upload awq format

Signed-off-by: n1ck-guo <heng.guo@intel.com>

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "/models/falcon3-3B",
+  "activation": "swiglu",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "parallel_attn": false,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "amp": true,
+    "autoround_version": "0.4.2",
+    "batch_size": 8,
+    "bits": 4,
+    "data_type": "int",
+    "dataset": "NeelNanda/pile-10k",
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "gradient_accumulate_steps": 1,
+    "group_size": 128,
+    "iters": 2000,
+    "low_gpu_mem_usage": false,
+    "lr": 0.0005,
+    "minmax_lr": 0.0005,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "nsamples": 512,
+    "quant_method": "awq",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "sym": true,
+    "to_quant_block_names": null,
+    "version": "gemm",
+    "zero_point": false
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 11,
+  "eos_token_id": 11,
+  "transformers_version": "4.47.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c562834450322997adf80173189f7e92325ea891c0cf392ffadcba9b0738962
+size 2869360568

quantization_config.json

@@ -0,0 +1,28 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 2048,
+  "batch_size": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 0.0005,
+  "minmax_lr": 0.0005,
+  "gradient_accumulate_steps": 1,
+  "iters": 2000,
+  "amp": true,
+  "nsamples": 512,
+  "low_gpu_mem_usage": false,
+  "to_quant_block_names": null,
+  "enable_norm_bias_tuning": false,
+  "dataset": "NeelNanda/pile-10k",
+  "autoround_version": "0.4.2",
+  "quant_method": "awq",
+  "zero_point": false,
+  "version": "gemm",
+  "modules_to_not_convert": [
+    "lm_head"
+  ]
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}