MNCLLM
/

Mistral-7B-OP-over500-grad1.0

Text Generation

Inference Endpoints

text-generation-inference

Model card Files Files and versions Community

MNCLLM commited on Oct 25, 2023

Commit

f7789c5

•

1 Parent(s): f020494

Upload config

Files changed (1) hide show

config.json +3 -6

config.json CHANGED Viewed

@@ -1,9 +1,8 @@
 {
-  "_name_or_path": "/data/models/koLLM/Mistral-7B-v0.1/orca_platy_output_500over_/batch1_epochs2_lr1e-05_paged_adamw_32bit_cosine_length4096_warmup_0.05_max_grad1.0_grad_accu10/",
   "architectures": [
-    "LlamaForCausalLM"
   ],
-  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -11,13 +10,11 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
-  "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,

 {
+  "_name_or_path": "mistralai/Mistral-7B-v0.1",
   "architectures": [
+    "MistralForCausalLM"
   ],
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,