Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,29 +1,40 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "_name_or_path": "unsloth/mistral-7b-bnb-4bit",
   "architectures": [
-    "LlamaForCausalLM"
+    "MistralForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 14336,
-  "max_position_embeddings": 8192,
-  "model_type": "llama",
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
   "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": "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-05,
-  "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
   "unsloth_version": "2024.5",
   "use_cache": true,
-  "vocab_size": 128256
+  "vocab_size": 32000
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "transformers_version": "4.40.2"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f55df046b549c27c3f0a548a8a7931787b29bac4469317cc5990a505ca93f3
+size 4125687674