From 6f70aeacaafd6de79591b02918d7923a7bdbe2ff Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sun, 23 Aug 2026 07:23:16 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: intellectlabs/Kepler-8B-Instruct-v2 Source: Original Platform --- .gitattributes | 36 ++++ README.md | 117 +++++++++++ chat_template.jinja | 54 +++++ config.json | 61 ++++++ mergekit_config.yml | 14 ++ model-00001-of-00009.safetensors | 3 + model-00002-of-00009.safetensors | 3 + model-00003-of-00009.safetensors | 3 + model-00004-of-00009.safetensors | 3 + model-00005-of-00009.safetensors | 3 + model-00006-of-00009.safetensors | 3 + model-00007-of-00009.safetensors | 3 + model-00008-of-00009.safetensors | 3 + model-00009-of-00009.safetensors | 3 + model.safetensors.index.json | 347 +++++++++++++++++++++++++++++++ tokenizer.json | 3 + tokenizer_config.json | 30 +++ 17 files changed, 689 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 mergekit_config.yml create mode 100644 model-00001-of-00009.safetensors create mode 100644 model-00002-of-00009.safetensors create mode 100644 model-00003-of-00009.safetensors create mode 100644 model-00004-of-00009.safetensors create mode 100644 model-00005-of-00009.safetensors create mode 100644 model-00006-of-00009.safetensors create mode 100644 model-00007-of-00009.safetensors create mode 100644 model-00008-of-00009.safetensors create mode 100644 model-00009-of-00009.safetensors create mode 100644 model.safetensors.index.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json 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..c5265f0 --- /dev/null +++ b/README.md @@ -0,0 +1,117 @@ +--- +license: apache-2.0 +base_model: intellectlabs/Kepler-8B-Instruct-v2 +tags: +- gguf +- llama.cpp +- quantized +- merge +- mergekit +- qwen2 +- text-generation +- conversational +language: +- en +pipeline_tag: text-generation +--- + +
+ +# 🪐 Kepler-8B-Instruct — GGUF + +### Quantized GGUF builds of Kepler-8B-Instruct — ready to run anywhere llama.cpp does. + +**License: Apache 2.0** · **Format: GGUF** · **Base: [Kepler-8B-Instruct](https://huggingface.co/intellectlabs/Kepler-8B-Instruct)** + +**[Original Model](https://huggingface.co/intellectlabs/Kepler-8B-Instruct)** · **[llama.cpp](https://github.com/ggerganov/llama.cpp)** · **[Discussions](../../discussions)** + +
+ +--- + +## ✨ What is this? + +**Kepler-8B-Instruct** is an 8-billion-parameter assistant built by merging `Qwen/Qwen2.5-7B-Instruct` (85%) with `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B` (15%) using [mergekit](https://github.com/arcee-ai/mergekit). The blend keeps Qwen2.5-Instruct's clean, reliable instruction-following as the foundation while folding in a touch of DeepSeek's reasoning-distilled behavior. + +This repository packages that model as **GGUF** — the universal format for [llama.cpp](https://github.com/ggerganov/llama.cpp) and everything built on it. One file, no Python environment, no CUDA setup. It runs on a gaming laptop, a Raspberry Pi-class board, or a headless server with equal ease. + +**Highlights:** +- 🧩 A reliable instruction-following foundation with a light touch of reasoning-model flavor +- ⚡ Seven precision levels included, from a ~3 GB ultra-light build to full-precision F16 +- 🔌 Drop-in compatible with llama.cpp, LM Studio, Ollama, koboldcpp, GPT4All, Jan, and text-generation-webui +- 🗂️ Native ChatML support, with a built-in default identity — ask "who are you" and it answers as Kepler by intellectlabs, in whatever language you ask in + +## 🚀 Quick Start + +### llama.cpp +```bash +./llama-cli -hf intellectlabs/Kepler-8B-Instruct-GGUF:Q4_K_M -p "Explain quantum entanglement simply." +``` + +Or download a specific file manually: +```bash +huggingface-cli download intellectlabs/Kepler-8B-Instruct-GGUF Kepler-8B-Instruct-Q4_K_M.gguf --local-dir . +./llama-cli -m Kepler-8B-Instruct-Q4_K_M.gguf -p "Hello, who are you?" -cnv +``` + +### LM Studio +Search **`intellectlabs/Kepler-8B-Instruct-GGUF`** directly in the LM Studio model search bar and download your preferred quant. + +### Ollama +```bash +ollama run hf.co/intellectlabs/Kepler-8B-Instruct-GGUF:Q4_K_M +``` + +## 📦 Available Quantizations + +| File | Quant | Size (approx.) | Quality | Recommended For | +|---|---|---|---|---| +| `Kepler-8B-Instruct-Q2_K.gguf` | Q2_K | ~3.1 GB | ⭐️ | Extreme low-RAM devices only | +| `Kepler-8B-Instruct-Q3_K_M.gguf` | Q3_K_M | ~4.0 GB | ⭐️⭐️ | Low-RAM systems, testing | +| `Kepler-8B-Instruct-Q4_0.gguf` | Q4_0 | ~4.7 GB | ⭐️⭐️⭐️ | Legacy-hardware compatibility | +| `Kepler-8B-Instruct-Q4_K_M.gguf` | Q4_K_M | ~4.9 GB | ⭐️⭐️⭐️⭐️ | **Best balance — recommended default** | +| `Kepler-8B-Instruct-Q5_K_M.gguf` | Q5_K_M | ~5.7 GB | ⭐️⭐️⭐️⭐️ | Higher quality, still efficient | +| `Kepler-8B-Instruct-Q8_0.gguf` | Q8_0 | ~8.5 GB | ⭐️⭐️⭐️⭐️⭐️ | Near-lossless, if you have the RAM | +| `Kepler-8B-Instruct-F16.gguf` | F16 | ~16 GB | ⭐️⭐️⭐️⭐️⭐️ | Full precision, GPU/server use | + +> 💡 **New here?