Upload GPTNeoForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "EleutherAI/gpt-neo-125m",
   "activation_function": "gelu_new",
   "architectures": [
     "GPTNeoForCausalLM"
@@ -28,6 +29,7 @@
     ]
   ],
   "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
   "embed_dropout": 0,
   "eos_token_id": 50256,
   "gradient_checkpointing": false,
@@ -39,14 +41,31 @@
   "model_type": "gpt_neo",
   "num_heads": 12,
   "num_layers": 12,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "resid_dropout": 0,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.9.0.dev0",
-  "use_cache": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": false,
   "vocab_size": 50257,
   "window_size": 256
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e473f1e5a49e4498949c0204792b247e4a4d23d199fc0de8c6c7dd06375d114d
+size 220685232