unsloth
/

codellama-7b-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

48ef5f1

•

1 Parent(s): f36ad61

Upload config

Files changed (1) hide show

config.json +4 -2

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "codellama/CodeLlama-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -17,6 +17,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
@@ -38,7 +39,8 @@
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 32016
 }

 {
+  "_name_or_path": "unsloth/codellama-7b",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
+  "pad_token_id": 0,
   "pretraining_tp": 1,
   "quantization_config": {
     "_load_in_4bit": true,
   "rope_theta": 1000000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 32016
 }