unsloth
/

Qwen2-1.5B-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

cc30f2c

•

1 Parent(s): 032cd61

Upload config

Files changed (1) hide show

config.json +3 -1

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2-1.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -16,6 +16,7 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
@@ -37,6 +38,7 @@
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

 {
+  "_name_or_path": "unsloth/Qwen2-1.5B",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
+  "pad_token_id": 151646,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.0",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936