Training in progress, epoch 0

adapter_config.json

@@ -1,6 +1,6 @@
 {
   "auto_mapping": null,
-  "base_model_name_or_path": "TheBloke/Llama-2-7B-fp16",
+  "base_model_name_or_path": "TheBloke/CodeLlama-7B-fp16",
   "bias": "none",
   "fan_in_fan_out": null,
   "inference_mode": true,
@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj",
     "up_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj",
-    "q_proj",
-    "gate_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0156269e0eeb08603ebafcce6ae424f5a2ea44fe8b89024ec2c22f39c273d751
+size 319876032

config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "TheBloke/CodeLlama-7B-fp16",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "TheBloke/CodeLlama-7B-fp16--configuration_llama.LlamaConfig",
+    "AutoModel": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaModel",
+    "AutoModelForCausalLM": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForCausalLM",
+    "AutoModelForSequenceClassification": "TheBloke/CodeLlama-7B-fp16--modeling_llama.LlamaForSequenceClassification"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 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,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32016
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba6d6291d49bb6faec06e1974982c42a80d019f9d6bdf3d6b442a0d7ed1844a
-size 4027
+oid sha256:f5befa28b6859aa81c683f1b29594b745724349581e910e2f91077215382b67f
+size 4475