Upload LlamaForCausalLM

config.json

@@ -19,22 +19,30 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
+    "batch_size": 1,
     "bits": 3,
+    "block_name_to_quantize": "model.layers",
     "damp_percent": 0.1,
     "dataset": "wikitext2",
     "desc_act": false,
+    "disable_exllama": false,
     "group_size": 128,
-    "modules_in_block_to_quantize": null,
+    "model_seqlen": 4096,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens"
+    ],
+    "pad_token_id": null,
     "quant_method": "gptq",
     "sym": true,
-    "true_sequential": true
+    "true_sequential": true,
+    "use_cuda_fp16": true
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -5,5 +5,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.41.2"
+  "transformers_version": "4.44.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e2dfce86968d979a72735c2cc53755ac0ec9b851e0b6ef7ab45f485dcae160
-size 4853712424
+oid sha256:4b4c380053ea82e13e60e0ea39d1d798715e7458d3a110e5826678a8fd724f6a
+size 4856489224