初始化项目，由ModelHub XC社区提供模型

Model: tartuNLP/Apertus-EstLLM-8B-Instruct-0326
Source: Original Platform

.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

README.md

@@ -0,0 +1,253 @@
+---
+library_name: transformers
+language:
+- et
+- en
+base_model:
+- tartuNLP/Apertus-EstLLM-8B-Instruct-1125
+- swiss-ai/Apertus-8B-Instruct-2509
+tags:
+- merge
+license: apache-2.0
+---
+
+![image/png](assets/logo-sinine.png)
+
+# Apertus EstLLM 8B 0326 Instruct
+
+`Llama-3.1-EstLLM-8B-Instruct-0326` is obtained by applying the chat-vector merge approach
+to [tartuNLP/Apertus-EstLLM-8B-Instruct-1125](https://huggingface.co/tartuNLP/Apertus-EstLLM-8B-Instruct-1125).
+
+## Use with transformers
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model_name = "tartuNLP/Apertus-EstLLM-8B-Instruct-0326"
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    dtype="auto",
+    device_map="auto"
+)
+
+# to use on apple silicon, load the following way
+# model = AutoModelForCausalLM.from_pretrained(
+#     model_name,
+#     dtype=torch.float16,
+#     device_map="mps",
+# )
+
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+messages = [
+    {"role": "user", "content": "Kas sa räägid eesti keelt?"}
+]
+
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+
+model_inputs = tokenizer(text, return_tensors="pt").to(model.device)
+
+generated_ids = model.generate(
+    **model_inputs,
+    max_new_tokens=128,
+    do_sample=True,
+    temperature=0.4,
+    # specify eos token to stop at the end of the assistant response
+    eos_token_id=tokenizer.eos_token_id,
+)
+
+# generated_ids include the input tokens as well, so we only decode new tokens
+response = tokenizer.decode(
+    generated_ids[0][model_inputs["input_ids"].shape[1]:],
+    skip_special_tokens=True,
+)
+
+print(response)
+```
+
+## Evaluation
+
+## Logits-based
+
+Scores for logits-based evaluation benchmarks are available on the [EuroEval](https://euroeval.com/leaderboards/Monolingual/estonian/) leaderboard.
+
+## Generative
+
+Every benchmark in this category is treated as a *generative* problem, and thus the evaluation is performed on the model responses obtained with 0 temperature (not logits).
+The top scores are higlighted with **bold**. Second best scores are highlighted with **_italic bold_**. Rows are sorted in descending order based on the number of parameters of models (not scores).
+The test set is used for evaluation of each dataset unless noted otherwise.
+
+Note that _all models are evaluated with the same prompt template_ for comparability, meaning that the scores do not necessarily represent each model's best possible
+performance. This is especially the case for `deepseek-ai/DeepSeek-V3-0324` on some of the benchmarks.
+
+Only models of comparable size are evaluated on benchmarks in English.
+
+### Instruction-following
+
+#### Estonian
+
+Instruction level strict accuracy is reported for IFEval-et.
+
+| Model (# parameters ↓) | [IFEval-et](https://huggingface.co/datasets/tartuNLP/ifeval_et)  |
+|-------|-----------------------------------|
+| moonshotai/Kimi-K2-Instruct | **0.7891** |
+| deepseek-ai/DeepSeek-V3.2 | 0.7221 |
+| deepseek-ai/DeepSeek-V3-0324 | 0.7171 |
+| mistralai/Mistral-Large-3-675B-Instruct-2512 | 0.7097 |
+| meta-llama/Llama-3.1-405B-Instruct | 0.7159 |
+| meta-llama/Llama-3.3-70B-Instruct | **_0.7705_** |
+| Qwen/Qwen2.5-72B-Instruct | 0.7407 |
+| google/gemma-3-27b-it | 0.7655 |
+| google/gemma-3-12b-it | 0.7556 |
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.5571 |
+| utter-project/EuroLLM-9B-Instruct | 0.5397 |
+| mistralai/Ministral-3-8B-Instruct-2512 | 0.4888 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326** | 0.5608 | 
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125 | 0.4665 | 
+| swiss-ai/Apertus-8B-Instruct-2509| 0.5484 |
+| meta-llama/Llama-3.1-8B-Instruct | 0.3797 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 | 0.6141 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 | 0.5174 |
+| BSC-LT/salamandra-7b-instruct | 0.5195 |
+| tartuNLP/Llammas | 0.3524 |
+| Qwen/Qwen2.5-7B-Instruct | 0.4988 |
+| CohereLabs/tiny-aya-global | 0.6687 |
+
+
+#### English
+
+Instruction level strict accuracy is reported for IFEval-en.
