初始化项目，由ModelHub XC社区提供模型

Model: Locutusque/Hyperion-3.0-Mistral-7B-DPO
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,220 @@
+---
+library_name: transformers
+license: apache-2.0
+language:
+- en
+widget:
+- example_title: Reasoning
+  text: >
+    <|im_start|>system
+
+    You are Hyperion, an AI assistant developed by Sebastian Gabarain with a
+    focus in reasoning, coding, science, and other general-purpose subjects. You
+    are an AI assistant that follows instruction extremely well. Help as much as
+    you can.
+
+    <|im_end|>
+
+    <|im_start|>user
+
+    In this task, you are given a description of an object and its surroundings.
+    Your
+
+    task is to describe the motion of the object mentioned in the description
+    using
+
+    differential equations. The answer should be a mathematical expression in t.
+    Description:
+
+    A ball is thrown up at 30 ft/sec from 3 feet off the ground. Solve this
+    step-by-step,
+
+    explaining each step in detail.
+
+    <|im_end|>
+
+    <|im_start|>assistant
+  output:
+    text: >
+      Hyperion here. The task requires you to describe the motion of a ball
+      thrown up using differential equations. Here's the detailed explanation of
+      how to solve it:
+
+
+      1. Identify the given information:
+         - Initial velocity (v0): 30 ft/sec
+         - Initial height (y0): 3 feet off the ground
+
+      2. Determine the acceleration due to gravity (g) at sea level, which is
+      approximately -32.2 ft/s^2. Since we're dealing with a short distance and
+      not very high altitudes, we can consider this value of g as constant.
+
+
+      3. Use Newton's second law of motion to find the differential equation
+      that describes the motion:
+         - The net force acting on the ball is the sum of gravity (mg) and air resistance (which we will neglect for simplicity). So, Fnet = mg.
+         - Since acceleration equals force divided by mass, a = Fnet/m. In this case, m cancels out, so a = g.
+         - The motion equation becomes: dv/dt = g = -32.2 ft/s^2 (since we're moving upwards). This is the first differential equation.
+
+      4. Since we want to describe the ball's position (y) as well, we need
+      another differential equation. We can use kinematics equations:
+         - The velocity equation is v = v0 + at. Substitute the value of a from step 3:
+           dv/dt = -32.2 ft/s^2. Rewriting it as an integral:
+            ∫dv = -32.2 ft/s^2 * dt
+         - Integrating with respect to time, we get v(t) = -16.1 t + C (constant of integration).
+
+      5. Now we have two equations, one for velocity and another for position:
+         - dv/dt = -32.2 ft/s^2 (equation 1)
+         - v(t) = -16.1 t + C (equation 2)
+
+      6. We need to find the constant C using the initial conditions given in
+      the problem. We know that initially, at time t=0, the ball's velocity is
+      v0:
+         - Equation 2 becomes v0 = -16.1 * 0 + C, which simplifies to C = v0 = 30 ft/sec (initial velocity).
+
+      7. Now we have both equations with the constants filled in:
+         - dv/dt = -32.2 ft/s^2 (equation 1)
+         - v(t) = -16.1 t + 30 ft/sec (equation 2)
+
+      8. Finally, we need to find the ball's position (y) as a function of time:
+         - Use the second kinematics equation y = y0 + v0*t + ½*a*t^2 (since acceleration is constant, it can be moved outside the integral).
+         - Substitute the values for v0 and a:
+           y(t) = 3 ft + (30 ft/sec) * t + (-½ * 32.2 ft/s^2) * t^2
+
+      That's it! The differential equation describing the motion of the ball is:
+         - dv/dt = -32.2 ft/s^2 (equation 1)
+         - v(t) = -16.1 t + 30 ft/sec (equation 2)
+         - y(t) = 3 ft + (30 ft/sec) * t - (16.1 t^2) ft (equation 3)
+datasets:
+- Locutusque/hyperion-dpo-v1.0
+---
+# Hyperion-3.0-Mistral-7B-DPO
+
+## Model Details
+- **Model Name**: Locutusque/Hyperion-3.0-Mistral-7B-DPO 
+- **Base Model**: mistralai/Mistral-7B-v0.1
+- **Publisher**: Locutusque
+- **Model Type**: Question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, logical reasoning
+- **Language**: Multi-domain, English language
+- **License**: Apache-2.0
+
+## Model Description
