Model save

README.md

@@ -0,0 +1,57 @@
+---
+base_model: bigcode/starcoder2-7b
+library_name: transformers
+model_name: staradapters-python
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for staradapters-python
+
+This model is a fine-tuned version of [bigcode/starcoder2-7b](https://huggingface.co/bigcode/starcoder2-7b).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="ahmedashrafay/staradapters-python", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/aaa2419-columbia/huggingface/runs/6qi4etd4)
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.12.1
+- Transformers: 4.47.0.dev0
+- Pytorch: 2.4.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

final_checkpoint/config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "bigcode/starcoder2-7b",
+  "activation_function": "gelu",
+  "architectures": [
+    "Starcoder2ForCausalLM"
+  ],
+  "attention_dropout": 0.1,
+  "attention_softmax_in_fp32": true,
+  "bos_token_id": 0,
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 4608,
+  "initializer_range": 0.018042,
+  "intermediate_size": 18432,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 36,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 4,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "residual_dropout": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "sliding_window": 4096,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.0.dev0",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

final_checkpoint/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.0.dev0"
+}

final_checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d47be73f35a9cca78f0f9193acc5cdf6c4a163c6c435b7f282189336b7a343
+size 4395894528