+
+
+| Model (# parameters ↓) | [IFEval-en](https://huggingface.co/datasets/tartuNLP/ifeval_en)  |
+|-------|-----------------------------------|
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.7564 |
+| utter-project/EuroLLM-9B-Instruct | 0.7004 |
+| mistralai/Ministral-3-8B-Instruct-2512 | 0.6845 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326** | 0.7089 |
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125 | 0.6638 |
+| swiss-ai/Apertus-8B-Instruct-2509 | 0.7808 |
+| meta-llama/Llama-3.1-8B-Instruct | _**0.8106**_ |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 | **0.8173** |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 | 0.7527 |
+| tartuNLP/Llammas | 0.4373 |
+| BSC-LT/salamandra-7b-instruct | 0.3289 |
+| Qwen/Qwen2.5-7B-Instruct | 0.7954 |
+
+### Multiple Choice
+
+All datasets except Winogrande-et are evaluated in 0-shot mode. Winogrande-et is evaluated in 3-shot mode. Exact match accuracy is reported for every dataset.
+
+#### Estonian Language Competence
+
+| Model (# parameters ↓) | [Grammar-et](https://huggingface.co/datasets/TalTechNLP/grammar_et)| [Inflection-et](https://huggingface.co/datasets/TalTechNLP/inflection_et)| [Word-Meanings-et](https://huggingface.co/datasets/TalTechNLP/word_meanings_et) |
+|-------|------|------|--------|
+| moonshotai/Kimi-K2-Instruct  | **0.916** | 0.6458 | **0.9689** |
+| deepseek-ai/DeepSeek-V3.2 | 0.781 | 0.6891 | 0.8134 |
+| deepseek-ai/DeepSeek-V3-0324  | 0.364 | 0 | 0 |
+| mistralai/Mistral-Large-3-675B-Instruct-2512 | 0.796 | _**0.8355**_ | 0.9488 |
+| meta-llama/Llama-3.1-405B-Instruct | 0.818 | **0.9089** | 0.9438 |
+| meta-llama/Llama-3.3-70B-Instruct  | 0.797 | 0.6421 | 0.9408 |
+| Qwen/Qwen2.5-72B-Instruct  | 0.694 | 0.5208 | 0.9057 |
+| google/gemma-3-27b-it | 0.817 | 0.5934 | 0.9529 |
+| google/gemma-3-12b-it | 0.789 | 0.4227 | 0.9318 |
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.644 | 0.4466 | 0.9288 |
+| utter-project/EuroLLM-9B-Instruct | 0.764 | 0.367 | 0.9258 |
+| mistralai/Ministral-3-8B-Instruct-2512 | 0.562 | 0.4833 | 0.8395 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326**| 0.713 | 0.4326 | 0.9438 |
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125| 0.646 | 0.421 | 0.9178 |
+| swiss-ai/Apertus-8B-Instruct-2509 | 0.512 | 0.3662 | 0.9027 |
+| meta-llama/Llama-3.1-8B-Instruct | 0.657 | 0.4165 | 0.8335 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 | _**0.8310**_ | 0.5777 | _**0.9619**_ |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825  | 0.692 | 0.5188 | 0.9569 |
+| BSC-LT/salamandra-7b-instruct  | 0.594 | 0.2668 | 0.8084 |
+| Qwen/Qwen2.5-7B-Instruct | 0.598 | 0.4136 | 0.7984 |
+| tartuNLP/Llammas | 0.529 | 0.2289 | 0.5326 |
+| CohereLabs/tiny-aya-global | 0.563 | 0.3221 | 0.8455 |
+
+#### Knowledge and Reasoning (Estonian)
+
+
+| Model (# parameters ↓) | [Winogrande-et](https://huggingface.co/datasets/tartuNLP/winogrande_et) | [Trivia-et](https://huggingface.co/datasets/TalTechNLP/trivia_et) | [Exam-et](https://huggingface.co/datasets/TalTechNLP/exam_et) | [GlobalPIQA-et](https://huggingface.co/datasets/mrlbenchmarks/global-piqa-nonparallel/viewer/ekk_latn)|  [TruthfulQA-et](https://huggingface.co/datasets/LumiOpen/opengpt-x_truthfulqax/viewer/mc_ET) |
+|-------|-----------------------------------|---------------------------------------------|---------------------------------------------|---------------------------------------------|-------------------------------------------|
+| moonshotai/Kimi-K2-Instruct  | **0.8138** | 0.4225 | **0.8414** | **0.79** | **0.7136** |
+| deepseek-ai/DeepSeek-V3.2 | 0.4805 | 0.38 | 0.614 | 0.7 | 0.5863 |
+| deepseek-ai/DeepSeek-V3-0324  | **_0.8042_** | 0.27 | 0.1221 | 0.04 | 0.2093 |
+| mistralai/Mistral-Large-3-675B-Instruct-2512 | 0.7487 | 0.4275 | 0.7931 | _**0.73**_ | 0.6854 |
+| meta-llama/Llama-3.1-405B-Instruct |0.7878  | **0.4713** | _**0.8309**_ | 0.58 | _**0.7001**_ |
+| meta-llama/Llama-3.3-70B-Instruct  |0.7397  | 0.3875 | 0.7652 | 0.58 | 0.6255 |
+| Qwen/Qwen2.5-72B-Instruct  | 0.7227 | 0.315 | 0.7162 | 0.65 | 0.6683 |
+| google/gemma-3-27b-it | 0.7510 | 0.325 | 0.7751 | 0.71 | 0.5814 |
