Upload LlamaForCausalLM

config.json

@@ -22,21 +22,6 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
-  "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
-    "bnb_4bit_compute_dtype": "float16",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "nf4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": true,
-    "load_in_8bit": false,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,
@@ -47,7 +32,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
+  "torch_dtype": "float16",
   "transformers_version": "4.44.2",
   "use_cache": true,
   "vocab_size": 128256

generation_config.json

@@ -6,7 +6,6 @@
     128008,
     128009
   ],
-  "pad_token_id": 128009,
   "temperature": 0.6,
   "top_p": 0.9,
   "transformers_version": "4.44.2"

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc913122b4a5230b43d796d5e26fadd669e1b9383d22916586b8401db735cfaa
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29485220c851efe964cc44eff4ea04d784bdfa7b112926be570b0f600ddf6e5
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8cb212179f57a1839fd177f6f4e2bd0ac2de8d2120cc7af56be2b790f89b560
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e298ab0c60a5b9da77082fccb4e73eac9fd484688d3c95bd99616b81ce1ac86f
+size 1168138808