unsloth
/

Mistral-Nemo-Base-2407-bnb-4bit

Text Generation

text-generation-inference

Inference Endpoints

4-bit precision

Model card Files Files and versions Community

danielhanchen commited on Aug 7

Commit

483aaa3

•

1 Parent(s): 0130a06

Upload config

Files changed (1) hide show

config.json +3 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mistralai/Mistral-Nemo-Base-2407",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -16,6 +16,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 8,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -37,6 +38,7 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 131072
 }

 {
+  "_name_or_path": "unsloth/Mistral-Nemo-Base-2407",
   "architectures": [
     "MistralForCausalLM"
   ],
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 8,
+  "pad_token_id": 10,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 131072
 }