+| google/gemma-3-12b-it | 0.6712 | 0.3237 | 0.7069 | 0.54 | 0.3158 |
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.5195 | 0.375 | 0.6097 | 0.52 | 0.399 |
+| utter-project/EuroLLM-9B-Instruct | 0.5846 | 0.3738 | 0.5589 | 0.55 | 0.2889 |
+| mistralai/Ministral-3-8B-Instruct-2512 | 0.5812 | 0.3125 | 0.5012 | 0.48 | 0.3525 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326** | 0.5976 | 0.35 | 0.6022 | 0.64 | 0.4296 |
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125 | 0.5467 | 0.3575 | 0.5651 | 0.63 | 0.3696 |
+| swiss-ai/Apertus-8B-Instruct-2509 | 0.5105 | 0.345 | 0.552 | 0.59 | 0.366 |
+| meta-llama/Llama-3.1-8B-Instruct | 0.5399 | 0.2888 | 0.5 | 0.54 | 0.437 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125  | 0.6440 | _**0.4288**_ | 0.6332 | 0.68 | 0.3794 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825  | 0.5812 | 0.425 | 0.5093 | 0.63 | 0.3525 |
+| BSC-LT/salamandra-7b-instruct  | 0.2878 | 0.2875 | 0.3556 | 0.55 | 0.3011 |
+| Qwen/Qwen2.5-7B-Instruct | 0.5473 | 0.2938 | 0.4913 | 0.57 | 0.4113 |
+| tartuNLP/Llammas | 0.5037 | 0.2838 | 0.3649 | 0.01 | 0.2032 |
+| CohereLabs/tiny-aya-global | 0.5603 | 0.31 | 0.5638 | 0.52 | 0.3782 |
+
+#### Knowledge and Reasoning (English)
+
+
+| Model (# parameters ↓) | [Winogrande](https://huggingface.co/datasets/allenai/winogrande)  | [GlobalPIQA-en](https://huggingface.co/datasets/mrlbenchmarks/global-piqa-nonparallel/viewer/eng_latn) | [TruthfulQA](https://huggingface.co/datasets/truthfulqa/truthful_qa) | [MMLU-Redux](https://huggingface.co/datasets/edinburgh-dawg/mmlu-redux-2.0) | [GSM8K](https://huggingface.co/datasets/openai/gsm8k) |
+|-------|-----------------------------------|-----------------------------------|-----------------------------------|-----------------------------------|-----------------------------------|
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.5546 | 0.58 |0.4614 | 0.6334 | 0.4139 |
+| utter-project/EuroLLM-9B-Instruct | 0.5059 | 0.58 | 0.2962 | 0.5741 | 0.5944 |
+| mistralai/Ministral-3-8B-Instruct-2512 | _**0.6503**_ | _**0.77**_ | 0.519 | _**0.7418**_ | 0.3927 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326** | 0.5699 | 0.69 | 0.4174 | 0.5946 | 0.5588 |
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125 | 0.5348 | 0.56 | 0.3647 | 0.5944 | 0.5277 |
+| swiss-ai/Apertus-8B-Instruct-2509 | 0.5133 | 0.73 | 0.3831 | 0.6099 | 0.5936 |
+| meta-llama/Llama-3.1-8B-Instruct | 0.5625 | 0.76 | _**0.5239**_ | 0.6959 | 0.7710 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 | 0.6118 | 0.76 | 0.3635 | 0.6606 | _**0.7726**_ |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 | 0.6084 | 0.71 | 0.366 | 0.6388 | 0.7202 |
+| tartuNLP/Llammas | 0.498 | 0 | 0.1971 | 0.3417 | 0.1456 |
+| BSC-LT/salamandra-7b-instruct | 0.4029 | 0.63 | 0.2717 | 0.5180 | 0.0076 |
+| Qwen/Qwen2.5-7B-Instruct | **0.6627** | **0.83** | **0.5875** | **0.7555** | **0.7862** |
+
+
+### Translation
+
+#### English to Estonian
+
+| Model | [wmt24pp](https://huggingface.co/datasets/google/wmt24pp) (BLEU ↑) |
+|-------|---------|
+| BSC-LT/salamandraTA-7b-instruct | 0.2713 |
+| **tartuNLP/Apertus-EstLLM-8B-Instruct-0326** | 0.2676 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-1125 | 0.2635 |
+| tartuNLP/Llama-3.1-EstLLM-8B-Instruct-0825 | 0.264 |
+| tartuNLP/Apertus-EstLLM-8B-Instruct-1125| 0.2609 |
+| utter-project/EuroLLM-9B-Instruct | 0.2602 |
+| utter-project/EuroLLM-9B-Instruct-2512 | 0.2567 |
+| swiss-ai/Apertus-8B-Instruct-2509 | 0.2372 |
+| tartuNLP/Llammas | 0.1472 |
+| meta-llama/Llama-3.1-8B-Instruct | 0.1406 |
+| BSC-LT/salamandra-7b-instruct | 0.1201 |
+| Qwen/Qwen2.5-7B-Instruct | 0.0476 |
+
+
+
+## Citation
+
+```
+@misc{dorkin2026estllmenhancingestoniancapabilities,
+      title={{EstLLM: Enhancing Estonian Capabilities in Multilingual LLMs via Continued Pretraining and Post-Training}}, 
+      author={Aleksei Dorkin and Taido Purason and Emil Kalbaliyev and Hele-Andra Kuulmets and Marii Ojastu and Mark Fišel and Tanel Alumäe and Eleri Aedmaa and Krister Kruusmaa and Kairit Sirts},
+      year={2026},
