commit b8a944fc76288ee56e61a8e800d612e22e31b9ea Author: ModelHub XC Date: Sun May 24 12:43:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Applied-Innovation-Center/Karnak-6B-v1.0 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..e26612e --- /dev/null +++ b/README.md @@ -0,0 +1,171 @@ +--- +license: apache-2.0 +language: + - ar + - en +pipeline_tag: text-generation +tags: + - text-generation + - pytorch + - transformers + - vllm + - causal-lm + - depth-extension + - arabic + - english + - Karnak-6B-v1.0 + - qwen +base_model: Qwen/Qwen3-4B-Instruct-2507 +model_name: Karnak-6B-v1.0 +parameters: 6B +inference: false +--- + +# Karnak-6B-v1.0 : Enhanced Arabic–English Large Language Model +Karnak-6B-v1.0 is a powerful AI model that works in both Arabic and English, with extra improvements that make it especially strong in Arabic and more natural in the way it writes and responds. It was built by taking an existing model and improving it through more training, so it can understand instructions better, handle longer text, and give more reliable answers. This makes it useful for everyday tasks like answering questions, explaining topics, writing content, or helping with work and research. It can also process long pieces of text, which is helpful for documents and extended conversations. A big advantage is that it is not locked to an online service only, since you can download it, run it locally on your own machine or servers, and even fine-tune it for your own specific use case. + +## Model Summary + +**Karnak-6B-v1.0 ** is a depth-extended causal language model optimized for **Arabic and English** generation. It is built on top of **Qwen/Qwen3-4B-Instruct-2507**, featuring architectural depth extension and a tokenizer specifically optimized for Arabic to improve fluency and efficiency. + +Karnak-6B-v1.0 was trained using **high-quality, filtered data** through a rigorous pipeline to enhance overall instruction-following capabilities, factuality, and robustness. + +## Key Features + +- **Depth Extension (~6B):** Expanded depth to increase reasoning capacity and improve long-range dependency modeling. +- **Arabic-Optimized Tokenizer:** Improved Arabic tokenization efficiency, resulting in reduced token fragmentation and higher-quality generation. +- **Multi-Stage Training:** The model evolved through: Pre-trained weights → Depth Extension → Continued Pre-training → SFT (Supervised Fine-Tuning). +- **Extended Context Window:** Designed for long-context usage with a **safe context range up to 20K tokens** (recommended to stay within this limit for optimal stability). + +## Model Details + +- **Model Name:** Karnak-6B-v1.0 +- **Base Model:** Qwen/Qwen3-4B-Instruct-2507 +- **Parameter Count:** ~6B (Depth-Extended) +- **Languages:** Arabic, English +- **Training:** High-quality filtered data + Multi-stage pipeline (Continued pre-training + SFT) +- **Safe Context Range:** Up to **20,000 tokens** + +--- + +## Usage + +### 1) Hugging Face Transformers + +To use Karnak-6B-v1.0 with the standard Transformers library, ensure you have the latest version installed. + +```bash +pip install -U "transformers>=4.40.0" torch accelerate +``` + +Python Code Example (Chat Template): + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +model_id = "Applied-Innovation-Center/Karnak-6B-v1.0 " + +# Load tokenizer and model +tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True) +model = AutoModelForCausalLM.from_pretrained( + model_id, + device_map="auto", + torch_dtype=torch.bfloat16, + trust_remote_code=True, +) + +# Prepare Input +prompt = "اشرح لي نظرية النسبية بشكل مبسط." +messages = [ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": prompt}, +] + +# Apply chat template +text = tokenizer.apply_chat_template( + messages, + tokenize=False, + add_generation_prompt=True, +) +model_inputs = tokenizer([text], return_tensors="pt").to(model.device) + +# Generate +generated_ids = model.generate( + **model_inputs, + max_new_tokens=512, + temperature=0.7, + top_p=0.9, +) + +# Decode output (removing the prompt tokens) +generated_ids = generated_ids[:, model_inputs.input_ids.shape[1]:] +response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] +print(response) +``` + +2) vLLM (Recommended for Production) +Karnak-6B-v1.0 is compatible with vLLM for high-throughput inference. + +Installation: + +```bash + +pip install -U vllm +``` + +Offline Inference: + +```python + +from vllm import LLM, SamplingParams + +model_id = "Applied-Innovation-Center/Karnak-6B-v1.0 " + +# Initialize the model +llm = LLM( + model=model_id, + trust_remote_code=True, + max_model_len=20000, # Safe context range + tensor_parallel_size=1, # Adjust based on available GPUs +) + +# Set sampling parameters +sampling_params = SamplingParams( + temperature=0.7, + top_p=0.9, + max_tokens=512, +) + +# Generate +prompts = ["ما هي عاصمة مصر؟"] +outputs = llm.generate(prompts, sampling_params) + +for o in outputs: + print(f"Prompt: {o.prompt}") + print(f"Generated: {o.outputs[0].text}") +``` + +Server Mode (OpenAI-Compatible API): + +You can serve the model as an API compatible with OpenAI clients: + +```bash + +vllm serve "Applied-Innovation-Center/Karnak-6B-v1.0 " \ + --trust-remote-code \ + --dtype bfloat16 \ + --port 8000 +``` + +Citation +If you use this model in your research or application, please cite it as follows: + +```bibtex +@misc{Karnak-6B-v1.0 -6B, + title={Karnak-6B-v1.0 : A Depth-Extended Arabic-English LLM}, + year={2026}, + publisher={Applied Innovation Center}, + howpublished={\url{[https://huggingface.co/Applied-Innovation-Center/Karnak-6B-v1.0 ](https://huggingface.co/Applied-Innovation-Center/Karnak-6B-v1.0 )}} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..be8732e --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are Karnak, created by AIC. You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..56ddd5a --- /dev/null +++ b/config.json @@ -0,0 +1,89 @@ +{ + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": null, + "dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 262144, + "max_window_layers": 36, + "model_type": "qwen3", + "num_attention_heads": 32, + "num_hidden_layers": 54, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 5000000, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.6.2", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 192728 +} diff --git a/model-00001-of-00003.safetensors b/model-00001-of-00003.safetensors new file mode 100644 index 0000000..1b7f618 --- /dev/null +++ b/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2df09f07731c4db539f5d7b72272002a98469d16da4795e51457327af5bc87d1 +size 4974212720 diff --git a/model-00002-of-00003.safetensors b/model-00002-of-00003.safetensors new file mode 100644 index 0000000..308e20c --- /dev/null +++ b/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7288cc50a5d590fc0c9e02b42fe86d158afa6cab35fa63babfd5df81e63548 +size 4996765024 diff --git a/model-00003-of-00003.safetensors b/model-00003-of-00003.safetensors new file mode 100644 index 0000000..24b7401 --- /dev/null +++ b/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f010f1ed05b2902bbe9198e5b30a7570f2f4111ffa4c780dc2390abad678d84c +size 1916391432 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..ae8c8eb --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,603 @@ +{ + "metadata": { + "total_size": 11887300608 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.q_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.44.self_attn.k_norm.weight": "model-00002-of-00003.safetensors", + "model.layers.44.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.48.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.48.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.49.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.49.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.50.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.50.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.51.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.51.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.52.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.52.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.q_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.53.self_attn.k_norm.weight": "model-00003-of-00003.safetensors", + "model.layers.53.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..57cbdae --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f644d71501367aaa569353e4787cd25cadb851169b709d8712bff51c72ce76f8 +size 15658511 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..9158804 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}