Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/workspace/open-calm/",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_parallel_residual": false,
+  "vocab_size": 52224
+}

gptq_model-4bit-32g.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568bcd0ea9d17b2bd4bcf011bdad50115f53ab28f2c5b0b2c103375448f2566c
+size 4587576709

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}