Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: unsloth/Qwen2-1.5B-Instruct
 language:
 - en
 license: apache-2.0
@@ -9,7 +10,6 @@ tags:
 - qwen2
 - trl
 - sft
-base_model: unsloth/Qwen2-1.5B-Instruct
 ---
 
 # Uploaded  model

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "unsloth/Qwen2-1.5B-Instruct",
+  "_name_or_path": "unsloth/qwen2-1.5b-instruct-bnb-4bit",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
@@ -16,13 +16,25 @@
   "num_attention_heads": 12,
   "num_hidden_layers": 28,
   "num_key_value_heads": 2,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "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-06,
   "rope_theta": 1000000.0,
   "sliding_window": 32768,
   "tie_word_embeddings": true,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.1",
-  "unsloth_version": "2024.5",
+  "transformers_version": "4.41.2",
+  "unsloth_version": "2024.6",
   "use_cache": true,
   "use_sliding_window": false,
   "vocab_size": 151936

generation_config.json

@@ -10,5 +10,5 @@
   "temperature": 0.7,
   "top_k": 20,
   "top_p": 0.8,
-  "transformers_version": "4.40.1"
+  "transformers_version": "4.41.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fa1f1630ad69cca0022e8c1089997e443c162a79ecd25a5e2716e41eecc4a09
+size 1217251687