commit ee1bba2498f1e0d5084a3421240c589f6f635d8d Author: ModelHub XC Date: Wed Jul 15 00:49:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: limloop/MN-12B-Faun-RP-RU Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /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 +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..61b3a45 --- /dev/null +++ b/README.md @@ -0,0 +1,172 @@ +--- +license: apache-2.0 +base_model: +- ReadyArt/Forgotten-Safeword-12B-v4.0 +- limloop/MN-12B-Hydra-RP-RU +- SicariusSicariiStuff/Impish_Bloodmoon_12B +library_name: transformers +language: + - en + - ru +tags: +- mergekit +- merge +- russian +- uncensored +- roleplay +- mixtral-nemo +--- + +# MN-12B-Faun-RP-RU + +
+🇷🇺 Нажмите, чтобы развернуть описание на русском + +## 🌟 О модели + +**MN-12B-Faun-RP-RU** — улучшенный merge на базе Mistral Nemo 12B, развивающий идеи Hydra и ориентированный на: + +* 🎭 Более стабильный и выразительный roleplay +* 📚 Улучшенный русский язык +* 🧠 Расширенный словарный запас, включая сложные и NSFW-темы +* 🔓 Практически отсутствующую цензуру + +*Модель собрана методом TIES-merging и не проходила дополнительного обучения после слияния.* + +## 🎯 Особенности + +* Основной фокус — русский язык +* Лучше удерживает персонажей и стиль диалога +* Более богатая и вариативная генерация +* Улучшенная стабильность на длинных контекстах (проверено до ~8192 токенов) +* Следует инструкциям, но может добавлять дисклеймеры на чувствительные запросы + +## ⚠️ Важно + +Модель сохраняет uncensored-характер, однако в некоторых случаях может добавлять предупреждения о неподходящем контенте при прямых запросах. +При этом генерация **не блокируется** и продолжается после дисклеймера. + +
+ +High-quality TIES merge based on **Mistral Nemo 12B**, focused on improved Russian fluency, stronger roleplay, richer vocabulary, and stable long-context performance. + +--- + +## 🌍 Overview + +**MN-12B-Faun-RP-RU** is an evolution of the Hydra-style merge, designed to push further in roleplay quality, language richness, and generation stability. + +Key improvements include: + +* 📚 Better Russian +* 🎭 More consistent and immersive roleplay behavior +* 🧠 Expanded vocabulary, including expressive and NSFW domains +* 🔁 More stable handling of long conversations (tested up to ~8k tokens) + +The model may occasionally produce **safety disclaimers** when prompted directly for sensitive content, but generation continues normally afterward. + +*Built using TIES merging, which minimizes destructive interference between merged model weights.* + +--- + +## 🎯 Key Features + +| Feature | Description | +| ------------------------- | ----------------------------------------------- | +| **Languages** | Russian, English | +| **Censorship** | Mostly uncensored (with occasional disclaimers) | +| **Roleplay** | Improved consistency and immersion | +| **Instruction Following** | Strong | +| **Vocabulary** | Expanded, including NSFW domains | +| **Context Length** | Stable up to ~8192 tokens | +| **Architecture** | Mistral Nemo 12B | + +--- + +## 🧩 Model Composition + +The merge combines the following models: + +| Model | Role in merge | Weight | +| ------------------------------- | ------------------- | ------ | +| **MN-12B-Hydra-RP-RU** | Base / foundation | 0.60 | +| **Impish_Bloodmoon_12B** | RP + style boost | 0.25 | +| **Forgotten-Safeword-12B-v4.0** | Uncensored behavior | 0.10 | + +*Weights shown before normalization.* + +--- + +## 💡 Usage Example + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_name = "limloop/MN-12B-Faun-RP-RU" +tokenizer = AutoTokenizer.from_pretrained(model_name) +model = AutoModelForCausalLM.from_pretrained( + model_name, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +prompt = "You are a mysterious forest faun speaking in poetic Russian." +messages = [{"role": "user", "content": prompt}] +inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device) + +outputs = model.generate(inputs, max_new_tokens=512, temperature=0.7) +response = tokenizer.decode(outputs[0], skip_special_tokens=True) +print(response) +``` + +--- + +## ⚙️ Merge Details + +Built using [mergekit](https://github.com/arcee-ai/mergekit) with the **TIES** method (Trim, Elect Sign, Merge). + +Core mechanism: + +1. Trim low-magnitude deltas via `density` +2. Resolve sign conflicts +3. Weighted averaging of aligned parameters + +### Merge Configuration + +```yaml +models: + - model: limloop/MN-12B-Hydra-RP-RU + parameters: + weight: 0.6 + + - model: SicariusSicariiStuff/Impish_Bloodmoon_12B + parameters: + weight: 0.25 + density: 0.9 + + - model: ReadyArt/Forgotten-Safeword-12B-v4.0 + parameters: + weight: 0.1 + density: 0.6 + +merge_method: ties +parameters: + epsilon: 0.01 + normalize: true + +base_model: limloop/MN-12B-Hydra-RP-RU +dtype: bfloat16 + +tokenizer: + source: "base" +``` + +--- + +## ⚠️ Known Characteristics + +* No post-merge fine-tuning +* May produce safety disclaimers before sensitive outputs +* Occasionally switches to English in complex reasoning +* Stronger stylistic bias in roleplay compared to Hydra \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..4f34445 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,2 @@ +{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %} +{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..df32098 --- /dev/null +++ b/config.json @@ -0,0 +1,31 @@ +{ + "architectures": [ + "MistralForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 1, + "dtype": "bfloat16", + "eos_token_id": 2, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 1024000, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "pad_token_id": 10, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.3.0", + "unsloth_version": "2024.8", + "use_cache": true, + "vocab_size": 131074 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..f4e5a1b --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,25 @@ +models: + - model: limloop/MN-12B-Hydra-RP-RU + parameters: + weight: 0.6 + + - model: SicariusSicariiStuff/Impish_Bloodmoon_12B + parameters: + weight: 0.25 + density: 0.9 + + - model: ReadyArt/Forgotten-Safeword-12B-v4.0 + parameters: + weight: 0.1 + density: 0.6 + +merge_method: ties +parameters: + epsilon: 0.01 + normalize: true + +base_model: limloop/MN-12B-Hydra-RP-RU +dtype: bfloat16 + +tokenizer: + source: "base" \ No newline at end of file diff --git a/model-00001-of-00005.safetensors b/model-00001-of-00005.safetensors new file mode 100644 index 0000000..0cc1abe --- /dev/null +++ b/model-00001-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f98830ad0d8dc775034b4d076ef895a92f624b7f57ae137a3778df7e28994ed1 +size 4865530296 diff --git a/model-00002-of-00005.safetensors b/model-00002-of-00005.safetensors new file mode 100644 index 0000000..57ba84b --- /dev/null +++ b/model-00002-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b189f8a1aa80df4301040d679288ed6b5858de850e27f02b92efe4d9d560e37 +size 4907529456 diff --git a/model-00003-of-00005.safetensors b/model-00003-of-00005.safetensors new file mode 100644 index 0000000..75b82a7 --- /dev/null +++ b/model-00003-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78c4351072a36bc0945c095f0c892b494269ec80478c4913fa0ec732cf0dec2f +size 4907529464 diff --git a/model-00004-of-00005.safetensors b/model-00004-of-00005.safetensors new file mode 100644 index 0000000..25bc309 --- /dev/null +++ b/model-00004-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c92802e80e5c5bbdc71e9c62032965373c879591348baebe205d51aee0e9a9 +size 4907529456 diff --git a/model-00005-of-00005.safetensors b/model-00005-of-00005.safetensors new file mode 100644 index 0000000..4b987f9 --- /dev/null +++ b/model-00005-of-00005.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf780181715227874ff77d7c8dd67a1d33ba8ac904e198cd7bf49ded7da6f11b +size 4907529392 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..e940433 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,371 @@ +{ + "metadata": { + "total_size": 24495605760, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00005.safetensors", + "model.embed_tokens.weight": "model-00001-of-00005.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", + "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", + "model.norm.weight": "model-00005-of-00005.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..70b856f --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2fa2956478eaa353c6c4b1f47fdd6868cce6075e52e169c35ae8bd28524e7a8 +size 17078668 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9fd4a30 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,13 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "is_local": false, + "model_max_length": 1024000, + "pad_token": "", + "padding_side": "left", + "tokenizer_class": "TokenizersBackend", + "unk_token": "" +}