GPTQ model commit

config.json

@@ -0,0 +1,60 @@
+{
+    "_name_or_path": "/workspace/process/clibrain_lince-zero/source",
+    "alibi": false,
+    "apply_residual_connection_post_layernorm": false,
+    "architectures": [
+        "FalconForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "auto_map": {
+        "AutoConfig": "configuration_falcon.FalconConfig",
+        "AutoModel": "modeling_falcon.FalconModel",
+        "AutoModelForCausalLM": "modeling_falcon.FalconForCausalLM",
+        "AutoModelForQuestionAnswering": "modeling_falcon.FalconForQuestionAnswering",
+        "AutoModelForSequenceClassification": "modeling_falcon.FalconForSequenceClassification",
+        "AutoModelForTokenClassification": "modeling_falcon.FalconForTokenClassification"
+    },
+    "bias": false,
+    "bos_token_id": 11,
+    "eos_token_id": 11,
+    "hidden_dropout": 0.0,
+    "hidden_size": 4544,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
+    "max_position_embeddings": 2048,
+    "model_type": "falcon",
+    "multi_query": true,
+    "new_decoder_architecture": false,
+    "num_attention_heads": 71,
+    "num_hidden_layers": 32,
+    "num_kv_heads": 71,
+    "pad_token_id": 0,
+    "parallel_attn": true,
+    "pretraining_tp": 1,
+    "quantization_config": {
+        "batch_size": 1,
+        "bits": 4,
+        "block_name_to_quantize": "transformer.h",
+        "damp_percent": 0.1,
+        "desc_act": true,
+        "disable_exllama": true,
+        "group_size": 128,
+        "max_input_length": null,
+        "model_seqlen": 2048,
+        "module_name_preceding_first_block": [
+            "transformer.word_embeddings"
+        ],
+        "pad_token_id": null,
+        "quant_method": "gptq",
+        "sym": true,
+        "tokenizer": null,
+        "true_sequential": true,
+        "use_cuda_fp16": true
+    },
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "torch_dtype": "float16",
+    "transformers_version": "4.34.0.dev0",
+    "use_cache": true,
+    "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.30.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:735e69883e7dfbb72db218d365fb0819c46c48dfc80e2dd7b317acce6993c902
+size 4041221560

quantize_config.json

@@ -0,0 +1,8 @@
+{
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": true,
+    "sym": true,
+    "true_sequential": true
+}

special_tokens_map.json

@@ -0,0 +1,16 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>MIDDLE<<"
+  ],
+  "eos_token": "<|endoftext|>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "add_prefix_space": false,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}