commit 18f95e6d36cab83031c0c526fa5812f41e461551 Author: ModelHub XC Date: Wed Jun 24 22:55:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Josephgflowers/Tinyllama-616M-Cinder Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..21b3632 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..0fc7a3e --- /dev/null +++ b/README.md @@ -0,0 +1,7 @@ +--- +license: mit +--- +I cut my TinyLlama 1.1B cinder v 2 down from 22 layers to 14. At 14 there was no coherent text but there were emerging ideas of a response. +I then trained on the Reason with Cinder dataset and prunned the model again to 11 layers and only emerging responses. I then trained on a subset of open orca, sharegpt, cinder again, and tiny textbooks. +I am putting it up as a base model that may need work. If you continue training please let me know on the tinyllama discord, I have some interesting plans for this model. +I use the Zephyr chat format. \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..d75e08f --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "_name_or_path": "/content/615-tiny-cinder/", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 5632, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 11, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.40.0.dev0", + "unsloth_version": "2024.1", + "use_cache": false, + "vocab_size": 32000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1acae62 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.40.0.dev0", + "use_cache": false +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..5a838ad --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6029b73904e20827a1afb8a704ae790af51f835bdac87a8cf71497c5cb79236f +size 1231133920 diff --git a/optimizer.pt b/optimizer.pt new file mode 100644 index 0000000..b1c1c1e --- /dev/null +++ b/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc29206e9bca7e8c7571445463be6a3ddd15390ca95d0666a1adafacd93e5250 +size 2118202 diff --git a/rng_state.pth b/rng_state.pth new file mode 100644 index 0000000..93a5222 --- /dev/null +++ b/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69 +size 14244 diff --git a/scheduler.pt b/scheduler.pt new file mode 100644 index 0000000..25c9c7c --- /dev/null +++ b/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c2a9400622e72f855cc7c52c65864031718692e3ab53663b1147c11b054c7c4 +size 1064 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..492d4b2 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..21779d6 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd04f0eadf90287bd26e1a183ac487d8a141b09b06aecb7725bbdd343640f2e +size 1842767 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..28ca70c --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,46 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "", + "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "max_length": 2048, + "model_max_length": 2048, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "stride": 0, + "tokenizer_class": "LlamaTokenizer", + "truncation_side": "right", + "truncation_strategy": "longest_first", + "unk_token": "", + "use_default_system_prompt": false +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..11ac438 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,105 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 500, + "global_step": 244, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.08, + "grad_norm": 1.1114288568496704, + "learning_rate": 4.610655737704918e-05, + "loss": 1.1993, + "step": 20 + }, + { + "epoch": 0.16, + "grad_norm": 1.016808271408081, + "learning_rate": 4.200819672131148e-05, + "loss": 1.1065, + "step": 40 + }, + { + "epoch": 0.25, + "grad_norm": 0.9619632363319397, + "learning_rate": 3.790983606557377e-05, + "loss": 1.0583, + "step": 60 + }, + { + "epoch": 0.33, + "grad_norm": 1.0110981464385986, + "learning_rate": 3.381147540983607e-05, + "loss": 1.0567, + "step": 80 + }, + { + "epoch": 0.41, + "grad_norm": 0.9327293038368225, + "learning_rate": 2.9713114754098366e-05, + "loss": 1.0537, + "step": 100 + }, + { + "epoch": 0.49, + "grad_norm": 0.9638545513153076, + "learning_rate": 2.5614754098360656e-05, + "loss": 1.0132, + "step": 120 + }, + { + "epoch": 0.57, + "grad_norm": 0.9243238568305969, + "learning_rate": 2.1516393442622952e-05, + "loss": 1.0462, + "step": 140 + }, + { + "epoch": 0.66, + "grad_norm": 0.9260810613632202, + "learning_rate": 1.7418032786885245e-05, + "loss": 1.0283, + "step": 160 + }, + { + "epoch": 0.74, + "grad_norm": 0.8994088172912598, + "learning_rate": 1.3319672131147543e-05, + "loss": 0.986, + "step": 180 + }, + { + "epoch": 0.82, + "grad_norm": 0.9872317314147949, + "learning_rate": 9.221311475409836e-06, + "loss": 1.0229, + "step": 200 + }, + { + "epoch": 0.9, + "grad_norm": 0.8821935653686523, + "learning_rate": 5.122950819672131e-06, + "loss": 0.9887, + "step": 220 + }, + { + "epoch": 0.98, + "grad_norm": 0.9044594168663025, + "learning_rate": 1.024590163934426e-06, + "loss": 1.0017, + "step": 240 + } + ], + "logging_steps": 20, + "max_steps": 244, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 244, + "total_flos": 3.947086554857472e+16, + "train_batch_size": 24, + "trial_name": null, + "trial_params": null +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..15da3e3 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f4eb89a0b2995933354872389ebff5afb7309d50339e59bd0a2a7c9d7c3fe94 +size 4984