初始化项目，由ModelHub XC社区提供模型

Model: indischepartij/TinyUltra-4x1.1B-Base-Alpha Source: Original Platform
2026-05-10 07:25:02 +08:00
commit a6c7d25257
13 changed files with 93868 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 +1,255 @@
+---
+license: cc-by-nc-4.0
+tags:
+- moe
+- merge
+- mergekit
+model-index:
+- name: TinyUltra-4x1.1B-Base-Alpha
+  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: 34.9
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      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: 61.42
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      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: 25.42
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      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: 37.59
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      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: 65.75
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      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: 2.58
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=indischepartij/TinyUltra-4x1.1B-Base-Alpha
+      name: Open LLM Leaderboard
+widget:
+  - example_title: Pirate!
+    messages:
+      - role: system
+        content: You are a pirate chatbot who always responds with Arr!
+      - role: user
+        content: "There's a llama on my lawn, how can I get rid of him?"
+    output:
+      text: >-
+        Arr! 'Tis a puzzlin' matter, me hearty! A llama on yer lawn be a rare
+        sight, but I've got a plan that might help ye get rid of 'im. Ye'll need
+        to gather some carrots and hay, and then lure the llama away with the
+        promise of a tasty treat. Once he's gone, ye can clean up yer lawn and
+        enjoy the peace and quiet once again. But beware, me hearty, for there
+        may be more llamas where that one came from! Arr!
+---
+
+![image/jpeg](https://i.imgur.com/rx3ckCc.jpeg)
+
+# TinyUltra-4x1.1B-Base-Alpha
+
+TinyUltra-4x1.1B-Base-Alpha is a Mixure of Experts (MoE) made with the following models using MergeKit:
+* [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0)
+* [vihangd/DopeyTinyLlama-1.1B-v1](https://huggingface.co/vihangd/DopeyTinyLlama-1.1B-v1)
+* [cognitivecomputations/TinyDolphin-2.8.1-1.1b](https://huggingface.co/cognitivecomputations/TinyDolphin-2.8.1-1.1b)
+* [Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test](https://huggingface.co/Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test)
+
+
+# Modelfile/Prompt format
+```markdown
+SYSTEM You are a TinyUltra, helpful and lovely AI assistant.
+
+TEMPLATE <|system|> {{ .System }}</s> <|user|> {{ .Prompt }}</s> <|assistant|>
+
+PARAMETER stop <|system|>
+PARAMETER stop <|user|>
+PARAMETER stop <|assistant|>
+PARAMETER stop </s>
+```
+
+## 🧩 Configuration
+
+```yaml
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    positive_prompts:
+    - "Help me debug this code."
+    - "Rewrite this function in Python."
+    - "Optimize this C# script."
+    - "Implement this feature using JavaScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "Assist me with writing a program that"
+  - source_model: vihangd/DopeyTinyLlama-1.1B-v1
+    positive_prompts:
+    - "How do you"
+    - "Explain the concept of"
+    - "Give an overview of"
+    - "Compare and contrast between"
+    - "Provide information about"
+    - "Help me understand"
+    - "Summarize"
+    - "Make a recommendation on"
+    - "Answer this question"
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts:
+    - "Write a program to solve this problem"
+    - "Modify this function to improve its performance"
+    - "Refactor this code to enhance readability"
+    - "Create a custom function for this specific use case"
+    - "Optimize this algorithm to reduce computational complexity"
+    - "Implement this feature by extending existing codebase"
+    - "Integrate this API call into the application"
+    - "Help me troubleshoot and fix this bug"
+    - "Review and test this code snippet before deployment"
+    - "Analyze this error log to identify potential issues"
+    - "Generate a set of unit tests for this module"
+    - "Evaluate different approaches to solving this problem"
+    - "Do a web search for"
+    - "Use the plugin to"
+  - source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+    positive_prompts:
+    - "add these numbers"
+    - "whats 2+2"
+    - "subtraction"
+    - "division"
+    - "multiplication"
+    - "addition"
+    - "I need help with a math problem"
+    - "Solve for x"
+    - "Add these two numbers together: 4 + 3 = 7"
+    - "Multiply 5 by 6: 5 * 6 = 30"
+    - "Divide 8 by 2: 8 / 2 = 4"
+    - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
+    - "Calculate the square root of 16: sqrt(16) = 4"
+    - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
+    - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
+    - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
+    - "Graph the line y = 2x + 3"
+    - "Approximate pi to three decimal places: 3.142"
+    - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
+    - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
+    - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
+    - "Solve the system of equations Ax = b: x = [-5, 10]"
+    - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
+```
+
+## 💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "gmonsoon/TinyUltra-4x1.1B-Base-Alpha"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+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"])
+```
+GGUF: https://huggingface.co/indischepartij/TinyUltra-4x1.1B-Base-Alpha-GGUF
+# [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_indischepartij__TinyUltra-4x1.1B-Base-Alpha)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |37.94|
+|AI2 Reasoning Challenge (25-Shot)|34.90|
+|HellaSwag (10-Shot)              |61.42|
+|MMLU (5-Shot)                    |25.42|
+|TruthfulQA (0-shot)              |37.59|
+|Winogrande (5-shot)              |65.75|
+|GSM8k (5-shot)                   | 2.58|
+
--- a/config.json
+++ b/config.json
@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "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": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}
--- a/mergekit_moe_config.yml
+++ b/mergekit_moe_config.yml
@@ -0,0 +1,65 @@
+
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+gate_mode: hidden
+dtype: float16
+experts:
+  - source_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+    positive_prompts:
+    - "Help me debug this code."
