Quantization made by Richard Erkhov.
Draco-8x7B - GGUF
- Model creator: https://huggingface.co/Weyaxi/
- Original model: https://huggingface.co/Weyaxi/Draco-8x7B/
Name | Quant method | Size |
---|---|---|
Draco-8x7B.Q2_K.gguf | Q2_K | 16.12GB |
Draco-8x7B.IQ3_XS.gguf | IQ3_XS | 18.02GB |
Draco-8x7B.IQ3_S.gguf | IQ3_S | 19.03GB |
Draco-8x7B.Q3_K_S.gguf | Q3_K_S | 19.03GB |
Draco-8x7B.IQ3_M.gguf | IQ3_M | 19.96GB |
Draco-8x7B.Q3_K.gguf | Q3_K | 21.0GB |
Draco-8x7B.Q3_K_M.gguf | Q3_K_M | 21.0GB |
Draco-8x7B.Q3_K_L.gguf | Q3_K_L | 22.51GB |
Draco-8x7B.IQ4_XS.gguf | IQ4_XS | 23.63GB |
Draco-8x7B.Q4_0.gguf | Q4_0 | 24.63GB |
Draco-8x7B.IQ4_NL.gguf | IQ4_NL | 24.91GB |
Draco-8x7B.Q4_K_S.gguf | Q4_K_S | 24.91GB |
Draco-8x7B.Q4_K.gguf | Q4_K | 26.49GB |
Draco-8x7B.Q4_K_M.gguf | Q4_K_M | 26.49GB |
Draco-8x7B.Q4_1.gguf | Q4_1 | 27.32GB |
Draco-8x7B.Q5_0.gguf | Q5_0 | 30.02GB |
Draco-8x7B.Q5_K_S.gguf | Q5_K_S | 30.02GB |
Draco-8x7B.Q5_K.gguf | Q5_K | 30.95GB |
Draco-8x7B.Q5_K_M.gguf | Q5_K_M | 30.95GB |
Draco-8x7B.Q5_1.gguf | Q5_1 | 32.71GB |
Draco-8x7B.Q6_K.gguf | Q6_K | 35.74GB |
Draco-8x7B.Q8_0.gguf | Q8_0 | 46.22GB |
Original model description:
license: apache-2.0 tags: - moe - openchat - hermes - dolphin - bagel model-index: - name: Draco-8x7B 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: 65.02 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B 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: 85.24 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B 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: 64.96 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B 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: 62.65 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B 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: 80.66 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B 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: 66.79 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=PulsarAI/Draco-8x7B name: Open LLM Leaderboard
π« Draco-8x7B
This is the model for Draco-8x7B. I used this repo to make this MOE model.
This model's experts are not using any merged models.
π Other branches (Number of Experts Per Token)
Other branches that this repository contains differ only slightly (from a git diff perspective) in terms of the number of experts per token.
Usually, a higher value for the number of experts per token will result in better performance, but it may also lead to increased inference time.
Number of experts per token | Link of the branch |
---|---|
2 | Main |
3 | 3-experts-per-token |
4 | 4-experts-per-token |
6 | 6-experts-per-token |
8 | 8-experts-per-token |
π¬ Prompt Template(s):
This model includes many models, so providing only one prompt template is not enough. You can use and try these prompt templates and decide which works best for you.
Note: The current chat template in the tokenizer config is set to openchat-3.5-0106's chat template.
Note 2: It is also important to note that jondurbin/bagel-dpo-7b-v0.1 is using many prompt templates other than I provided. You can visit jondurbin/bagel-dpo-7b-v0.1 to learn more about this templates.
GPT4 Correct
Used in openchat/openchat-3.5-0106, beowolx/CodeNinja-1.0-OpenChat-7B
GPT4 Correct User: {user}<|end_of_turn|>GPT4 Correct Assistant: {asistant}<|end_of_turn|>
ChatML:
Used in teknium/OpenHermes-2.5-Mistral-7B, jondurbin/bagel-dpo-7b-v0.1, cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser, senseable/WestLake-7B-v2
<|im_start|>system
{system}<|im_end|>
<|im_start|>user
{user}<|im_end|>
<|im_start|>assistant
{asistant}<|im_end|>
Math Alpaca
Used in meta-math/MetaMath-Mistral-7B
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{instruction}
### Response: Let's think step by step.
π οΈ Yaml Config
See config
base_model: openchat/openchat-3.5-0106
gate_mode: hidden
dtype: bfloat16
experts:
- source_model: openchat/openchat-3.5-0106
positive_prompts: # General (Mistral finetune)
- "chat"
- "assistant"
- "tell me"
- "explain"
- source_model: teknium/OpenHermes-2.5-Mistral-7B
positive_prompts: # General (Mistral finetune)
- "interact"
- "converse"
- "respond"
- "express"
- source_model: jondurbin/bagel-dpo-7b-v0.1
positive_prompts: # Science (Mistral finetune)
- "science"
- "biology"
- "chemistry"
- "physics"
- "Newton's laws"
- "scientific method"
- "periodic table"
- "photosynthesis process"
- source_model: meta-math/MetaMath-Mistral-7B
positive_prompts: # Math (Mistral finetune)
- "reason"
- "math"
- "mathematics"
- "solve"
- "count"
- source_model: cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
positive_prompts: # Uncensored (Mistral finetune)
- "dolphin"
- "uncensored"
- "unbiased"
- "unfiltered"
- "unrestricted"
- "offensive"
- source_model: beowolx/CodeNinja-1.0-OpenChat-7B
positive_prompts: # Code (openchat-3.5-1210 finetune)
- "code"
- "script"
- "python"
- "javascript"
- "programming"
- "algorithm"
- source_model: senseable/WestLake-7B-v2
positive_prompts: # Roleplay (Unknown finetune)
- "storywriting"
- "write"
- "scene"
- "story"
- "character"
- "act as"
- "you are"
- source_model: snorkelai/Snorkel-Mistral-PairRM-DPO
positive_prompts: # Question Answering (? Mistral-7B-Instruct-v0.2 finetune ?)
- "what happens"
- "what is"
- "what can"
- "why"
- "who"
- "can a"
π Quantizationed versions
Quantizationed versions of this model is available thanks to TheBloke.
GPTQ
GGUF
AWQ
If you would like to support me:
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 70.89 |
AI2 Reasoning Challenge (25-Shot) | 65.02 |
HellaSwag (10-Shot) | 85.24 |
MMLU (5-Shot) | 64.96 |
TruthfulQA (0-shot) | 62.65 |
Winogrande (5-shot) | 80.66 |
GSM8k (5-shot) | 66.79 |
- Downloads last month
- 216