Training in progress, step 100

README.md

@@ -0,0 +1,59 @@
+---
+base_model: Colby/starcoder-7b-agent-0.3-merged
+library_name: transformers
+model_name: starcoder-7b-agent-0.5
+tags:
+- generated_from_trainer
+- hf_jobs
+- trl
+- sft
+licence: license
+---
+
+# Model Card for starcoder-7b-agent-0.5
+
+This model is a fine-tuned version of [Colby/starcoder-7b-agent-0.3-merged](https://huggingface.co/Colby/starcoder-7b-agent-0.3-merged).
+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="Colby/starcoder-7b-agent-0.5", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 1.4.0
+- Transformers: 5.8.1
+- Pytorch: 2.12.0
+- Datasets: 4.8.5
+- Tokenizers: 0.22.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

adapter_config.json

@@ -0,0 +1,44 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Colby/starcoder-7b-agent-0.3-merged",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_proj",
+    "c_attn",
+    "c_fc"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:985a7ebc1f1e53cbae04a56bb980dc795a64fbfed9d915d4af57176735865efe
+size 882928784

chat_template.jinja

@@ -0,0 +1,9 @@
+{% for message in messages %}{% if message['role'] == 'system' %}<|system|>
+{{ message['content'] }}
+<|end|>
+{% elif message['role'] == 'user' %}<|user|>
+{{ message['content'] }}<|end|>
+{% elif message['role'] == 'assistant' %}<|assistant|>
+{{ message['content'] }}<|end|>
+{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>
+{% endif %}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80510a7def4d286bcd5281516c42b0b819947ee8fc164bd95d479515c6446d9f
+size 6289