+`Locutusque/Hyperion-3.0-Mistral-7B-DPO` is an advanced language model fine-tuned with a dataset of 20,000 meticulously curated high-quality preference pairs using Direct Preference Optimization (DPO). The examples were generated by GPT-4 to ensure exceptional quality and relevance. This model is designed to provide superior performance across a wide range of complex tasks, including question answering, conversational AI, code generation, medical text comprehension, mathematical reasoning, and logical reasoning.
+
+## Intended Use
+This model is intended for researchers, developers, and organizations seeking a highly capable and reliable language model for tackling challenging problems across various domains. Potential use cases include:
+- Intelligent tutoring systems and educational applications in science, medicine, mathematics, and computer science
+- Advanced conversational AI for technical support, customer service, and domain-specific chatbots
+- Code generation and analysis tools for software development and programming assistance
+- Medical text analysis and information retrieval for healthcare professionals and researchers
+- Mathematical problem-solving and logical reasoning applications for academia and industry
+
+## Training Data
+The `Locutusque/Hyperion-3.0-Mistral-7B-DPO` model was fine-tuned on a carefully curated dataset of 20,000 preference pairs, where 4,000 examples were used to fine-tune. These examples were generated by GPT-4 to ensure the highest quality and relevance across various domains, including programming, medical texts, mathematical problems, and reasoning tasks. The training data was further optimized using Direct Preference Optimization (DPO) to align the model's outputs with human preferences and improve overall performance.
+
+## Quants
+
+ExLlamaV2: https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-DPO-exl2
+
+GGUF: https://huggingface.co/bartowski/Hyperion-3.0-Mistral-7B-DPO-GGUF
+
+## Evaluation Results
+mmlu flan cot 5-shot
+
+|                            Tasks                            |Version|  Filter  |n-shot|  Metric   |Value |   |Stderr|
+|-------------------------------------------------------------|-------|----------|-----:|-----------|-----:|---|-----:|
+|mmlu_flan_cot_fewshot                                        |N/A    |get-answer|     0|exact_match|0.5833|±  |0.0118|
+| - mmlu_flan_cot_fewshot_humanities                          |N/A    |get-answer|     0|exact_match|0.5039|±  |0.0205|
+|  - mmlu_flan_cot_fewshot_formal_logic                       |      0|get-answer|     0|exact_match|0.2143|±  |0.1138|
+|  - mmlu_flan_cot_fewshot_high_school_european_history       |      0|get-answer|     0|exact_match|0.6667|±  |0.1143|
+|  - mmlu_flan_cot_fewshot_high_school_us_history             |      0|get-answer|     0|exact_match|0.7727|±  |0.0914|
+|  - mmlu_flan_cot_fewshot_high_school_world_history          |      0|get-answer|     0|exact_match|0.5385|±  |0.0997|
+|  - mmlu_flan_cot_fewshot_international_law                  |      0|get-answer|     0|exact_match|0.9231|±  |0.0769|
+|  - mmlu_flan_cot_fewshot_jurisprudence                      |      0|get-answer|     0|exact_match|0.5455|±  |0.1575|
+|  - mmlu_flan_cot_fewshot_logical_fallacies                  |      0|get-answer|     0|exact_match|0.7778|±  |0.1008|
+|  - mmlu_flan_cot_fewshot_moral_disputes                     |      0|get-answer|     0|exact_match|0.5526|±  |0.0817|
+|  - mmlu_flan_cot_fewshot_moral_scenarios                    |      0|get-answer|     0|exact_match|0.4000|±  |0.0492|
+|  - mmlu_flan_cot_fewshot_philosophy                         |      0|get-answer|     0|exact_match|0.7647|±  |0.0738|
+|  - mmlu_flan_cot_fewshot_prehistory                         |      0|get-answer|     0|exact_match|0.6571|±  |0.0814|
+|  - mmlu_flan_cot_fewshot_professional_law                   |      0|get-answer|     0|exact_match|0.3294|±  |0.0362|
+|  - mmlu_flan_cot_fewshot_world_religions                    |      0|get-answer|     0|exact_match|0.8947|±  |0.0723|
+| - mmlu_flan_cot_fewshot_other                               |N/A    |get-answer|     0|exact_match|0.6833|±  |0.0244|
+|  - mmlu_flan_cot_fewshot_business_ethics                    |      0|get-answer|     0|exact_match|0.9091|±  |0.0909|
+|  - mmlu_flan_cot_fewshot_clinical_knowledge                 |      0|get-answer|     0|exact_match|0.5862|±  |0.0931|
+|  - mmlu_flan_cot_fewshot_college_medicine                   |      0|get-answer|     0|exact_match|0.6364|±  |0.1050|
