初始化项目，由ModelHub XC社区提供模型

Model: andrijdavid/tinyllama-dare Source: Original Platform
2026-06-15 06:17:17 +08:00
commit e1e71ef03d
10 changed files with 93690 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
--- a/README.md
+++ b/README.md
@@ -0,0 +1,157 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- merge
+- llama
+base_model:
+- aihub-app/zyte-1B
+- TinyLlama/TinyLlama-1.1B-Chat-v1.0
+- BEE-spoke-data/TinyLlama-3T-1.1bee
+- sreeramajay/TinyLlama-1.1B-orca-v1.0
+- vihangd/DopeyTinyLlama-1.1B-v1
+- kevin009/lamatama
+model-index:
+- name: tinyllama-dare
+  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: 37.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      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: 62.78
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      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: 25.2
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      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: 39.01
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      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: 65.9
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      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: 1.67
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=andrijdavid/tinyllama-dare
+      name: Open LLM Leaderboard
+---
+# TinyLlama Merge
+
+### Models Merged
+
+The following models were included in the merge:
+* [aihub-app/zyte-1B](https://huggingface.co/aihub-app/zyte-1B)
+* [BEE-spoke-data/TinyLlama-3T-1.1bee](https://huggingface.co/BEE-spoke-data/TinyLlama-3T-1.1bee)
+* [sreeramajay/TinyLlama-1.1B-orca-v1.0](https://huggingface.co/sreeramajay/TinyLlama-1.1B-orca-v1.0)
+* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
+* [kevin009/lamatama](https://huggingface.co/kevin009/lamatama)
+
+# Disclaimer 
+
+The users of this model (hereinafter referred to as "the Model") should be aware of the following points prior to using the Model:
+
+* Factual Inaccuracy: The Model has been trained on a diverse set of data sources. However, it may occasionally generate outputs that contain factual inaccuracies. Users are advised to verify the factual correctness of the information provided by the Model, especially when using it for critical applications.
+
+* Potential Biases: Despite efforts to ensure fairness and neutrality, the Model may still exhibit biases inherent in the training data. These biases do not reflect the views or intentions of the developers. Users should be cautious of these potential biases, especially when using the Model in contexts where fairness and impartiality are crucial.
+
+* Hallucination: The Model might generate content that is not grounded in reality, commonly referred to as "hallucinations." This is a known limitation of language models and should be considered when interpreting the Model's outputs.
+
+* Inappropriate Content: While measures have been taken to minimize the risk, the Model might still generate content that could be deemed offensive, inappropriate, or not suitable for all audiences. We advise users to exercise discretion and consider the context of use.
+
+ Use at Your Own Risk: The Model is provided "as is," and the developers make no representations or warranties of any kind concerning the Model's performance or suitability for any particular purpose. The user assumes full responsibility and risk of loss resulting from using the Model.
+
+By using the Model, users acknowledge and agree to the terms stated in this disclaimer. This disclaimer is subject to change without notice, and the latest version can be found on the Model's Hugging Face page.
+# [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_andrijdavid__tinyllama-dare)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |38.64|
+|AI2 Reasoning Challenge (25-Shot)|37.29|
+|HellaSwag (10-Shot)              |62.78|
+|MMLU (5-Shot)                    |25.20|
+|TruthfulQA (0-shot)              |39.01|
+|Winogrande (5-shot)              |65.90|
+|GSM8k (5-shot)                   | 1.67|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "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": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/model-00001-of-00002.safetensors
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee9b28135e65e6d9587f734ffa852d66aaccc74e0beb3d33cd0f9c5dca9e9e70
+size 1980953936
--- a/model-00002-of-00002.safetensors
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615fdfd00e71a1d3b4e858c13761b0ad4528d9eae4616fe5b36570acc805e703
+size 219165920
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/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
+  }
+}
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer.model
+++ b/tokenizer.model
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,40 @@
+{
+  "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>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}