Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,6 +1,9 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- unsloth
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "codegood/DistHermYam-7B-ties",
+  "_name_or_path": "codegood/DistHermYam-7B-ties-bnb-4bit",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -17,9 +17,7 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": true,
     "llm_int8_enable_fp32_cpu_offload": false,
@@ -34,8 +32,9 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.38.2",
+  "torch_dtype": "float16",
+  "transformers_version": "4.39.1",
+  "unsloth_version": "2024.3",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.39.1"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02893f3f5dfa4684ab9994d487245d86e652224b9b2b077adc0a5514cb6cf4fb
-size 4125687695
+oid sha256:70103b70880c68146bd8247c2420c0fb937b7c7c5e6fc9dd5cca73dc8ba79ec1
+size 4125687611