AutoGPTQ model for ruGPT-13B: 4bits, gr128, desc_act=False

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "ruGPT-13B",
+  "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": 2048,
+  "n_embd": 5120,
+  "n_head": 40,
+  "n_inner": null,
+  "n_layer": 40,
+  "n_positions": 2048,
+  "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,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "vocab_size": 50272
+}

gptq_model-4bit-128g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b288cd40d36a00661cdd27c691bb6070b5ff380e6f06d6830cf995ed0ab6a677
+size 7252192499

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0352afefdae9a149bc23d06882d4b56b61627b13c4909ad68e2318022cb98028
+size 7766721696

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": "ruGPT-13B-4bit",
+  "model_file_base_name": "gptq_model-4bit-128g"
+}