Upload MistralForCausalLM

config.json

@@ -16,28 +16,11 @@
   "num_attention_heads": 32,
   "num_hidden_layers": 40,
   "num_key_value_heads": 8,
-  "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": [
-      "lm_head"
-    ],
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_theta": 1000000.0,
   "sliding_window": null,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.46.3",
   "use_cache": true,
   "vocab_size": 131072

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bcae2ef6979f19127eed5afa07ddf9815401fff6e70621dc343e44ae429c836
+size 4865522496

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55deb2ec0bfb9f9e73d7718888d07f52b8af287c4252506bba556d9f71dc9af
+size 4907529424

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9737968e97d35f1177a1f1de6e2d46d1c96f19805a798d16b29feb8df3baec0
+size 4907529456

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb0174975713c43e5275e91ea636841d3ae2850d5d2196e2dd229572e9a66bbe
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac8adc29e7fd06e4c18f2902205c98e54bf01a3f6f8d7e64f64506d7fa28f17
+size 4907496272