Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "codegood/Unsloth_Mistral_YU_4bit_new",
+  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -15,7 +15,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 0,
+  "pad_token_id": 2,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
@@ -29,11 +29,11 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
-  "rope_theta": 1000000.0,
-  "sliding_window": null,
+  "rope_theta": 10000.0,
+  "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": 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:c17fb33de3379ec94aaf80a8b88800c82d3b73188c8520962adf4e56e2e7f47e
-size 4125687610
+oid sha256:21c7dbb10e17cd4c04370d2594f99d6f05d3c4b22f5ec874bc3d36833ae96048
+size 4125687621