commit c105c453473b014268ab1c155ba60707f8d6e9ae Author: ModelHub XC Date: Fri Aug 14 02:05:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: acrastt/OmegLLaMA-3B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.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 diff --git a/README.md b/README.md new file mode 100644 index 0000000..31cc17e --- /dev/null +++ b/README.md @@ -0,0 +1,158 @@ +--- +language: +- en +license: apache-2.0 +library_name: transformers +tags: +- not-for-all-audiences +datasets: +- anon8231489123/Omegle_logs_dataset +pipeline_tag: text-generation +model-index: +- name: OmegLLaMA-3B + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: AI2 Reasoning Challenge (25-Shot) + type: ai2_arc + config: ARC-Challenge + split: test + args: + num_few_shot: 25 + metrics: + - type: acc_norm + value: 40.36 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: HellaSwag (10-Shot) + type: hellaswag + split: validation + args: + num_few_shot: 10 + metrics: + - type: acc_norm + value: 66.13 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU (5-Shot) + type: cais/mmlu + config: all + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 28.0 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: TruthfulQA (0-shot) + type: truthful_qa + config: multiple_choice + split: validation + args: + num_few_shot: 0 + metrics: + - type: mc2 + value: 33.31 + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: Winogrande (5-shot) + type: winogrande + config: winogrande_xl + split: validation + args: + num_few_shot: 5 + metrics: + - type: acc + value: 61.64 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GSM8k (5-shot) + type: gsm8k + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 0.23 + name: accuracy + source: + url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=acrastt/OmegLLaMA-3B + name: Open LLM Leaderboard +--- + +Buy Me A Coffee + +This is [Xander Boyce](https://huggingface.co/takeraparterer)'s [OmegLLaMA LoRA](https://huggingface.co/takeraparterer/Omegllama) merged with [OpenLLama 3B](https://huggingface.co/openlm-research/open_llama_3b). + +Prompt format: +``` +Interests: {interests} +Conversation: +You: {prompt} +Stranger: +``` +For multiple interests, seperate them with space. Repeat You and Stranger for multi-turn conversations, which means Interests and Conversation are technically part of the system prompt. + +GGUF quantizations available [here](https://huggingface.co/maddes8cht/acrastt-OmegLLaMA-3B-gguf). + +This model is very good at NSFW ERP and sexting(For a 3B model). I recommend using this with [Faraday.dev](https://faraday.dev/) if you want ERP or sexting. + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_acrastt__OmegLLaMA-3B) + +| Metric | Value | +|-----------------------|---------------------------| +| Avg. | 38.28 | +| ARC (25-shot) | 40.36 | +| HellaSwag (10-shot) | 66.13 | +| MMLU (5-shot) | 28.0 | +| TruthfulQA (0-shot) | 33.31 | +| Winogrande (5-shot) | 61.64 | +| GSM8K (5-shot) | 0.23 | + +# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) +Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_acrastt__OmegLLaMA-3B) + +| Metric |Value| +|---------------------------------|----:| +|Avg. |38.28| +|AI2 Reasoning Challenge (25-Shot)|40.36| +|HellaSwag (10-Shot) |66.13| +|MMLU (5-Shot) |28.00| +|TruthfulQA (0-shot) |33.31| +|Winogrande (5-shot) |61.64| +|GSM8k (5-shot) | 0.23| + diff --git a/config.json b/config.json new file mode 100644 index 0000000..573ed2e --- /dev/null +++ b/config.json @@ -0,0 +1,22 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 3200, + "initializer_range": 0.02, + "intermediate_size": 8640, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 26, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.30.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..737a363 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.30.0.dev0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..5d3d004 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1db450c6e083446358233d3e841161e65aa5d981db152d716775118255fa637c +size 6852982288 diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..e539ab1 --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113d2c959824fa205ff5fdbc1bea8855a7527d47662a5c3df01ebd99fe635884 +size 6853038093 diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..1c141cf --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1 @@ +{"bos_token": {"content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}} \ No newline at end of file diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8d6be7d --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b +size 534194 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..75ff0f5 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1 @@ +{"add_bos_token": true, "add_eos_token": false, "model_max_length": 2048, "pad_token": null, "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "clean_up_tokenization_spaces": false, "bos_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"__type": "AddedToken", "content": "", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}} \ No newline at end of file