Upload LlamaForCausalLM

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "_name_or_path": "chat_summarizer/quantized_8bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -16,12 +16,35 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 32,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "batch_size": 1,
+    "bits": 8,
+    "block_name_to_quantize": "model.layers",
+    "damp_percent": 0.1,
+    "dataset": [
+      "c4"
+    ],
+    "desc_act": false,
+    "disable_exllama": false,
+    "group_size": 128,
+    "max_input_length": null,
+    "model_seqlen": 4096,
+    "module_name_preceding_first_block": [
+      "model.embed_tokens"
+    ],
+    "pad_token_id": null,
+    "quant_method": "gptq",
+    "sym": true,
+    "tokenizer": null,
+    "true_sequential": true,
+    "use_cuda_fp16": true
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.34.0",
+  "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -6,5 +6,5 @@
   "pad_token_id": 0,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.34.0"
+  "transformers_version": "4.34.1"
 }

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7887db21bb240dfdfcf233a2f61135a94f97754f793cfffdee3465a0658caf
+size 7160285785