Hosein/MobileLLM-125M-None.4.3

README.md

@@ -0,0 +1,58 @@
+---
+base_model: facebook/MobileLLM-125M
+library_name: transformers
+model_name: MobileLLM-125M-None.4.3
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for MobileLLM-125M-None.4.3
+
+This model is a fine-tuned version of [facebook/MobileLLM-125M](https://huggingface.co/facebook/MobileLLM-125M).
+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="RoyArkh/MobileLLM-125M-None.4.3", 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: 0.13.0
+- Transformers: 4.48.0
+- Pytorch: 2.2.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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}}
+}
+```

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "facebook/MobileLLM-125M",
+  "architectures": [
+    "MobileLLMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "facebook/MobileLLM-125M--configuration_mobilellm.MobileLLMConfig",
+    "AutoModelForCausalLM": "facebook/MobileLLM-125M--modeling_mobilellm.MobileLLMForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_sharing": false,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "mobilellm",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "share_embedding": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.48.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4423c0b6e0f8868c6fca9afff60c68a79d42b8a6ff8d90e314bb6736dfe2ae3
+size 498572168

runs/Jan16_19-32-00_ip-10-192-12-244/events.out.tfevents.1737055936.ip-10-192-12-244.44347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:737503338d66745b1f664ebee02bb4e0003038df0050e16cdbbd315d919e5f85
+size 15492

runs/Jan16_19-33-50_ip-10-192-12-244/events.out.tfevents.1737056030.ip-10-192-12-244.47006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c527258c7cc4664b7db14932e97d93caf26368793ce62e0fc737ea39a282d75
+size 9696

runs/Jan16_19-34-38_ip-10-192-12-244/events.out.tfevents.1737056094.ip-10-192-12-244.48174.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:128a898e4aef32bec6b3225418f21510239368f41a2ee5d820841874ac263b37
+size 138352

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {},
+  "bos_token": "",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506a64ffbe680c2ddd657ab4f44567620762748dcc839973a795ad7d60d35438
+size 5624