Upload of AutoGPTQ quantized model

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "OpenAssistant/falcon-40b-sft-mix-1226",
+  "alibi": false,
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "RWForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "OpenAssistant/falcon-40b-sft-mix-1226--configuration_RW.RWConfig",
+    "AutoModel": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWModel",
+    "AutoModelForCausalLM": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForCausalLM",
+    "AutoModelForQuestionAnswering": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForQuestionAnswering",
+    "AutoModelForSequenceClassification": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForSequenceClassification",
+    "AutoModelForTokenClassification": "OpenAssistant/falcon-40b-sft-mix-1226--modelling_RW.RWForTokenClassification"
+  },
+  "bias": false,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "hidden_dropout": 0.0,
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "RefinedWeb",
+  "n_head": 128,
+  "n_head_kv": 8,
+  "n_layer": 60,
+  "parallel_attn": true,
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 65040
+}

gptq_model-4bit-128g.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db95563e1914cec1d13d640822e88f7cd6392f76cf49f14469135ab30d993e27
+size 23336713200

quantize_config.json

@@ -0,0 +1,10 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": true,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": [
+    ">>MIDDLE<<",
+    "<|prompter|>",
+    ">>ABSTRACT<<",
+    ">>DOMAIN<<",
+    "<|prefix_begin|>",
+    "<|assistant|>",
+    ">>SUMMARY<<",
+    "<|prefix_end|>",
+    ">>INTRODUCTION<<",
+    ">>TITLE<<",
+    ">>PREFIX<<",
+    ">>SUFFIX<<",
+    ">>ANSWER<<",
+    "<|system|>",
+    ">>QUESTION<<",
+    ">>COMMENT<<"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "sep_token": "<|endoftext|>"
+}

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"
+}