Training in progress, epoch 1

README.md

@@ -0,0 +1,59 @@
+---
+base_model: analyticspro/slm-125m-base
+library_name: transformers
+model_name: slm-125m-sft-full
+tags:
+- generated_from_trainer
+- sft
+- trl
+- hf_jobs
+licence: license
+---
+
+# Model Card for slm-125m-sft-full
+
+This model is a fine-tuned version of [analyticspro/slm-125m-base](https://huggingface.co/analyticspro/slm-125m-base).
+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="analyticspro/slm-125m-sft-full", 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: 1.8.0
+- Transformers: 5.14.1
+- Pytorch: 2.13.0
+- Datasets: 5.0.0
+- 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}
+}
+```

chat_template.jinja

@@ -0,0 +1 @@
+{% if messages[0]['role'] == 'system' %}{{ '<|system|>' + messages[0]['content'] + eos_token }}{% set messages = messages[1:] %}{% endif %}{% for m in messages %}{% if m['role'] == 'user' %}{{ '<|user|>' + m['content'] + eos_token }}{% elif m['role'] == 'assistant' %}{{ '<|assistant|>' }}{% generation %}{{ m['content'] + eos_token }}{% endgeneration %}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% endif %}

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "float32",
+  "eos_token_id": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 16384
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "do_sample": true,
+  "eos_token_id": [
+    1
+  ],
+  "max_new_tokens": 120,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 2,
+  "temperature": 0.8,
+  "top_p": 0.95,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef29c6a4bf50770a81319426af7d13bc523108556a50b2c06ff0f54c132970f6
+size 503405488

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eos|>",
+  "extra_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6205887eee6348d8c303784e31601aafdeee7552f951794b04402c6bd2a03990
+size 5777