Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -8,6 +8,7 @@ tags:
 - unsloth
 - mistral
 - trl
+- sft
 base_model: unsloth/Phi-3-mini-4k-instruct-bnb-4bit
 ---
 

config.json

@@ -1,137 +1,40 @@
 {
-  "_name_or_path": "Phi-3-mini-128k-instruct",
+  "_name_or_path": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit",
   "architectures": [
-    "Phi3ForCausalLM"
+    "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "auto_map": {
-    "AutoConfig": "configuration_phi3.Phi3Config",
-    "AutoModelForCausalLM": "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": 131072,
-  "model_type": "phi3",
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
-  "original_max_position_embeddings": 4096,
   "pad_token_id": 32000,
-  "resid_pdrop": 0.0,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": {
-    "long_factor": [
-      1.0299999713897705,
-      1.0499999523162842,
-      1.0499999523162842,
-      1.0799999237060547,
-      1.2299998998641968,
-      1.2299998998641968,
-      1.2999999523162842,
-      1.4499999284744263,
-      1.5999999046325684,
-      1.6499998569488525,
-      1.8999998569488525,
-      2.859999895095825,
-      3.68999981880188,
-      5.419999599456787,
-      5.489999771118164,
-      5.489999771118164,
-      9.09000015258789,
-      11.579999923706055,
-      15.65999984741211,
-      15.769999504089355,
-      15.789999961853027,
-      18.360000610351562,
-      21.989999771118164,
-      23.079999923706055,
-      30.009998321533203,
-      32.35000228881836,
-      32.590003967285156,
-      35.56000518798828,
-      39.95000457763672,
-      53.840003967285156,
-      56.20000457763672,
-      57.95000457763672,
-      59.29000473022461,
-      59.77000427246094,
-      59.920005798339844,
-      61.190006256103516,
-      61.96000671386719,
-      62.50000762939453,
-      63.3700065612793,
-      63.48000717163086,
-      63.48000717163086,
-      63.66000747680664,
-      63.850006103515625,
-      64.08000946044922,
-      64.760009765625,
-      64.80001068115234,
-      64.81001281738281,
-      64.81001281738281
-    ],
-    "short_factor": [
-      1.05,
-      1.05,
-      1.05,
-      1.1,
-      1.1,
-      1.1500000000000001,
-      1.2000000000000002,
-      1.2500000000000002,
-      1.3000000000000003,
-      1.3500000000000003,
-      1.5000000000000004,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.000000000000001,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.0500000000000007,
-      2.1000000000000005,
-      2.1000000000000005,
-      2.1000000000000005,
-      2.1500000000000004,
-      2.1500000000000004,
-      2.3499999999999996,
-      2.549999999999999,
-      2.5999999999999988,
-      2.5999999999999988,
-      2.7499999999999982,
-      2.849999999999998,
-      2.849999999999998,
-      2.9499999999999975
-    ],
-    "type": "su"
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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_theta": 10000.0,
-  "sliding_window": 262144,
+  "sliding_window": 2048,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.5",
   "use_cache": true,
   "vocab_size": 32064
-}
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 32000,
+  "pad_token_id": 32000,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99310e83b03a0e394e503026b3f9747bfd54c155e2811d1d0f417240755a8419
+size 2264298173