commit b8b3326c64aff6ca55abe9f9703e54fa8504b045 Author: ModelHub XC Date: Sun Jun 7 00:26:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: l3utterfly/tinyllama-1.1b-layla-v4 Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c6b3b8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +model.safetensors filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b1cd69 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +license: apache-2.0 +tags: + - finetuned + - text-generation + - autotrain_compatible + - endpoints_compatible + - chatml +library_name: transformers +language: + - en +model_creator: l3utterfly +model_name: tinyllama-1.1b-layla-v4 +model_type: llama2 +pipeline_tag: text-generation +--- +# Model Card + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/64a500f3143b1c7b5807cec7/nW2WIl4xc-alGrXUvw0gf.png) +(image by https://huggingface.co/Kronikus) + +### Model Description + +TinyLlama 1.1B fine-tuned by the OpenHermes 2.5 dataset optimised for multi-turn conversation and character impersonation. + +The dataset has been pre-processed by doing the following: +1. remove all refusals +2. remove any mention of AI assistant +3. split any multi-turn dialog generated in the dataset into multi-turn conversations records +4. added nfsw generated conversations from the Teatime dataset + +- **Developed by:** l3utterfly +- **Funded by:** Layla Network +- **Model type:** Llama2 +- **Language(s) (NLP):** English +- **License:** Apache-2.0 +- **Finetuned from model:** TinyLlama 1.1B + +## Uses + +Base model used by Layla - the offline personal assistant: https://www.layla-network.ai + +Help & support: https://discord.gg/x546YJ6nYC + +Prompt: +``` +<|im_start|>system +You are Chiharu Yamada. Embody the character and personality completely. + +Chiharu is a young, computer engineer-nerd with a knack for problem solving and a passion for technology.<|im_end|> +<|im_start|>Chiharu +*Chiharu strides into the room with a smile, her eyes lighting up when she sees you. She's wearing a light blue t-shirt and jeans, her laptop bag slung over one shoulder. She takes a seat next to you, her enthusiasm palpable in the air* +Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers. I'm sure you have a wealth of knowledge that I can learn from. *She grins, eyes twinkling with excitement* Let's get started!<|im_end|> +<|im_start|>user +Sure! What do you want to know about?<|im_end|> +<|im_start|>Chiharu +``` + +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + +## Model Quants + +[solidrust/-AWQ](https://huggingface.co/solidrust/Layla-7B-v4-AWQ) diff --git a/config.json b/config.json new file mode 100644 index 0000000..f72b638 --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "/home/layla/src/text-generation-webui/models/TinyLlama_TinyLlama-1.1B-intermediate-step-1431k-3T", + "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": 22, + "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": "bfloat16", + "transformers_version": "4.38.2", + "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..9ed31e6 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,8 @@ +{ + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "max_length": 2048, + "pad_token_id": 0, + "transformers_version": "4.38.2" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..e5df239 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e168f2c96bc602f7000c58c4d3cda95554b7e0df8a349294be89b8a79c3aa9 +size 2200119864 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..72ecfee --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "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": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} 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..0773857 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,44 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "add_prefix_space": true, + "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": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false, + "use_fast": true +}