Upload MistralForCausalLM

config.json

@@ -4,8 +4,8 @@
     "MistralForCausalLM"
   ],
   "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
+  "bos_token_id": 32768,
+  "eos_token_id": 32769,
   "head_dim": 128,
   "hidden_act": "silu",
   "hidden_size": 4096,
@@ -16,13 +16,14 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
+  "pad_token_id": 32769,
   "quantization_config": {
     "_load_in_4bit": true,
     "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_storage": "uint8",
     "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": true,
+    "bnb_4bit_use_double_quant": false,
     "llm_int8_enable_fp32_cpu_offload": false,
     "llm_int8_has_fp16_weight": false,
     "llm_int8_skip_modules": null,
@@ -36,7 +37,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.0",
+  "transformers_version": "4.44.2",
   "use_cache": true,
-  "vocab_size": 32768
+  "vocab_size": 32770
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.44.0"
+  "bos_token_id": 32768,
+  "eos_token_id": 32769,
+  "pad_token_id": 32769,
+  "transformers_version": "4.44.2"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e252a89503ab5e34bf7a4fb04a1491ceef59e576b2997c18c36ac36a19c6d55
+size 4539512136

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6cf0d2410ef6cf8dc07cf1b6e6cfd756655b9e45b8ad778f66308cdd5ed8942
+size 536903808