Upload LlamaForCausalLM

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "bos_token_id": 128000,
-  "eos_token_id": 128009,
+  "eos_token_id": 128001,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -18,12 +18,27 @@
   "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": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "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": null,
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "torch_dtype": "float16",
+  "transformers_version": "4.43.2",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -1,12 +1,9 @@
 {
   "bos_token_id": 128000,
   "do_sample": true,
-  "eos_token_id": [
-    128001,
-    128009
-  ],
+  "eos_token_id": 128001,
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.43.2"
 }

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ec887469c2dcebce46295020a38f4e19570dc5a41348a26f6ed452c0c6156e0
+size 4652072864

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
+size 1050673280