+|  - mmlu_flan_cot_fewshot_global_facts                       |      0|get-answer|     0|exact_match|0.6000|±  |0.1633|
+|  - mmlu_flan_cot_fewshot_human_aging                        |      0|get-answer|     0|exact_match|0.6087|±  |0.1041|
+|  - mmlu_flan_cot_fewshot_management                         |      0|get-answer|     0|exact_match|0.9091|±  |0.0909|
+|  - mmlu_flan_cot_fewshot_marketing                          |      0|get-answer|     0|exact_match|0.8000|±  |0.0816|
+|  - mmlu_flan_cot_fewshot_medical_genetics                   |      0|get-answer|     0|exact_match|1.0000|±  |0.0000|
+|  - mmlu_flan_cot_fewshot_miscellaneous                      |      0|get-answer|     0|exact_match|0.8023|±  |0.0432|
+|  - mmlu_flan_cot_fewshot_nutrition                          |      0|get-answer|     0|exact_match|0.6667|±  |0.0833|
+|  - mmlu_flan_cot_fewshot_professional_accounting            |      0|get-answer|     0|exact_match|0.4839|±  |0.0912|
+|  - mmlu_flan_cot_fewshot_professional_medicine              |      0|get-answer|     0|exact_match|0.5806|±  |0.0901|
+|  - mmlu_flan_cot_fewshot_virology                           |      0|get-answer|     0|exact_match|0.3889|±  |0.1182|
+| - mmlu_flan_cot_fewshot_social_sciences                     |N/A    |get-answer|     0|exact_match|0.7003|±  |0.0239|
+|  - mmlu_flan_cot_fewshot_econometrics                       |      0|get-answer|     0|exact_match|0.4167|±  |0.1486|
+|  - mmlu_flan_cot_fewshot_high_school_geography              |      0|get-answer|     0|exact_match|0.9091|±  |0.0627|
+|  - mmlu_flan_cot_fewshot_high_school_government_and_politics|      0|get-answer|     0|exact_match|0.8095|±  |0.0878|
+|  - mmlu_flan_cot_fewshot_high_school_macroeconomics         |      0|get-answer|     0|exact_match|0.6512|±  |0.0735|
+|  - mmlu_flan_cot_fewshot_high_school_microeconomics         |      0|get-answer|     0|exact_match|0.5769|±  |0.0988|
+|  - mmlu_flan_cot_fewshot_high_school_psychology             |      0|get-answer|     0|exact_match|0.9000|±  |0.0391|
+|  - mmlu_flan_cot_fewshot_human_sexuality                    |      0|get-answer|     0|exact_match|0.6667|±  |0.1421|
+|  - mmlu_flan_cot_fewshot_professional_psychology            |      0|get-answer|     0|exact_match|0.6522|±  |0.0578|
+|  - mmlu_flan_cot_fewshot_public_relations                   |      0|get-answer|     0|exact_match|0.5833|±  |0.1486|
+|  - mmlu_flan_cot_fewshot_security_studies                   |      0|get-answer|     0|exact_match|0.4074|±  |0.0964|
+|  - mmlu_flan_cot_fewshot_sociology                          |      0|get-answer|     0|exact_match|0.8182|±  |0.0842|
+|  - mmlu_flan_cot_fewshot_us_foreign_policy                  |      0|get-answer|     0|exact_match|0.7273|±  |0.1408|
+| - mmlu_flan_cot_fewshot_stem                                |N/A    |get-answer|     0|exact_match|0.4866|±  |0.0262|
+|  - mmlu_flan_cot_fewshot_abstract_algebra                   |      0|get-answer|     0|exact_match|0.0909|±  |0.0909|
+|  - mmlu_flan_cot_fewshot_anatomy                            |      0|get-answer|     0|exact_match|0.4286|±  |0.1373|
+|  - mmlu_flan_cot_fewshot_astronomy                          |      0|get-answer|     0|exact_match|0.5625|±  |0.1281|
+|  - mmlu_flan_cot_fewshot_college_biology                    |      0|get-answer|     0|exact_match|0.5000|±  |0.1291|
+|  - mmlu_flan_cot_fewshot_college_chemistry                  |      0|get-answer|     0|exact_match|0.5000|±  |0.1890|
+|  - mmlu_flan_cot_fewshot_college_computer_science           |      0|get-answer|     0|exact_match|0.2727|±  |0.1408|
+|  - mmlu_flan_cot_fewshot_college_mathematics                |      0|get-answer|     0|exact_match|0.3636|±  |0.1521|
+|  - mmlu_flan_cot_fewshot_college_physics                    |      0|get-answer|     0|exact_match|0.3636|±  |0.1521|
+|  - mmlu_flan_cot_fewshot_computer_security                  |      0|get-answer|     0|exact_match|0.7273|±  |0.1408|
+|  - mmlu_flan_cot_fewshot_conceptual_physics                 |      0|get-answer|     0|exact_match|0.6538|±  |0.0951|
+|  - mmlu_flan_cot_fewshot_electrical_engineering             |      0|get-answer|     0|exact_match|0.7500|±  |0.1118|
+|  - mmlu_flan_cot_fewshot_elementary_mathematics             |      0|get-answer|     0|exact_match|0.7317|±  |0.0701|
