add new training files for possible new loading approach

.gitattributes

@@ -71,3 +71,5 @@ pytorch_model-00002-of-00039.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00008-of-00039.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00037-of-00039.bin filter=lfs diff=lfs merge=lfs -text
 pytorch_model-00038-of-00039.bin filter=lfs diff=lfs merge=lfs -text
+finetuned_conversations.pth filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

adapter_config.json

@@ -1,14 +1,17 @@
 {
-  "base_model_name_or_path": "chainyo/alpaca-lora-7b",
+  "base_model_name_or_path": "Sandiago21/llama-7b-hf-prompt-answering",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
   "lora_alpha": 16,
   "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 4,
+  "revision": null,
   "target_modules": [
     "q_proj",
     "v_proj"

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482ce154ea1f70f1ed8c7bc69e87712111be96b7c34491b556ca1ae43ff438ae
+oid sha256:82b9965da92e0780377740523e506b6fc9020d242bb11645eb17a637cebbe971
 size 8434381

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "decapoda-research/llama-7b-hf",
+  "_name_or_path": "Sandiago21/llama-7b-hf-prompt-answering",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -9,15 +9,27 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
   "max_sequence_length": 2048,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
   "pad_token_id": -1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_type": "fp4",
+    "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": false,
+    "load_in_8bit": true
+  },
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.28.0.dev0",
-  "use_cache": true,
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": false,
   "vocab_size": 32000
 }

finetuned_conversations.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd029581367e730fd9eb153c60befee837443891c48e853957c6d94217cd2be5
+size 7539803655

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96b020f5dcfaafd1def4df39ccadd2d1527760b8696265782b83ccf5db125416
+size 7539796821

special_tokens_map.json

@@ -1 +1,24 @@
-{}
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -1 +1,33 @@
-{"bos_token": "", "eos_token": "", "model_max_length": 1000000000000000019884624838656, "tokenizer_class": "LlamaTokenizer", "unk_token": ""}
+{
+  "add_bos_token": true,
+  "add_eos_token": true,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dca92296f96ae7d0ebe763192e441f69834de07a7c8daa4201fea156cbe6392b
-size 3643
+oid sha256:9d853438453178ebf4e0181c1f1b40d972e2fcedc3237c508b72acb67e2eba20
+size 3963