GPTQ model commit

config.json

@@ -0,0 +1,37 @@
+{
+    "_name_or_path": "/workspace/process/lumiopen_poro-34b/source",
+    "apply_residual_connection_post_layernorm": false,
+    "architectures": [
+        "BloomForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "attention_softmax_in_fp32": true,
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_dropout": 0.0,
+    "hidden_size": 7168,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "masked_softmax_fusion": true,
+    "model_type": "bloom",
+    "n_head": 56,
+    "n_layer": 54,
+    "pad_token_id": 3,
+    "pretraining_tp": 1,
+    "slow_but_exact": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.35.2",
+    "use_cache": true,
+    "vocab_size": 128000,
+    "quantization_config": {
+        "bits": 4,
+        "group_size": 32,
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "sym": true,
+        "true_sequential": true,
+        "model_name_or_path": null,
+        "model_file_base_name": "model",
+        "quant_method": "gptq"
+    }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f250cb4a94919cd49fa3de1528a78808c40268ca6893f61c0b0fb91538a7a039
+size 22939449056

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 32,
+  "damp_percent": 0.1,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "model"
+}

special_tokens_map.json

@@ -0,0 +1,28 @@
+{
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}