+|  - mmlu_flan_cot_fewshot_high_school_biology                |      0|get-answer|     0|exact_match|0.5938|±  |0.0882|
+|  - mmlu_flan_cot_fewshot_high_school_chemistry              |      0|get-answer|     0|exact_match|0.3636|±  |0.1050|
+|  - mmlu_flan_cot_fewshot_high_school_computer_science       |      0|get-answer|     0|exact_match|0.5556|±  |0.1757|
+|  - mmlu_flan_cot_fewshot_high_school_mathematics            |      0|get-answer|     0|exact_match|0.3103|±  |0.0874|
+|  - mmlu_flan_cot_fewshot_high_school_physics                |      0|get-answer|     0|exact_match|0.2353|±  |0.1060|
+|  - mmlu_flan_cot_fewshot_high_school_statistics             |      0|get-answer|     0|exact_match|0.3043|±  |0.0981|
+|  - mmlu_flan_cot_fewshot_machine_learning                   |      0|get-answer|     0|exact_match|0.4545|±  |0.1575|
+
+|                 Groups                 |Version|  Filter  |n-shot|  Metric   |Value |   |Stderr|
+|----------------------------------------|-------|----------|-----:|-----------|-----:|---|-----:|
+|mmlu_flan_cot_fewshot                   |N/A    |get-answer|     0|exact_match|0.5833|±  |0.0118|
+| - mmlu_flan_cot_fewshot_humanities     |N/A    |get-answer|     0|exact_match|0.5039|±  |0.0205|
+| - mmlu_flan_cot_fewshot_other          |N/A    |get-answer|     0|exact_match|0.6833|±  |0.0244|
+| - mmlu_flan_cot_fewshot_social_sciences|N/A    |get-answer|     0|exact_match|0.7003|±  |0.0239|
+| - mmlu_flan_cot_fewshot_stem           |N/A    |get-answer|     0|exact_match|0.4866|±  |0.0262|
+
+## How to Use
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_name = "Locutusque/Hyperion-3.0-Mistral-7B-DPO"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# For a text generation task
+input_text = "<|im_start|>user\nExplain the implications of quantum entanglement in layman's terms.<|im_end|>\n<|im_start|>assistant\n"
+input_ids = tokenizer.encode(input_text, return_tensors="pt")
+
+# Generate a response
+outputs = model.generate(input_ids, max_length=200, do_sample=True, top_p=0.7, top_k=6) # These are the recommended sample settings.
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Known Limitations
+While the training data has been carefully curated and optimized, there may still be some inconsistencies or biases present due to the inherent complexity and diversity of the source dataset. Users should be aware of potential limitations and carefully evaluate the model's outputs for their specific use case.
+
+Additionally, this model is highly compliant and will attempt to respond to most requests. For enterprise-level deployment, it is strongly recommended to further fine-tune the model using DPO to align its behavior with specific requirements and constraints.
+
+## Licensing Information
+This model is released under the Apache-2.0 license.

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "Locutusque/Hyperion-3.0-Mistral-7B-alpha",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.39.1"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931e088e4a3aedde7acc53377a541bb08d90ffaba7cdcd64092b37eb9a165af4
+size 1889587040

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac1a62cea9625cc1e253d7e13eaf8609a5883d66716e452091400ad8bb94218
+size 1946243936

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99369b1ec92218276e7e32c5c015aa476e0b33873372767abd2279a26a273c8a
+size 1979781432

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79b8a9260b0df09ae0a8aa3a0768c6ee20a4f5ce0d90e7b8c314ee7c5351673a
+size 1946243984

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5a5dc60b410658c6bb2a693b77e64a3ffea5c68750820c722b3bbddda72d73
+size 1979781448

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021b8b5f2c67a34ddd6b04d0b6f144dec067d75e1bad0ef3f35664f244c3d618
+size 1946243984

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b57435681dcb93d0db9c4f5db4954e4cbd18d74078f87f31f631dcb089cdb185
+size 1979781448

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67fda4a69b451da5ca0867da60f7a2921125c1f852fae6fe3bb5fc97c56b1a46
+size 815834680

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14483464192
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00008-of-00008.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "model.norm.weight": "model-00008-of-00008.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}