TheBloke
/

Airoboros-L2-70B-2.1-GPTQ

Text Generation

text-generation-inference

4-bit precision

Model card Files Files and versions Community

TheBloke commited on Aug 29, 2023

Commit

bda8561

•

1 Parent(s): 5cb3869

Initial GPTQ model commit

Files changed (1) hide show

config.json +4 -4

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-    "_name_or_path": "airoboros-l2-70b-2.1",
     "architectures": [
         "LlamaForCausalLM"
     ],
@@ -15,14 +15,14 @@
     "num_hidden_layers": 80,
     "num_key_value_heads": 8,
     "pad_token_id": 0,
-    "pretraining_tp": 1,
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.32.0",
     "use_cache": true,
     "vocab_size": 32000,
     "quantization_config": {
         "bits": 4,
         "group_size": -1,

 {
+    "_name_or_path": "llama-2-70b-hf",
     "architectures": [
         "LlamaForCausalLM"
     ],
     "num_hidden_layers": 80,
     "num_key_value_heads": 8,
     "pad_token_id": 0,
     "rms_norm_eps": 1e-05,
     "rope_scaling": null,
     "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.31.0",
     "use_cache": true,
     "vocab_size": 32000,
+    "pretraining_tp": 1,
     "quantization_config": {
         "bits": 4,
         "group_size": -1,