Update GPTQ model, quantised with sequence_length=8192

config.json

@@ -1,39 +1,39 @@
 {
-    "_name_or_path": "/fsx/bigcode/experiments/pretraining/conversions/starcoderplus/large-model",
-    "activation_function": "gelu",
-    "architectures": [
-        "GPTBigCodeForCausalLM"
-    ],
-    "attention_softmax_in_fp32": true,
-    "multi_query": true,
-    "attn_pdrop": 0.1,
-    "bos_token_id": 0,
-    "embd_pdrop": 0.1,
-    "eos_token_id": 0,
-    "inference_runner": 0,
-    "initializer_range": 0.02,
-    "layer_norm_epsilon": 1e-05,
-    "max_batch_size": null,
-    "max_sequence_length": null,
-    "model_type": "gpt_bigcode",
-    "n_embd": 6144,
-    "n_head": 48,
-    "n_inner": 24576,
-    "n_layer": 40,
-    "n_positions": 8192,
-    "pad_key_length": true,
-    "pre_allocate_kv_cache": false,
-    "resid_pdrop": 0.1,
-    "scale_attention_softmax_in_fp32": true,
-    "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": "float32",
-    "transformers_version": "4.28.1",
-    "use_cache": true,
-    "validate_runner_input": true,
-    "vocab_size": 49152
-}
+  "_name_or_path": "/workspace/process/starcoderplus/source",
+  "activation_function": "gelu",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "multi_query": true,
+  "n_embd": 6144,
+  "n_head": 48,
+  "n_inner": 24576,
+  "n_layer": 40,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "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": "4.30.0.dev0",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}

gptq_model-4bit--1g.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670fbd11d17ee50b41deb548dd448d8718a2f3f3ebba0ecb77973bb8f1bf3080
+oid sha256:5d7020dc8e70f8efe417ffeb2f78e4b1089a234543a9254248e3ff85607a5a4c
 size 8906589520