Upload folder using huggingface_hub

README.md

@@ -1,3 +1,34 @@
 ---
 license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- code
+- code-generation
+- parrot-coder
+- inserloft
 ---
+
+# Parrot Coder 🦜 (Safetensors)
+
+**Parrot Coder** is a highly efficient, 200M parameter language model optimized for rapid code autocompletion and code generation tasks. Developed by Inserloft Research.
+
+This repository contains the **merged base model + LoRA adapters** in `.safetensors` format, ready for direct inference using `transformers`.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "InserloftResearch/Parrot-Coder"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+prompt = "def fibonacci(n):"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_new_tokens=50)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+For GGUF versions, visit our [Ollama Registry](https://ollama.com/Inserloft/ParrotCode).

config.json

@@ -0,0 +1,44 @@
+{
+  "activation_function": "gelu_new",
+  "add_cross_attention": false,
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "created_by": "Inserloft Research",
+  "description": "Modelo de 200M de par\u00e1metros enfocado en autocompletado r\u00e1pido de c\u00f3digo.",
+  "dtype": "float16",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_name": "Parrot Coder",
+  "model_type": "gpt2",
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 16,
+  "n_positions": 2048,
+  "pad_token_id": null,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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,
+  "tags": [
+    "code-generation",
+    "autocompletion",
+    "inserloft"
+  ],
+  "tie_word_embeddings": true,
+  "transformers_version": "5.16.1",
+  "use_cache": false,
+  "vocab_size": 50257,
+  "web": "Research.Inserloft.com",
+  "n_ctx": 2048
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.16.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62310d6cfbb0ed3a6ef2545f117365800ebc89bb5b0e7adb438f40ea8a5054c
+size 510223992

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": 512,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}