Upload folder using huggingface_hub

compressed_config.json

@@ -0,0 +1,28 @@
+{
+  "format": "mindpipe_hf_save_pretrained_debug",
+  "algorithm": "smoothquant",
+  "model_path": "/mnt/82_store/LLM-weights/Llama-2-7b-hf",
+  "result_dir": "/mnt/82_store/wxx/HWQuant/Mindpipe/results/Llama-2-7b-hf/smoothquant/smoothquant_w8a8_seq512_alpha0p85",
+  "weight_bits": 8,
+  "activation_bits": 8,
+  "sequence_length": 512,
+  "group_size": 128,
+  "output_dir": "/mnt/82_store/wxx/HWQuant/Mindpipe/tmp_hf_save/Llama-2-7b-hf-SmoothQuant-w8a8/_pre_save_workflow",
+  "pre_save_metrics": {
+    "perplexity": 6.480299961179449,
+    "evaluation_dataset": "wikitext2",
+    "sequence_length": 512,
+    "evaluated_chunks": 4,
+    "batch_size": 1,
+    "elapsed_seconds": 1.3628588523715734,
+    "tokens_per_second": 1499.7884751184185,
+    "model_path": "/mnt/82_store/LLM-weights/Llama-2-7b-hf",
+    "quantization_algorithm": "smoothquant",
+    "weight_bits": 8,
+    "activation_bits": 8,
+    "device": "cuda:0",
+    "dtype": "float16",
+    "artifacts_path": "artifacts.json"
+  },
+  "load_note": "Use MindPipe to rebuild the compression structure before loading the HF state dict."
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

extra_artifacts/act_scales.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3c6023f407f6b4d5ad0a8204558be314f8aec2851a65d2ccadfc1decb0ee8c
+size 4623921

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "5.5.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd242f7204fbea2b193c17e4771592815f468112dd74e6b57a4a349d98d6b628
+size 13476864944

reload_metrics.json

@@ -0,0 +1,32 @@
+{
+  "perplexity": 6.480299961179449,
+  "evaluation_dataset": "wikitext2",
+  "sequence_length": 512,
+  "evaluated_chunks": 4,
+  "batch_size": 1,
+  "elapsed_seconds": 0.5743283228948712,
+  "tokens_per_second": 3558.9399277704556,
+  "ppl_comparison": {
+    "checked": true,
+    "passed": true,
+    "pre_save_ppl": 6.480299961179449,
+    "reload_ppl": 6.480299961179449,
+    "abs_diff": 0.0,
+    "rel_diff": 0.0,
+    "abs_tol": 0.0001,
+    "rel_tol": 1e-05
+  },
+  "original_ppl_comparison": {
+    "checked": true,
+    "passed": false,
+    "original_result_ppl": 7.168461910124875,
+    "pre_save_ppl": 6.480299961179449,
+    "reload_ppl": 6.480299961179449,
+    "pre_abs_diff": 0.6881619489454254,
+    "pre_rel_diff": 0.0959985499781274,
+    "reload_abs_diff": 0.6881619489454254,
+    "reload_rel_diff": 0.0959985499781274,
+    "abs_tol": 0.0001,
+    "rel_tol": 1e-05
+  }
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}