Upload 11 files

updated config.json

README.md

@@ -1,13 +1,6 @@
 ---
 base_model: Salesforce/codegen-350M-mono
-license: apache-2.0
-datasets:
-- google/code_x_glue_ct_code_to_text
-language:
-- en
-metrics:
-- bleu
-pipeline_tag: text-generation
+library_name: peft
 ---
 
 # Model Card for Model ID

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a19989674fc643868e89448b447163039bc38e26b78003d85f9b4ced825ac59
+oid sha256:e4c1e53a4aaea92587393b4434b8fbf3bbadf83fe87aee9266ed09717e418a8e
 size 7874776

config.json

@@ -0,0 +1,55 @@
+{
+  "_name_or_path": "Salesforce/codegen-350M-mono",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "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"
+  },
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "use_flash_attention_2": true,
+  "vocab_size": 51200
+}

tokenizer.json

@@ -6,7 +6,16 @@
     "strategy": "LongestFirst",
     "stride": 0
   },
-  "padding": null,
+  "padding": {
+    "strategy": {
+      "Fixed": 256
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 50256,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 50256,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf2f48a7002c3728e963de579d63f6c00b08ec511d33d8bb2f9e1e5a051c6950
+oid sha256:f5f5f6d037e5f5351ac9a76ac48d009cfe5032e52df87658afeeaa04a79e6405
 size 4792