replace auto-round format

Signed-off-by: wenhuach <wenhuach87@gmail.com>

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,231 @@
+{
+  "_name_or_path": "/data5/models/Qwen2-57B-A14B-Instruct",
+  "architectures": [
+    "Qwen2MoeForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen2_moe",
+  "moe_intermediate_size": 2560,
+  "norm_topk_prob": false,
+  "num_attention_heads": 28,
+  "num_experts": 64,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "quantization_config": {
+    "amp": true,
+    "autoround_version": "0.3.1.dev",
+    "backend": "auto_round:gptq:exllamav2",
+    "bits": 4,
+    "data_type": "int",
+    "dataset": "NeelNanda/pile-10k",
+    "enable_minmax_tuning": true,
+    "enable_norm_bias_tuning": false,
+    "enable_quanted_input": true,
+    "extra_config": {
+      "model.layers.0.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.1.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.10.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.11.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.12.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.13.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.14.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.15.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.16.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.17.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.18.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.19.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.2.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.20.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.21.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.22.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.23.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.24.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.25.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.26.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.27.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.3.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.4.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.5.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.6.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.7.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.8.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      },
+      "model.layers.9.mlp.shared_expert_gate": {
+        "bits": 32,
+        "data_type": "float",
+        "group_size": null,
+        "sym": null
+      }
+    },
+    "gradient_accumulate_steps": 1,
+    "group_size": 128,
+    "iters": 1000,
+    "low_gpu_mem_usage": false,
+    "lr": 0.001,
+    "minmax_lr": 0.001,
+    "nsamples": 512,
+    "quant_block_list": null,
+    "quant_method": "intel/auto-round",
+    "scale_dtype": "torch.float16",
+    "seqlen": 2048,
+    "sym": true,
+    "train_bs": 8
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.001,
+  "shared_expert_intermediate_size": 20480,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e113ea93ed860c0e9c07f27fa684b647188b336cc5e3d680d83e4a8281bf2d5
+size 4997691976

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4e45b31b31165c6e4687c770d478cfe9a029de31673fa2ca0413e91c1a872bc
+size 4996621008

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f84c17dba989ee536cd53fc0f685c924e618ae76935786e50bce54373999148
+size 4996623024

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13108599956b113ef62793f0aa17c76783d73c4b1281b26c374b5499848d06df
+size 4996623936

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd22f2bc3f2868746e5ecb45fd8d765646167e0facf62ff332a00629e57cd74a
+size 5000294216

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8947429a5f121c56024ec3c471bf29c8e762cf68363953701ff1c7a177f178b
+size 4996623952

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9186f14b77e28e65f2640a3c2346fdab0a2158caa55c22af0a33963b842032cb
+size 1456164256

quantization_config.json

@@ -0,0 +1,194 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "sym": true,
+  "data_type": "int",
+  "enable_quanted_input": true,
+  "enable_minmax_tuning": true,
+  "seqlen": 2048,
+  "train_bs": 8,
+  "scale_dtype": "torch.float16",
+  "lr": 0.001,
+  "minmax_lr": 0.001,
+  "gradient_accumulate_steps": 1,
+  "iters": 1000,
+  "amp": true,
+  "nsamples": 512,
+  "low_gpu_mem_usage": false,
+  "quant_block_list": null,
+  "enable_norm_bias_tuning": false,
+  "dataset": "NeelNanda/pile-10k",
+  "autoround_version": "0.3.1.dev",
+  "quant_method": "intel/auto-round",
+  "backend": "auto_round:gptq:exllamav2",
+  "extra_config": {
+    "model.layers.0.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.1.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.2.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.3.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.4.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.5.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.6.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.7.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.8.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.9.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.10.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.11.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.12.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.13.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.14.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.15.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.16.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.17.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.18.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.19.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.20.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.21.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.22.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.23.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.24.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.25.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.26.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    },
+    "model.layers.27.mlp.shared_expert_gate": {
+      "data_type": "float",
+      "bits": 32,
+      "group_size": null,
+      "sym": null
+    }
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 65536,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}