Upload Phi3ForCausalLM

config.json

@@ -1,29 +1,34 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
   "architectures": [
-    "LlamaForCausalLM"
+    "Phi3ForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "auto_map": {
+    "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 3072,
   "initializer_range": 0.02,
-  "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "mlp_bias": false,
-  "model_type": "llama",
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
-  "num_key_value_heads": 8,
-  "pretraining_tp": 1,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_compute_dtype": "float32",
     "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_quant_type": "fp4",
     "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
@@ -33,12 +38,14 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
+  "resid_pdrop": 0.0,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000.0,
+  "sliding_window": 2047,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "use_cache": false,
-  "vocab_size": 128256
+  "use_cache": true,
+  "vocab_size": 32064
 }

generation_config.json

@@ -1,9 +1,11 @@
 {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5426c1ad1d14ae1dfb0f4261c018e5f3e0e818ade37f80c804d04b2ac63e8e
+size 2827324312