+      eprint={2603.02041},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2603.02041}, 
+}

chat_template.jinja

@@ -0,0 +1,337 @@
+{%- macro render_typescript_type(param_spec, required_params, is_nullable=false) -%}
+    {%- if param_spec.type == "array" -%}
+        {%- if param_spec['items'] -%}
+            {%- if param_spec['items']['type'] == "string" -%}
+                {{- "string[]" }}
+            {%- elif param_spec['items']['type'] == "number" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "integer" -%}
+                {{- "number[]" }}
+            {%- elif param_spec['items']['type'] == "boolean" -%}
+                {{- "boolean[]" }}
+            {%- else -%}
+                {%- set inner_type = render_typescript_type(param_spec['items'], required_params) -%}
+                {%- if inner_type == "object | object" or inner_type|length > 50 -%}
+                    {{- "any[]" }}
+                {%- else -%}
+                    {{- inner_type + "[]" }}
+                {%- endif -%}
+            {%- endif -%}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- else -%}
+            {{- "any[]" }}
+            {%- if param_spec.nullable -%}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type is defined and param_spec.type is iterable and param_spec.type is not string and param_spec.type is not mapping and param_spec.type[0] is defined -%}
+        {#- Handle array of types like ["object", "object"] from Union[dict, list] #}
+        {%- if param_spec.type | length > 1 -%}
+            {{- param_spec.type | join(" | ") }}
+        {%- else -%}
+            {{- param_spec.type[0] }}
+        {%- endif -%}
+    {%- elif param_spec.oneOf -%}
+        {#- Handle oneOf schemas - check for complex unions and fallback to any #}
+        {%- set has_object_variants = false -%}
+        {%- for variant in param_spec.oneOf -%}
+            {%- if variant.type == "object" -%}
+                {%- set has_object_variants = true -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- if has_object_variants and param_spec.oneOf|length > 1 -%}
+            {{- "any" }}
+        {%- else -%}
+            {%- for variant in param_spec.oneOf -%}
+                {{- render_typescript_type(variant, required_params) -}}
+                {%- if variant.description %}
+                    {{- "// " + variant.description }}
+                {%- endif -%}
+                {%- if variant.default is defined %}
+                    {{ "// default: " + variant.default|tojson }}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- " | " }}
+                {% endif -%}
+            {%- endfor -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "string" -%}
+        {%- if param_spec.enum -%}
+            {{- '"' + param_spec.enum|join('" | "') + '"' -}}
+        {%- else -%}
+            {{- "string" }}
+            {%- if param_spec.nullable %}
+                {{- " | null" }}
+            {%- endif -%}
+        {%- endif -%}
+    {%- elif param_spec.type == "number" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "integer" -%}
+        {{- "number" }}
+    {%- elif param_spec.type == "boolean" -%}
+        {{- "boolean" }}
+    {%- elif param_spec.type == "object" -%}
+        {%- if param_spec.properties -%}
+            {{- "{\n" }}
+            {%- for prop_name, prop_spec in param_spec.properties.items() -%}
+                {{- prop_name -}}
+                {%- if prop_name not in (param_spec.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{ render_typescript_type(prop_spec, param_spec.required or []) }}
+                {%- if not loop.last -%}
+                    {{-", " }}
+                {%- endif -%}
+            {%- endfor -%}
+            {{- "}" }}
+        {%- else -%}
+            {{- "object" }}
+        {%- endif -%}
+    {%- else -%}
+        {{- "any" }}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tools(tools) -%}
+    {%- for tool in tools %}
+        {{- "// " + tool.description + "\n" }}
+        {{- "type "+ tool.name + " = " }}
+        {%- if tool.parameters and tool.parameters.properties %}
+            {{- "(_: {\n" }}
