Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "codegood/DistHermYam-7B-ties-bnb-4bit",
+  "_name_or_path": "codegood/DistHermYam-7B-ties",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pretraining_tp": 1,
+  "pad_token_id": 2,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
@@ -33,8 +33,8 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.39.1",
+  "transformers_version": "4.39.3",
   "unsloth_version": "2024.3",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.1"
+  "transformers_version": "4.39.3"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8b6316e4a0406f91b3cc0e4a0b642de0eddbce74696ce110e97d3ef30aebb89
-size 4125687614
+oid sha256:b1a2e85d1f1ca182ad051e6daa7a6c74d116385c2a34a8ea526e7fb38c1da4fc
+size 4125687616