** Start with **Q4_K_M** — it's the sweet spot most people use: small enough to run comfortably, strong enough to feel close to the full model. + +## 🧠 Prompt Format + +This model uses the **ChatML** template (inherited from its Qwen2 base): + +``` +<|im_start|>system +You are a helpful assistant.<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +Most tools (llama.cpp `-cnv`, LM Studio, Ollama) apply this automatically via the embedded chat template — no manual formatting needed. + +## 🛠️ How It Was Made + +1. **Merge** — `deepseek-ai/DeepSeek-R1-Distill-Qwen-7B` linearly blended into `Qwen/Qwen2.5-7B-Instruct` (15%/85%) using mergekit, with the tokenizer taken from the base model. +2. **Convert** — merged safetensors converted to GGUF (F16) using `llama.cpp`'s `convert_hf_to_gguf.py`. +3. **Quantize** — F16 GGUF quantized into multiple formats using `llama-quantize`, covering everything from ultra-compact (Q2_K) to near-lossless (Q8_0). + +## ⚠️ Limitations + +- This is a **merge**, not a model trained from scratch — behavior is a blend of its parent models and may inherit their quirks or biases. +- Lower-bit quantizations (Q2_K, Q3_K_M) trade quality for size; expect more inconsistency at extreme compression. +- Not evaluated on standard benchmarks yet — treat outputs with normal LLM caution, especially for factual or high-stakes use. + +## 🙏 Credits + +- Base models: [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct), [deepseek-ai/DeepSeek-R1-Distill-Qwen-7B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B) +- Merge tooling: [mergekit](https://github.com/arcee-ai/mergekit) +- Quantization tooling: [llama.cpp](https://github.com/ggerganov/llama.cpp) + +--- + +
+ +**If this was useful, a ⭐️ on the repo helps others find it.** + +
\ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..bdf7919 --- /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 Qwen, created by Alibaba Cloud. 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..c5590b1 --- /dev/null +++ b/config.json @@ -0,0 +1,61 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 3584, + "initializer_range": 0.02, + "intermediate_size": 18944, + "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" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2", + "num_attention_heads": 28, + "num_hidden_layers": 28, + "num_key_value_heads": 4, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": false, + "transformers_version": "5.0.0", + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151665 +} diff --git a/mergekit_config.yml b/mergekit_config.yml new file mode 100644 index 0000000..a29da95 --- /dev/null +++ b/mergekit_config.yml @@ -0,0 +1,14 @@ + +slices: + - sources: + - model: Qwen/Qwen2.5-7B-Instruct + layer_range: [0, 28] + - model: deepseek-ai/DeepSeek-R1-Distill-Qwen-7B + layer_range: [0, 28] +merge_method: slerp +base_model: Qwen/Qwen2.5-7B-Instruct +parameters: + t: + - value: 0.5 +dtype: bfloat16 +tokenizer_source: base diff --git a/model-00001-of-00009.safetensors b/model-00001-of-00009.safetensors new file mode 100644 index 0000000..61d6fa7 --- /dev/null +++ b/model-00001-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cf93d4d9dc8438c257d2d11bf13757c36da4abfc9e59ae9d346f70e716aad08 +size 1087134848 diff --git a/model-00002-of-00009.safetensors b/model-00002-of-00009.safetensors new file mode 100644 index 0000000..0f5ef9c --- /dev/null +++ b/model-00002-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:616a7c713ac350b08c6787a3e1373797e9c14d56e083db2d4781301dfe9bec68 +size 1990007272 diff --git a/model-00003-of-00009.safetensors b/model-00003-of-00009.safetensors new file mode 100644 index 0000000..a0c7dcf --- /dev/null +++ b/model-00003-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584e03b067ffba55aae08c8cb11e0d1aca2bbde30153886676b58fc352f72def +size 1893836600 diff --git a/model-00004-of-00009.safetensors b/model-00004-of-00009.safetensors new file