+            {%- for param_name, param_spec in tool.parameters.properties.items() %}
+                {%- if param_spec.description %}
+                    {{- "// " + param_spec.description + "\n" }}
+                {%- endif %}
+                {{- param_name }}
+                {%- if param_name not in (tool.parameters.required or []) -%}
+                    {{- "?" }}
+                {%- endif -%}
+                {{- ": " }}
+                {{- render_typescript_type(param_spec, tool.parameters.required or []) }}
+                {%- if param_spec.default is defined -%}
+                    {%- if param_spec.enum %}
+                        {{- ", // default: " + param_spec.default }}
+                    {%- elif param_spec.oneOf %}
+                        {{- "// default: " + param_spec.default }}
+                    {%- else %}
+                        {{- ", // default: " + param_spec.default|tojson }}
+                    {%- endif -%}
+                {%- endif -%}
+                {%- if not loop.last %}
+                    {{- ",\n" }}
+                {%- else %}
+                    {{- "\n" }}
+                {%- endif -%}
+            {%- endfor %}
+            {{- "}) => any;" }}
+        {%- else -%}
+            {{- "() => any;" }}
+        {%- endif -%}
+        {%- if not loop.last -%}
+            {{- "\n" }}
+        {%- endif -%}
+    {%- endfor %}
+{%- endmacro -%}
+
+{{ bos_token }}
+
+{%- set system_token = '<|system_start|>' -%}
+{%- set end_system_token = '<|system_end|>' -%}
+{%- set developer_token = '<|developer_start|>' -%}
+{%- set end_developer_token = '<|developer_end|>' -%}
+{%- set user_token = '<|user_start|>' -%}
+{%- set end_user_token = '<|user_end|>' -%}
+{%- set assistant_token = '<|assistant_start|>' -%}
+{%- set end_assistant_token = '<|assistant_end|>' -%}
+{%- set inner_token = '<|inner_prefix|>' -%}
+{%- set outer_token = '<|inner_suffix|>' -%}
+{%- set tool_calls_token = '<|tools_prefix|>' -%}
+{%- set end_tool_calls_token = '<|tools_suffix|>' -%}
+{%- set image_token = '<|image|>' -%}
+
+{%- set ns = namespace(in_assistant=false, in_tool=false, in_inner=false, waiting_for_tool_outputs=false, assistant_format=none) -%}
+
+{%- if messages and messages[0].role == 'system' -%}
+    {%- if "content" in messages[0] -%}
+        {%- if messages[0].content is string -%}
+            {{ system_token + messages[0].content + end_system_token }}
+        {%- elif messages[0].content is mapping and "text" in messages[0].content -%}
+            {{ system_token + messages[0].content.text + end_system_token }}
+        {%- else -%}
+            {{- raise_exception("Invalid system message") -}}
+        {%- endif -%}
+    {%- else -%}
+        {{- raise_exception("Invalid system message") -}}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {{ system_token + 'You are Apertus, a helpful assistant created by the SwissAI initiative.\nKnowledge cutoff: 2024-04\nCurrent date: ' + strftime_now('%Y-%m-%d') + end_system_token }}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+
+{{ developer_token + 'Deliberation: ' }}
+{%- if enable_thinking is defined and enable_thinking -%}
+    {{ 'enabled\n' }}
+{%- else -%}
+    {{ 'disabled\n' }}
+{%- endif -%}
+{%- if tools is defined and tools -%}
+    {{ 'Tool Capabilities:\n' + render_tools(tools) }}
+{%- else -%}
+    {{ 'Tool Capabilities: disabled' }}
+{%- endif -%}
+{{ end_developer_token }}
+
+{%- for message in loop_messages -%}
+    {%- if message.role == 'user' -%}
+        {%- set ns.in_inner = false -%}
+        {%- if ns.in_tool -%}
+            {{ ']' }}
+            {%- set ns.in_tool = false -%}
+        {%- endif -%}
+        {%- if ns.in_assistant -%}
+            {{ end_assistant_token }}
+            {%- set ns.in_assistant = false -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {{ user_token }}
+            {%- if message.content is string -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "parts" in message.content -%}
+                {%- set parts = message.content.parts -%}
+                {%- for part in parts -%}
