Upload LlamaForCausalLM

config.json

@@ -17,18 +17,35 @@
   "num_key_value_heads": 40,
   "pretraining_tp": 1,
   "quantization_config": {
-    "backend": "llm-awq",
+    "batch_size": 1,
     "bits": 4,
+    "block_name_to_quantize": "model.layers",
+    "cache_block_outputs": true,
+    "damp_percent": 0.1,
+    "dataset": "c4",
+    "desc_act": false,
+    "exllama_config": {
+      "version": 1
+    },
     "group_size": 128,
-    "quant_method": "awq",
-    "version": "gemv",
-    "zero_point": true
+    "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,
+    "use_exllama": true
   },
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
+  "torch_dtype": "float16",
   "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32000

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0894450909d566b74ebfbdcf5d79525c6ee62745d95776c7fe602a5dc41fdb92
+size 4991476560

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dc34d6438d566a094eaefd8e4c0cbf3421803def6400d572dbfa30c1429c72
+size 2267958280