Upload 8 files

README.md

@@ -1,3 +1,228 @@
----
-license: mit
----
+---
+tags:
+- merge
+- mergekit
+- lazymergekit
+- anthracite-org/magnum-v2-12b
+- Trappu/Nemo-Picaro-12B
+base_model:
+- anthracite-org/magnum-v2-12b
+- Trappu/Nemo-Picaro-12B
+model-index:
+- name: Magnum-Picaro-0.7-v2-12b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 30.03
+      name: strict accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 35.75
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 4.76
+      name: exact match
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 9.73
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 19.56
+      name: acc_norm
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 28.67
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Trappu/Magnum-Picaro-0.7-v2-12b
+      name: Open LLM Leaderboard
+license: apache-2.0
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Details
+
+This model is a merge between [Trappu/Nemo-Picaro-12B](https://huggingface.co/Trappu/Nemo-Picaro-12B), a model trained on my own little dataset free of synthetic data, which focuses solely on storywriting and scenrio prompting (Example: `[ Scenario: bla bla bla; Tags: bla bla bla ]`), and [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b).
+
+The reason why I decided to merge it with Magnum (and don't recommend Picaro alone) is because that model, aside from its obvious flaws (rampant impersonation, stupid, etc...), is a one-trick pony and will be really rough for the average LLM user to handle. The idea was to have Magnum work as some sort of stabilizer to fix the issues that emerge from the lack of multiturn/smart data in Picaro's dataset. It worked, I think. I enjoy the outputs and it's smart enough to work with.
+
+But yeah the goal of this merge was to make a model that's both good at storytelling/narration but also fine when it comes to other forms of creative writing such as RP or chatting. I don't think it's quite there yet but it's something for sure.
+
+# Prompting
+
+As explained before, Picaro is a model that functions mainly through scenario prompting but merging it with Magnum has made it a lot more versatile so you can use it however you see fit. Both models were trained on chatml so below is the recommended prompt formatting.
+
+```
+<|im_start|>system
+system prompt<|im_end|>
+<|im_start|>user
+bla bla bla<|im_end|>
+<|im_start|>assistant
+bla bla bla you!<|im_end|>
+```
+
+For SillyTavern users:
+
+[Instruct template](https://firebasestorage.googleapis.com/v0/b/koios-academy.appspot.com/o/trappu%2FChatML%20custom%20Instruct%20template.json?alt=media&token=9142757f-811c-460c-ad0e-d04951b1687f)
+
+[Context template](https://firebasestorage.googleapis.com/v0/b/koios-academy.appspot.com/o/trappu%2FChatML%20custom%20context%20template.json?alt=media&token=0926fc67-fa9f-4c86-ad16-8c7c4c8e0b64)
+
+[Settings preset](https://firebasestorage.googleapis.com/v0/b/koios-academy.appspot.com/o/trappu%2FHigh%20temp%20-%20Min%20P%20(4).json?alt=media&token=ac569562-af11-4da1-83c1-d86b25bb4fe1)
+
+The above settings are the ones I recommend. 
+
+Temp = 1.2
+
+Min P = 0.1
+
+DRY Rep Pen: Multiplier = 0.8, Base = 1.75, Allowed Length = 2, Penalty Range = 1024
+
+Little guide on useful samplers and how to import settings presets and instruct/context templates and other stuff people might find useful [here](https://rentry.co/PygmalionFAQ#q-what-are-the-best-settings-for-rpadventurenarrationchatting)
+
+Every other sampler neutralized.
+
+# Quants
+
+Imatrix: https://huggingface.co/mradermacher/Magnum-Picaro-0.7-v2-12b-i1-GGUF
+
+Static: https://huggingface.co/mradermacher/Magnum-Picaro-0.7-v2-12b-GGUF
+
+
+# Magnum-Picaro-0.7-v2-12b
+
+Magnum-Picaro-0.7-v2-12b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+* [Trappu/Nemo-Picaro-12B](https://huggingface.co/Trappu/Nemo-Picaro-12B)
+* [anthracite-org/magnum-v2-12b](https://huggingface.co/anthracite-org/magnum-v2-12b)
+
+## 🧩 Configuration
+
+```yaml
+models:
+    - model: Trappu/Nemo-Picaro-12B
+      parameters:
+        density: 0.7
+        weight: 0.5
+    - model: anthracite-org/magnum-v2-12b
+      parameters:
+        density: 0.3
+        weight: 0.5
+
+merge_method: ties
+base_model: Trappu/Nemo-Picaro-12B
+parameters:
+    normalize: true
+    int8_mask: true
+dtype: bfloat16
+
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "Trappu/Magnum-Picaro-0.7-v2-12b"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Trappu__Magnum-Picaro-0.7-v2-12b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |21.42|
+|IFEval (0-Shot)    |30.03|
+|BBH (3-Shot)       |35.75|
+|MATH Lvl 5 (4-Shot)| 4.76|
+|GPQA (0-shot)      | 9.73|
+|MuSR (0-shot)      |19.56|
+|MMLU-PRO (5-shot)  |28.67|

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Trappu/Nemo-Picaro-fixed",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.42.4",
+  "unsloth_version": "2024.8",
+  "use_cache": false,
+  "vocab_size": 131072
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 24495564800}, "weight_map": {"lm_head.weight": "model-00001-of-00005.safetensors", "model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.safetensors"}}

output-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b58ef6fbe4dd3af8f747ee727951070dc90f82202d47c331f8db7a138549e66
+size 8159727372

output-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d6814c9af875b7d8cc431a09e1052ba2d7a0b5dab7721692f9f317431dfd01c
+size 528482400

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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}