Upload generation_config.json with huggingface_hub

generation_config.json

@@ -1,40 +1,7 @@
 {
-  "_name_or_path": "/apdcephfs/share_733425/timhuang/fanqiwan/PLMs/llemma-34b",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
+  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 8192,
-  "initializer_range": 0.02,
-  "intermediate_size": 22016,
-  "max_position_embeddings": 4096,
-  "model_type": "llama",
-  "num_attention_heads": 64,
-  "num_hidden_layers": 48,
-  "num_key_value_heads": 8,
   "pad_token_id": 0,
-  "pretraining_tp": 1,
-  "quantization_config": {
-    "bnb_4bit_compute_dtype": "bfloat16",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.34.1",
-  "use_cache": true,
-  "vocab_size": 32000
+  "transformers_version": "4.34.1"
 }