mode 100644 index 0000000..8f2aecd --- /dev/null +++ b/model-00004-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89acdcd4473680d2e6805ba28534741b1709eda1363153ec45639406e95952a +size 1864467840 diff --git a/model-00005-of-00009.safetensors b/model-00005-of-00009.safetensors new file mode 100644 index 0000000..17bd1a3 --- /dev/null +++ b/model-00005-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0f1303bd6cac932d085d77807394d209111820a0357af5df274594679fdc207 +size 1864467832 diff --git a/model-00006-of-00009.safetensors b/model-00006-of-00009.safetensors new file mode 100644 index 0000000..f101dd1 --- /dev/null +++ b/model-00006-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1b2ee74f283cb2fcc775fee0f9ac8585db885dc68ab1d21a692049fe367a410 +size 1864467840 diff --git a/model-00007-of-00009.safetensors b/model-00007-of-00009.safetensors new file mode 100644 index 0000000..5a16441 --- /dev/null +++ b/model-00007-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5bda08f8fe304426bb559992997d66f61be918f6a827e00c963db52c39ddfb +size 1864467832 diff --git a/model-00008-of-00009.safetensors b/model-00008-of-00009.safetensors new file mode 100644 index 0000000..3e2053f --- /dev/null +++ b/model-00008-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3c7433f495c66245966f0ff5c5bbdda0d9378e532e5f0492904931d0df4d52c +size 1864467792 diff --git a/model-00009-of-00009.safetensors b/model-00009-of-00009.safetensors new file mode 100644 index 0000000..6cbf192 --- /dev/null +++ b/model-00009-of-00009.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e430633b4fb87814a3d608e584040192fa1d255e55e80a89328cf70729c9e6a +size 932233872 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..75dd7ae --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,347 @@ +{ + "metadata": { + "total_size": 15225512960, + "mergekit_version": "0.1.4" + }, + "weight_map": { + "lm_head.weight": "model-00001-of-00009.safetensors", + "model.embed_tokens.weight": "model-00002-of-00009.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00009.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00009.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", + "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00009.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00009.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00009.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", + "model.layers.21.input_layernorm.weight": "model-00005-of-00009.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00009.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", + "model.layers.25.input_layernorm.weight": "model-00006-of-00009.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00007-of-00009.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", + "model.layers.4.input_layernorm.weight": "model-00007-of-00009.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00009.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00009-of-00009.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", + "model.norm.weight": "model-00009-of-00009.safetensors" + } +} \ No newline at end of file diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..34510ff --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8 +size 11421892 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..0ca84bd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,30 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "is_local": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "chat_template": "{%- if messages[0]['role'] != 'system' -%}{{- '<|im_start|>system\\nYou are Kepler, an AI assistant created by intellectlabs. If asked who you are, who made you, or what model you are, give a short, direct one- or two-sentence answer \u2014 you are Kepler by intellectlabs. Never claim to be Qwen, DeepSeek, ChatGPT, or any other assistant. Do not add extra unrelated commentary, examples, or continue the conversation on your own \u2014 answer only what was asked, then stop. Always reply in the same language the user wrote in (e.g. reply in Hindi if asked in Hindi, English if asked in English). Be helpful, clear, and concise, like a professional assistant.<|im_end|>\\n' -}}{%- endif -%}{%- for message in messages -%}{{- '<|im_start|>' + message['role'] + '\\n' + message['content'] + '<|im_end|>\\n' -}}{%- endfor -%}{%- if add_generation_prompt -%}{{- '<|im_start|>assistant\\n' -}}{%- endif -%}" +} \ No newline at end of file