Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -2,6 +2,8 @@
 library_name: transformers
 tags:
 - unsloth
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -17,14 +17,26 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pad_token_id": 770,
+  "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_scaling": null,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.45.0",
-  "unsloth_version": "2024.9.post3",
+  "transformers_version": "4.44.2",
+  "unsloth_version": "2024.9.post4",
   "use_cache": true,
   "vocab_size": 32768
 }

generation_config.json

@@ -4,5 +4,5 @@
   "eos_token_id": 2,
   "max_length": 32768,
   "pad_token_id": 770,
-  "transformers_version": "4.45.0"
+  "transformers_version": "4.44.2"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7e049ebf68dc43f6c6e277b3c78d7539519e119ea211050e918b8fe7b1de848
+size 4138577009