You can deploy this model and start earning money today!

RichardErkhov/
M4-ai_-_Orca-2.0-Tau-1.8B-gguf

Name: M4-ai_-_Orca-2.0-Tau-1.8B-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Orca-2.0-Tau-1.8B - GGUF

Model creator: https://huggingface.co/M4-ai/
Original model: https://huggingface.co/M4-ai/Orca-2.0-Tau-1.8B/

Name	Quant method	Size
Orca-2.0-Tau-1.8B.Q2_K.gguf	Q2_K	0.79GB
Orca-2.0-Tau-1.8B.Q3_K_S.gguf	Q3_K_S	0.89GB
Orca-2.0-Tau-1.8B.Q3_K.gguf	Q3_K	0.95GB
Orca-2.0-Tau-1.8B.Q3_K_M.gguf	Q3_K_M	0.95GB
Orca-2.0-Tau-1.8B.Q3_K_L.gguf	Q3_K_L	0.98GB
Orca-2.0-Tau-1.8B.IQ4_XS.gguf	IQ4_XS	1.01GB
Orca-2.0-Tau-1.8B.Q4_0.gguf	Q4_0	1.04GB
Orca-2.0-Tau-1.8B.IQ4_NL.gguf	IQ4_NL	1.05GB
Orca-2.0-Tau-1.8B.Q4_K_S.gguf	Q4_K_S	1.08GB
Orca-2.0-Tau-1.8B.Q4_K.gguf	Q4_K	1.13GB
Orca-2.0-Tau-1.8B.Q4_K_M.gguf	Q4_K_M	1.13GB
Orca-2.0-Tau-1.8B.Q4_1.gguf	Q4_1	1.13GB
Orca-2.0-Tau-1.8B.Q5_0.gguf	Q5_0	1.22GB
Orca-2.0-Tau-1.8B.Q5_K_S.gguf	Q5_K_S	1.24GB
Orca-2.0-Tau-1.8B.Q5_K.gguf	Q5_K	1.28GB
Orca-2.0-Tau-1.8B.Q5_K_M.gguf	Q5_K_M	1.28GB
Orca-2.0-Tau-1.8B.Q5_1.gguf	Q5_1	1.31GB
Orca-2.0-Tau-1.8B.Q6_K.gguf	Q6_K	1.47GB
Orca-2.0-Tau-1.8B.Q8_0.gguf	Q8_0	1.82GB

Original model description:

language:

en license: other library_name: transformers datasets:
Open-Orca/SlimOrca
m-a-p/Code-Feedback
MaziyarPanahi/WizardLM_evol_instruct_V2_196k
camel-ai/math
camel-ai/physics
camel-ai/biology
camel-ai/chemistry
LDJnr/Capybara
jondurbin/airoboros-3.2
microsoft/orca-math-word-problems-200k inference: parameters: do_sample: true temperature: 0.8 top_p: 0.95 top_k: 40 max_new_tokens: 250 repetition_penalty: 1.1 model-index:
name: Orca-2.0-Tau-1.8B 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: 37.12 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B 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: 61.13 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B 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: 45.27 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B 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: 39.1 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B 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: 59.59 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B 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: 28.96 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=M4-ai/Orca-2.0-Tau-1.8B name: Open LLM Leaderboard

Orca-2.0-Tau-1.8B

We fine-tuned tau-1.8B on a high quality mix for general-purpose assistants. A DPO version of this will be released soon. We use the ChatML prompt format.

Model Details

Model Description

This model has capabilities in math, coding, writing, and more. We fine-tuned it using a high quality mix for general-purpose assistants.

Developed by: M4-ai
Language(s) (NLP): English and maybe Chinese
License: tongyi-qianwen license
Finetuned from model: tau-1.8B

Uses

General purpose assistant, question answering, chain-of-thought, etc..

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Evaluation

Coming soon

Training Details

Training Data

Open-Orca/SlimOrca
m-a-p/Code-Feedback
MaziyarPanahi/WizardLM_evol_instruct_V2_196k
camel-ai/math
camel-ai/physics
camel-ai/biology
camel-ai/chemistry
LDJnr/Capybara
jondurbin/airoboros-3.2
microsoft/orca-math-word-problems-200k

Evaluations

Tasks	Version	Filter	Metric	Value		Stderr
agieval_nous	N/A	none	acc	0.2537	±	0.0086
		none	acc_norm	0.2474	±	0.0085
- agieval_aqua_rat	1	none	acc	0.2283	±	0.0264
		none	acc_norm	0.2441	±	0.0270
- agieval_logiqa_en	1	none	acc	0.2750	±	0.0175
		none	acc_norm	0.3164	±	0.0182
- agieval_lsat_ar	1	none	acc	0.2087	±	0.0269
		none	acc_norm	0.1739	±	0.0250
- agieval_lsat_lr	1	none	acc	0.1843	±	0.0172
		none	acc_norm	0.2353	±	0.0188
- agieval_lsat_rc	1	none	acc	0.2602	±	0.0268
		none	acc_norm	0.1784	±	0.0234
- agieval_sat_en	1	none	acc	0.3544	±	0.0334
		none	acc_norm	0.2961	±	0.0319
- agieval_sat_en_without_passage	1	none	acc	0.3107	±	0.0323
		none	acc_norm	0.2282	±	0.0293
- agieval_sat_math	1	none	acc	0.2727	±	0.0301
		none	acc_norm	0.2091	±	0.0275
truthfulqa_mc2	2	none	acc	0.3923	±	0.0139

Training Hyperparameters

Training regime: bf16 non-mixed precision

Technical Specifications

Hardware

We used 8 Kaggle TPUs, and we trained at a global batch size of 128 and sequence length of 2048.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	45.20
AI2 Reasoning Challenge (25-Shot)	37.12
HellaSwag (10-Shot)	61.13
MMLU (5-Shot)	45.27
TruthfulQA (0-shot)	39.10
Winogrande (5-shot)	59.59
GSM8k (5-shot)	28.96

RichardErkhov/M4-ai_-_Orca-2.0-Tau-1.8B-gguf