4-bit 128g

config.json

@@ -1,8 +1,9 @@
 {
-  "_name_or_path": "SthenoWriter-L2-13B",
+  "_name_or_path": "./hf_weights/Stheno-1.10-L2-13B/",
   "architectures": [
     "LlamaForCausalLM"
   ],
+  "attention_bias": false,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -21,7 +22,18 @@
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0.dev0",
+  "transformers_version": "4.35.2",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32000,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "damp_percent": 0.01,
+    "desc_act": false,
+    "static_groups": false,
+    "sym": true,
+    "true_sequential": true,
+    "model_name_or_path": null,
+    "model_file_base_name": null
+  }
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d0e49caef515dcd7ece3fd2d16ddf8b165719a8457fdf8bf585a4cbed2615b2
+size 7259435192

quantize_config.json

@@ -0,0 +1,11 @@
+{
+  "bits": 4,
+  "group_size": 128,
+  "damp_percent": 0.01,
+  "desc_act": false,
+  "static_groups": false,
+  "sym": true,
+  "true_sequential": true,
+  "model_name_or_path": null,
+  "model_file_base_name": null
+}