Upload GptOssForCausalLM

config.json

@@ -47,6 +47,21 @@
   "num_local_experts": 32,
   "output_router_logits": false,
   "pad_token_id": 199999,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "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": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "beta_fast": 32.0,

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6144f0b8c6c68fbe771ce0bee1a45484ddcfa0cf8eefd1c2535462b8f3df7af6
+size 4993602118

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ed0071303019e5eebfd4734019ac63492a1340f90e6df45e35451a85be5ee9
+size 4996013148

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5215bfd3dc6194ca0849064560167581cfda2fcbb4fbb72c01bcd20dace90b2f
+size 3451566750