+    - "Rewrite this function in Python."
+    - "Optimize this C# script."
+    - "Implement this feature using JavaScript."
+    - "Convert this HTML structure into a more efficient design."
+    - "Assist me with writing a program that"
+  - source_model: vihangd/DopeyTinyLlama-1.1B-v1
+    positive_prompts:
+    - "How do you"
+    - "Explain the concept of"
+    - "Give an overview of"
+    - "Compare and contrast between"
+    - "Provide information about"
+    - "Help me understand"
+    - "Summarize"
+    - "Make a recommendation on"
+    - "Answer this question"
+  - source_model: cognitivecomputations/TinyDolphin-2.8.1-1.1b
+    positive_prompts:
+    - "Write a program to solve this problem"
+    - "Modify this function to improve its performance"
+    - "Refactor this code to enhance readability"
+    - "Create a custom function for this specific use case"
+    - "Optimize this algorithm to reduce computational complexity"
+    - "Implement this feature by extending existing codebase"
+    - "Integrate this API call into the application"
+    - "Help me troubleshoot and fix this bug"
+    - "Review and test this code snippet before deployment"
+    - "Analyze this error log to identify potential issues"
+    - "Generate a set of unit tests for this module"
+    - "Evaluate different approaches to solving this problem"
+    - "Do a web search for"
+    - "Use the plugin to"
+  - source_model: Josephgflowers/Tinyllama-Cinder-1.3B-Reason-Test
+    positive_prompts:
+    - "add these numbers"
+    - "whats 2+2"
+    - "subtraction"
+    - "division"
+    - "multiplication"
+    - "addition"
+    - "I need help with a math problem"
+    - "Solve for x"
+    - "Add these two numbers together: 4 + 3 = 7"
+    - "Multiply 5 by 6: 5 * 6 = 30"
+    - "Divide 8 by 2: 8 / 2 = 4"
+    - "Find the remainder when 9 is divided by 3: 9 % 3 = 0"
+    - "Calculate the square root of 16: sqrt(16) = 4"
+    - "Simplify the expression (a+b)/(c-d): (a+b)/(c-d)"
+    - "Factor out the common factor of 2 from 4x + 6y: 2(2x + 3y)"
+    - "Solve for x in the equation 3x - 7 = 2x + 5: x = 12"
+    - "Graph the line y = 2x + 3"
+    - "Approximate pi to three decimal places: 3.142"
+    - "Find the derivative of f(x) = sin(x): f'(x) = cos(x)"
+    - "Integrate g(x) = x^2 over the interval [0, 1]: g(1) - g(0) = 1/3"
+    - "Calculate the determinant of the matrix A = [[2, 3], [4, 5]]: det(A) = 2*5 - 3*4 = -2"
+    - "Solve the system of equations Ax = b: x = [-5, 10]"
+    - "Calculate the sum of the first n natural numbers using the formula Sn = n*(n+1)/2: sum(n=1 to 5) = 15"
--- a/model-00001-of-00004.safetensors
+++ b/model-00001-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d38f31ef61bf68f90303925662e940e7aaa1c0fd144c96c7549865c9790d1c1
+size 1992400992
--- a/model-00002-of-00004.safetensors
+++ b/model-00002-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2045a530438abd30ab4c899bca713086bc48e5e66b28e81f1533826b68e6da8
+size 1983916872
--- a/model-00003-of-00004.safetensors
+++ b/model-00003-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a3e4dbec96346b449a29529514bda3ba68c6c1988ef0a56d1018a44cd77eca4
+size 1983916872
--- a/model-00004-of-00004.safetensors
+++ b/model-00004-of-00004.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd9b26580bb02a40ab88a2d3ca7d4a58c4b2225a47db42246d31e4e58c7248e6
+size 807871392
--- a/model.safetensors.index.json
+++ b/model.safetensors.index.json
--- a/special_tokens_map.json
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "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": "<s>",
+  "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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}