GPT2gpt2-medium: 8bits, gr128, desc_act=False

config.json

@@ -0,0 +1,41 @@
+{
+ "_name_or_path": "gpt2-medium",
+ "activation_function": "gelu_new",
+ "architectures": [
+ "GPT2LMHeadModel"
+ ],
+ "attn_pdrop": 0.1,
+ "bos_token_id": 50256,
+ "embd_pdrop": 0.1,
+ "eos_token_id": 50256,
+ "initializer_range": 0.02,
+ "layer_norm_epsilon": 1e-05,
+ "model_type": "gpt2",
+ "n_ctx": 1024,
+ "n_embd": 1024,
+ "n_head": 16,
+ "n_inner": null,
+ "n_layer": 24,
+ "n_positions": 1024,
+ "n_special": 0,
+ "predict_special_tokens": true,
+ "reorder_and_upcast_attn": false,
+ "resid_pdrop": 0.1,
+ "scale_attn_by_inverse_layer_idx": false,
+ "scale_attn_weights": true,
+ "summary_activation": null,
+ "summary_first_dropout": 0.1,
+ "summary_proj_to_labels": true,
+ "summary_type": "cls_index",
+ "summary_use_proj": true,
+ "task_specific_params": {
+ "text-generation": {
+ "do_sample": true,
+ "max_length": 50
+ }
+ },
+ "torch_dtype": "float16",
+ "transformers_version": "4.34.1",
+ "use_cache": true,
+ "vocab_size": 50257
+}

gptq_model-8bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad4f6424760eab23f7f7251f0ce9d984b578811a5ee9c3e56be516bbe89245e9
+size 415624978

gptq_model-8bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52d5ef4f69ac1f9b8d22527d7a596992a031b8b0a70eed2c34972027452bb5d5
+size 518409360

quantize_config.json

@@ -0,0 +1,11 @@
+{
+ "bits": 8,
+ "group_size": 128,
+ "damp_percent": 0.01,
+ "desc_act": false,
+ "static_groups": false,
+ "sym": true,
+ "true_sequential": true,
+ "model_name_or_path": "gpt2-mediumGPTQ8",
+ "model_file_base_name": "gptq_model-8bit-128g"
+}