Upload LlamaForCausalLM

config.json

@@ -1,8 +1,10 @@
 {
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "architectures": [
     "LlamaForCausalLM"
   ],
   "attention_bias": false,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
   "hidden_act": "silu",
@@ -15,12 +17,24 @@
   "num_hidden_layers": 22,
   "num_key_value_heads": 4,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "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": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.35.0",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.0.dev0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,7 +1,11 @@
 {
   "bos_token_id": 1,
+  "do_sample": true,
   "eos_token_id": 2,
   "max_length": 2048,
-  "pad_token_id": 0,
-  "transformers_version": "4.35.0"
+  "max_new_token": 250,
+  "pad_token_id": 2,
+  "temperature": 0.1,
+  "top_p": 0.7,
+  "transformers_version": "4.37.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47ca7268b793c62699e38ebd9255bda3e7cbfa3294c9458188fa2b83c6050807
-size 1024784726
+oid sha256:ede1f42872539e33f2b151f6292cb2ed60dc2b757b989fbf0c5c3d020b750f49
+size 762453328