初始化项目，由ModelHub XC社区提供模型

Model: Aryanne/TinyllamaMix-1.1B
Source: Original Platform

.gitattributes

@@ -0,0 +1,37 @@
+*.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
+f16.gguf filter=lfs diff=lfs merge=lfs -text
+q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,168 @@
+---
+license: apache-2.0
+inference:
+  parameters:
+    temperature: 0.79
+widget:
+- messages:
+  - role: user
+    content: How to gain more money?
+model-index:
+- name: TinyllamaMix-1.1B
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 31.48
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 48.39
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.05
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 33.45
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 58.48
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 1.06
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Aryanne/TinyllamaMix-1.1B
+      name: Open LLM Leaderboard
+---
+
+This a TinyLlama mix merge, experimental, using a custom merge method.
+Should be better at RP.
+
+```yaml
+merge_method: task_swapping
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
+models:
+  - model: cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser
+    parameters:
+      weight: 0.75
+      diagonal_offset: 5
+  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    parameters:
+      weight: 0.85
+      diagonal_offset: 17
+      invert_offset: True
+dtype: bfloat16
+name: bye
+---
+merge_method: task_swapping
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
+models:
+  - model: vihangd/DopeyTinyLlama-1.1B-v1
+    parameters:
+      weight: 0.8
+      diagonal_offset: 3
+      invert_offset: False
+dtype: bfloat16
+name: hello
+---
+merge_method: task_arithmetic
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
+models:
+  - model: hello
+    parameters:
+      weight: 0.66
+  - model: bye+Anarchist/PIPPA_LORA_TinyLlama
+    parameters:
+      weight: 0.5
+dtype: bfloat16
+```
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_Aryanne__TinyllamaMix-1.1B)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |32.99|
+|AI2 Reasoning Challenge (25-Shot)|31.48|
+|HellaSwag (10-Shot)              |48.39|
+|MMLU (5-Shot)                    |25.05|
+|TruthfulQA (0-shot)              |33.45|
+|Winogrande (5-shot)              |58.48|
+|GSM8k (5-shot)                   | 1.06|
+

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Doctor-Shotgun/TinyLlama-1.1B-32k",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 32768,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b18997e938d7b268172ea8c02810518205970cd1ad1ff1a031840e1d3f058ff
+size 2201016800

mergekit_config.yml

@@ -0,0 +1,36 @@
+merge_method: task_swapping
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
+models:
+  - model: cognitivecomputations/TinyDolphin-2.8.2-1.1b-laser
+    parameters:
+      weight: 0.75
+      diagonal_offset: 5
+  - model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    parameters:
+      weight: 0.85
+      diagonal_offset: 17
+      invert_offset: True
+dtype: bfloat16
+name: bye
+---
+merge_method: task_swapping
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k-Instruct
+models:
+  - model: vihangd/DopeyTinyLlama-1.1B-v1
+    parameters:
+      weight: 0.8
+      diagonal_offset: 3
+      invert_offset: False
+dtype: bfloat16
+name: hello
+---
+merge_method: task_arithmetic
+base_model: Doctor-Shotgun/TinyLlama-1.1B-32k
+models:
+  - model: hello
+    parameters:
+      weight: 0.66
+  - model: bye+Anarchist/PIPPA_LORA_TinyLlama
+    parameters:
+      weight: 0.5
+dtype: bfloat16

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fc712f78d2ceebc3d494812eb53a29c773770af116660f3e87cfde426ecbca
+size 1980953936

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eece21b0900f8ab85000620b0002f9509599606620093ea17ef8671113751af0
+size 219165920

q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73a3375c8956356b098bced0b51cc6db17025b35512f12cfd07574ac6bc8312b
+size 1169807872

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}