Trained with Unsloth

Upload model trained with Unsloth 2x faster

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: unsloth/mistral-7b-bnb-4bit
 language:
 - en
 license: apache-2.0
@@ -8,7 +9,6 @@ tags:
 - unsloth
 - mistral
 - trl
-base_model: unsloth/mistral-7b-bnb-4bit
 ---
 
 # Uploaded  model

config.json

@@ -6,6 +6,7 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -15,7 +16,7 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
-  "pad_token_id": 2,
+  "pad_token_id": 0,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "bfloat16",
     "bnb_4bit_quant_type": "nf4",
@@ -29,12 +30,13 @@
     "quant_method": "bitsandbytes"
   },
   "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.39.3",
-  "unsloth_version": "2024.4",
+  "transformers_version": "4.44.0",
+  "unsloth_version": "2024.8",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.39.3"
+  "max_length": 32768,
+  "pad_token_id": 0,
+  "transformers_version": "4.44.0"
 }