updated to latest SFT version

config.json

@@ -1,36 +1,51 @@
 {
-    "architectures": [
-        "Phi3ForCausalLM"
-    ],
-    "attention_bias": false,
-    "attention_dropout": 0.0,
-    "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": 3072,
-    "initializer_range": 0.02,
-    "intermediate_size": 8192,
-    "max_position_embeddings": 4096,
-    "model_type": "phi3",
-    "num_attention_heads": 32,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 32,
-    "original_max_position_embeddings": 4096,
-    "pad_token_id": 32000,
-    "partial_rotary_factor": 1.0,
-    "resid_pdrop": 0.0,
-    "rms_norm_eps": 1e-05,
-    "rope_scaling": null,
-    "rope_theta": 10000.0,
-    "sliding_window": 2047,
-    "tie_word_embeddings": false,
-    "torch_dtype": "float16",
-    "transformers_version": "4.52.4",
-    "use_cache": true,
-    "vocab_size": 32064
-}
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "dtype": "float16",
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "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": 10000.0,
+  "sliding_window": 2047,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}

generation_config.js

@@ -1,11 +0,0 @@
-{
-    "_from_model_config": true,
-    "bos_token_id": 1,
-    "eos_token_id": [
-      32000,
-      32001,
-      32007
-    ],
-    "pad_token_id": 32000,
-    "transformers_version": "4.52.4"
-  }

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    32000,
+    32001,
+    32007
+  ],
+  "pad_token_id": 32000,
+  "transformers_version": "4.56.0"
+}

model-00002-of-00002.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1bf27ad0a0e81bee50b5d3266c7e7a52bc61e5f3b1f8cb98c702dbd74d49c483
-size 2669692488

model-00001-of-00002.safetensors → model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2d16a4618df2b1aa1ceb49746a483de843c5f8bda9c0c78405f1b67f6f8d53d
-size 4972489200
+oid sha256:c4ddeba03d42e37d4ee3a2e83e1f97f7aac52a1136e201289b519aee709e91d2
+size 2264109938