Upload GPTNeoXForCausalLM

config.json

@@ -19,22 +19,31 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "quantization_config": {
+    "batch_size": 1,
     "bits": 8,
+    "block_name_to_quantize": "gpt_neox.layers",
     "damp_percent": 0.1,
     "dataset": "wikitext2",
     "desc_act": false,
+    "disable_exllama": false,
     "group_size": 128,
-    "modules_in_block_to_quantize": null,
+    "model_seqlen": 4096,
+    "module_name_preceding_first_block": [
+      "gpt_neox.embed_in",
+      "gpt_neox.emb_dropout"
+    ],
+    "pad_token_id": null,
     "quant_method": "gptq",
     "sym": true,
-    "true_sequential": true
+    "true_sequential": true,
+    "use_cuda_fp16": true
   },
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 0,
   "eos_token_id": 0,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.44.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21df5df7a94e64f164d99b48b1b2ba2b2a7d008c43cfc7f18d52b4004ae4c7df
+oid sha256:1ed0e1876b20f3357cd500eb63beb4bbd2691fb81675f660541d37cbefc611f6
 size 241993160