+                    {%- if part.type == "text" -%}
+                        {{ part.text }}
+                    {%- elif part.type == "image" -%}
+                        {{ image_token }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid user part: " + part.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid user message: " + message.role) -}}
+            {%- endif -%}
+            {{ end_user_token }}
+        {%- endif -%}
+    {%- elif message.role == 'assistant' -%}
+        {%- if not ns.in_assistant -%}
+            {{ assistant_token }}
+            {%- set ns.in_assistant = true -%}
+        {%- endif -%}
+        {%- if "content" in message -%}
+            {%- if message.content is string and (ns.assistant_format is none or ns.assistant_format == "string") -%}
+                {%- if ns.in_tool -%}
+                    {{ ']' }}
+                    {%- set ns.in_tool = false -%}
+                {%- endif -%}
+                {%- set ns.assistant_format = "string" -%}
+                {{ message.content }}
+            {%- elif message.content is mapping and "blocks" in message.content and (ns.assistant_format is none or ns.assistant_format == "mapping") -%}
+                {%- set ns.assistant_format = "mapping" -%}
+                {%- set blocks = message.content.blocks -%}
+                {%- for block in blocks -%}
+                    {%- if block.type == 'thoughts' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if not ns.in_inner -%}
+                            {%- set ns.in_inner = true -%}
+                            {{ inner_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- elif block.type == 'tool_calls' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if ns.in_inner and not loop.first and block.calls|length == 1 and block.calls[0].name == 'display_answers' -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ tool_calls_token + '[' }}
+                        {%- for tool_call in block.calls -%}
+                            {{- '{"' + tool_call.name + '": ' + tool_call.arguments + '}' }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{ ']' + end_tool_calls_token }}
+                        {%- set ns.waiting_for_tool_outputs = true -%}
+                    {%- elif block.type == 'tool_outputs' -%}
+                        {%- if ns.in_tool -%}
+                            {{- raise_exception("Cannot have both tool outputs as separate messages and tool outputs as blocks") -}}
+                        {%- endif -%}
+                        {{ '[' }}
+                        {%- for tool_output in block.outputs -%}
+                            {{- tool_output.output }}
+                            {%- if not loop.last -%}
+                                {{- ", " }}
+                            {%- endif -%}
+                        {%- endfor -%}
+                        {{- ']' }}
+                        {%- set ns.waiting_for_tool_outputs = false -%}
+                    {%- elif block.type == 'response' -%}
+                        {%- if ns.in_tool -%}
+                            {{ ']' }}
+                            {%- set ns.in_tool = false -%}
+                        {%- endif -%}
+                        {%- if (not loop.first and ns.in_inner) or (ns.in_assistant and ns.in_inner) -%}
+                            {%- set ns.in_inner = false -%}
+                            {{ outer_token }}
+                        {%- endif -%}
+                        {{ block.text }}
+                    {%- else -%}
+                        {{- raise_exception("Invalid assistant block type: " + block.type) -}}
+                    {%- endif -%}
+                {%- endfor -%}
+            {%- else -%}
+                {{- raise_exception("Invalid assistant content") -}}
+            {%- endif -%}
+        {%- else -%}
+            {{- raise_exception("Invalid assistant message") -}}
+        {%- endif -%}
+        {%- if "tool_calls" in message and message.tool_calls -%}
+            {{ tool_calls_token + '[' }}
+            {%- for tool_call in message.tool_calls -%}
+                {%- if tool_call.type == 'function' -%}
