Upload folder using huggingface_hub

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "Qwen/Qwen-14B",
+  "architectures": [
+    "QWenLMHeadModel"
+  ],
+  "attn_dropout_prob": 0.0,
+  "auto_map": {
+    "AutoConfig": "Qwen/Qwen-14B--configuration_qwen.QWenConfig",
+    "AutoModelForCausalLM": "Qwen/Qwen-14B--modeling_qwen.QWenLMHeadModel"
+  },
+  "bf16": true,
+  "emb_dropout_prob": 0.0,
+  "fp16": false,
+  "fp32": false,
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27392,
+  "kv_channels": 128,
+  "layer_norm_epsilon": 1e-06,
+  "max_position_embeddings": 8192,
+  "model_type": "qwen",
+  "no_bias": true,
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "onnx_safe": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 1.0,
+  "scale_attn_weights": true,
+  "seq_length": 2048,
+  "softmax_in_fp32": false,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "QWenTokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0",
+  "use_cache": true,
+  "use_cache_kernel": false,
+  "use_cache_quantization": false,
+  "use_dynamic_ntk": true,
+  "use_flash_attn": true,
+  "use_logn_attn": true,
+  "vocab_size": 152064
+}

pytorch_model.bin.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221682e1db942c8e57999254f9608b9a8bcd5c63a9e3b0b2486d13e5633cb160
+size 16029578416

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 8,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": "pytorch_model.bin"
+}