Upload PhiForCausalLM

config.json

@@ -19,6 +19,30 @@
   "num_key_value_heads": 32,
   "partial_rotary_factor": 0.4,
   "qk_layernorm": false,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 4,
+    "block_name_to_quantize": null,
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": null,
+    "module_name_preceding_first_block": null,
+    "modules_in_block_to_quantize": null,
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": false,
+    "use_exllama": true
+  },
   "resid_pdrop": 0.1,
   "rope_scaling": null,
   "rope_theta": 10000.0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c42e73d1e5c308f32604ad0e601d10e74003f007c17cea8126f92b6bd4f9012
-size 524735712
+oid sha256:6bc9a7ab5c39038a0e3af61847a6ecce0c2a30ba28518fde79043b51811db6d7
+size 1836707464