Upload Phi3ForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- orpo
 ---
 
 # Model Card for Model ID

config.json

@@ -1,30 +1,50 @@
 {
-  "_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": 128256,
-  "eos_token_id": 128257,
+  "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": 32011,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32012,
   "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,
-  "pad_token_id": 128257,
-  "pretraining_tp": 1,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32012,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_storage": "uint8",
+    "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"
+  },
+  "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": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 128258
+  "vocab_size": 32013
 }

generation_config.json

@@ -1,10 +1,7 @@
 {
-  "bos_token_id": 128256,
-  "do_sample": true,
-  "eos_token_id": 128257,
-  "max_length": 4096,
-  "pad_token_id": 128257,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "_from_model_config": true,
+  "bos_token_id": 32011,
+  "eos_token_id": 32012,
+  "pad_token_id": 32012,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5f240baec74d082ddd7abc3325cf44e509e632319ab5bdb49272c054b1d3ba
+size 2692932856