silu",
8
  "hidden_size": 4096,
9
  "initializer_range": 0.02,
10
  "intermediate_size": 14336,
11
- "max_position_embeddings": 2048,
12
  "model_type": "mistral",
13
  "num_attention_heads": 32,
14
  "num_hidden_layers": 32,
@@ -18,7 +19,7 @@
18
  "sliding_window": 4096,
19
  "tie_word_embeddings": false,
20
  "torch_dtype": "bfloat16",
21
- "transformers_version": "4.35.2",
22
- "use_cache": true,
23
  "vocab_size": 32000
24
  }
 
2
  "architectures": [
3
  "MistralForCausalLM"
4
  ],
5
+ "attention_dropout": 0.0,
6
  "bos_token_id": 1,
7
  "eos_token_id": 2,
8
  "hidden_act": "silu",
9
  "hidden_size": 4096,
10
  "initializer_range": 0.02,
11
  "intermediate_size": 14336,
12
+ "max_position_embeddings": 32768,
13
  "model_type": "mistral",
14
  "num_attention_heads": 32,
15
  "num_hidden_layers": 32,
 
19
  "sliding_window": 4096,
20
  "tie_word_embeddings": false,
21
  "torch_dtype": "bfloat16",
22
+ "transformers_version": "4.36.2",
23
+ "use_cache": false,
24
  "vocab_size": 32000
25
  }
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": "4.35.2"
 
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.36.2",
6
+ "use_cache": false
7
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a21178cfbca8cbf881e7d3fa07909c98c430916d3c13f44a2ba493fa9f3919a4
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e24470455ff8dd92b207ed00295e2bdc644af810a73ca7994dd8928f9de58e86
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b14f6521b044d9d38257e8891ca42ba83c0218e5e8456cb6824cc0e59291ef8
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39131017474537afe8b3af090725735f4b10ac7f7c57bbb1a5a9b351555d6ebc
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78c68a4c318e6dae31d9c6e9ff7cdd682f8ea370ca3d5c83f02f5dbef31e0722
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a217c2c7b64e9080e6f829ad97ef839eed2e1a96f95a4b22a98bd76cf2852f4e
3
  size 4540516344
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60d86db1129ac96f45a41e41b592c96ff5ad32aab2f19b25e17f5d8d4450386e
3
  size 14483623678
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8055884494f1795783df1ccaddd48470c2153e222d3e87c67ef102b942d2d1c2
3
  size 14483623678
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
  "0": {
4
  "content": "<unk>",
@@ -30,7 +32,7 @@
30
  "clean_up_tokenization_spaces": false,
31
  "eos_token": "</s>",
32
  "legacy": true,
33
- "model_max_length": 2048,
34
  "pad_token": null,
35
  "sp_model_kwargs": {},
36
  "spaces_between_special_tokens": false,
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
32
  "clean_up_tokenization_spaces": false,
33
  "eos_token": "</s>",
34
  "legacy": true,
35
+ "model_max_length": 4096,
36
  "pad_token": null,
37
  "sp_model_kwargs": {},
38
  "spaces_between_special_tokens": false,