Text Generation
Transformers
Safetensors
English
mistral
text-generation-inference
Inference Endpoints
instruction-pretrain commited on
Commit
f4679e2
1 Parent(s): 79497cb

Upload MistralForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +23 -22
  2. generation_config.json +1 -1
config.json CHANGED
@@ -1,24 +1,25 @@
1
  {
2
- "architectures": [
3
- "MistralForCausalLM"
4
- ],
5
- "bos_token_id": 1,
6
- "eos_token_id": 2,
7
- "hidden_act": "silu",
8
- "hidden_size": 2048,
9
- "initializer_range": 0.02,
10
- "intermediate_size": 8192,
11
- "max_position_embeddings": 2048,
12
- "model_type": "mistral",
13
- "num_attention_heads": 32,
14
- "num_hidden_layers": 20,
15
- "num_key_value_heads": 8,
16
- "rms_norm_eps": 1e-05,
17
- "rope_theta": 10000.0,
18
- "sliding_window": 2048,
19
- "tie_word_embeddings": false,
20
- "torch_dtype": "float16",
21
- "transformers_version": "4.34.0.dev0",
22
- "use_cache": true,
23
- "vocab_size": 32000
 
24
  }
 
1
  {
2
+ "_name_or_path": "hf_mirror/InstructLM-1.3B",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 2048,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 8192,
12
+ "max_position_embeddings": 2048,
13
+ "model_type": "mistral",
14
+ "num_attention_heads": 32,
15
+ "num_hidden_layers": 20,
16
+ "num_key_value_heads": 8,
17
+ "rms_norm_eps": 1e-05,
18
+ "rope_theta": 10000.0,
19
+ "sliding_window": 2048,
20
+ "tie_word_embeddings": false,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.34.0",
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
  }
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": "4.34.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.34.0"
6
  }