+                    {%- set function = tool_call.function -%}
+                    {{- '{"' + function.name + '": ' + function.arguments + '}' }}
+                    {%- if not loop.last -%}
+                        {{- ", " }}
+                    {%- endif -%}
+                {%- else -%}
+                    {{- raise_exception("Invalid tool call type: " + tool_call.type) -}}
+                {%- endif -%}
+            {%- endfor -%}
+            {{ ']' + end_tool_calls_token }}
+            {%- set ns.waiting_for_tool_outputs = true -%}
+        {%- endif -%}
+    {%- elif message.role == 'tool' -%}
+        {%- if not ns.in_assistant -%}
+            {{- raise_exception("Tool message outside of assistant") -}}
+        {%- endif -%}
+        {%- if not ns.in_tool -%}
+            {{ '[' }}
+            {%- set ns.in_tool = true -%}
+        {%- else -%}
+            {{ ", "}}
+        {%- endif -%}
+        {{ message.content }}
+        {%- set ns.waiting_for_tool_outputs = false -%}
+    {%- else -%}
+        {{- raise_exception("Invalid message role") -}}
+    {%- endif -%}
+{%- endfor -%}
+{%- if ns.in_tool -%}
+    {{ ']' }}
+{%- endif -%}
+{%- if ns.in_assistant and not (continue_assistant_message is defined and continue_assistant_message) and not ns.waiting_for_tool_outputs -%}
+    {{ end_assistant_token }}
+{%- endif -%}
+{%- if add_generation_prompt -%}
+    {{ assistant_token }}
+{%- endif -%}

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "ApertusForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 68,
+  "hidden_act": "xielu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 65536,
+  "mlp_bias": false,
+  "model_type": "apertus",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 3,
+  "post_norm": false,
+  "qk_norm": true,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3",
+    "type": "llama3"
+  },
+  "rope_theta": 12000000,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    68,
+    72
+  ],
+  "pad_token_id": 3,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174a0305fe59da00f3f6422438a98f783890935d906ebe607c219c3e5dc0adc9
+size 4999776656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc87d197cda0fd413165ef75d5138aaa724ea7784d5551ca9311d916811c3620
+size 4882374192

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83d860d9d63f353d5f22c44102129c9e45317810f6bd634933543cab83320098
+size 4974647808

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4ccfcc62aa610b56f7943a1c4e701661a8d755f077bfeef3d259847eb2f8745
+size 1249928160

model.safetensors.index.json

@@ -0,0 +1,459 @@
+{
+  "metadata": {
+    "total_parameters": 8053338176,
+    "total_size": 16106676480
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_n": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.alpha_p": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.beta": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.act_fn.eps": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.feedforward_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_n": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.alpha_p": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.beta": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.act_fn.eps": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.feedforward_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_n": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.alpha_p": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.beta": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.act_fn.eps": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.feedforward_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_n": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.alpha_p": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.beta": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.act_fn.eps": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.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": "<|assistant_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010095abf1dc6f52d4867584e7b3f0d4eece854593ae310220ec7782dd1b0a66
+size 17078474