Training in progress, epoch 0

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: NousResearch/Llama-2-13b-chat-hf
+base_model: NousResearch/Llama-2-13b-hf
 ---
 
 # Model Card for Model ID
@@ -216,4 +216,23 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
+- PEFT 0.6.0
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- load_in_8bit: True
+- load_in_4bit: False
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: fp4
+- bnb_4bit_use_double_quant: False
+- bnb_4bit_compute_dtype: float32
+
+### Framework versions
+
+
 - PEFT 0.6.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "base_model_name_or_path": "NousResearch/Llama-2-13b-chat-hf",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
     "up_proj",
+    "k_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
+    "gate_proj",
+    "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68233e958260d3384a1f3af1a0428e9de96c0187fc6ef41a771ba0809f865781
+oid sha256:8f901d4b195002956b05d8bc4379698fbad417cbe96dba82402b90c6d99d8a57
 size 500897101

added_tokens.json

@@ -1,5 +1,6 @@
 {
   "</s>": 2,
+  "<pad>": 32000,
   "<s>": 1,
   "<unk>": 0
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "NousResearch/Llama-2-13b-hf",
+  "_name_or_path": "NousResearch/Llama-2-13b-chat-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -36,5 +36,5 @@
   "torch_dtype": "float16",
   "transformers_version": "4.35.0.dev0",
   "use_cache": false,
-  "vocab_size": 32000
+  "vocab_size": 32001
 }

tokenizer_config.json

@@ -25,6 +25,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
     }
   },
   "additional_special_tokens": [],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18461b3ceb672af29bdf70f2b48ef86d90cd60e8af45447000342dce27f9a81c
+oid sha256:44e1a7219538094be7c3aa3b9acee4e4ca955a354517e10f6445d9860f4e9041
 size 4475