unsloth
/

llama-3-8b-Instruct-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

a40f036

•

1 Parent(s): c8d54b5

Upload config

Files changed (1) hide show

config.json +5 -5

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-70B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -8,14 +8,14 @@
   "bos_token_id": 128000,
   "eos_token_id": 128009,
   "hidden_act": "silu",
-  "hidden_size": 8192,
   "initializer_range": 0.02,
-  "intermediate_size": 28672,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 80,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {

 {
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "bos_token_id": 128000,
   "eos_token_id": 128009,
   "hidden_act": "silu",
+  "hidden_size": 4096,
   "initializer_range": 0.02,
+  "intermediate_size": 14336,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {