You can deploy this model and start earning money today!

RichardErkhov/
WebraftAI_-_synapsellm-7b-mistral-v0.5-preview2-gguf

Name: WebraftAI_-_synapsellm-7b-mistral-v0.5-preview2-gguf
Availability: InStock

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

synapsellm-7b-mistral-v0.5-preview2 - GGUF

Model creator: https://huggingface.co/WebraftAI/
Original model: https://huggingface.co/WebraftAI/synapsellm-7b-mistral-v0.5-preview2/

Name	Quant method	Size
synapsellm-7b-mistral-v0.5-preview2.Q2_K.gguf	Q2_K	2.53GB
synapsellm-7b-mistral-v0.5-preview2.IQ3_XS.gguf	IQ3_XS	2.81GB
synapsellm-7b-mistral-v0.5-preview2.IQ3_S.gguf	IQ3_S	2.96GB
synapsellm-7b-mistral-v0.5-preview2.Q3_K_S.gguf	Q3_K_S	2.95GB
synapsellm-7b-mistral-v0.5-preview2.IQ3_M.gguf	IQ3_M	3.06GB
synapsellm-7b-mistral-v0.5-preview2.Q3_K.gguf	Q3_K	3.28GB
synapsellm-7b-mistral-v0.5-preview2.Q3_K_M.gguf	Q3_K_M	3.28GB
synapsellm-7b-mistral-v0.5-preview2.Q3_K_L.gguf	Q3_K_L	3.56GB
synapsellm-7b-mistral-v0.5-preview2.IQ4_XS.gguf	IQ4_XS	3.67GB
synapsellm-7b-mistral-v0.5-preview2.Q4_0.gguf	Q4_0	3.83GB
synapsellm-7b-mistral-v0.5-preview2.IQ4_NL.gguf	IQ4_NL	3.87GB
synapsellm-7b-mistral-v0.5-preview2.Q4_K_S.gguf	Q4_K_S	3.86GB
synapsellm-7b-mistral-v0.5-preview2.Q4_K.gguf	Q4_K	4.07GB
synapsellm-7b-mistral-v0.5-preview2.Q4_K_M.gguf	Q4_K_M	4.07GB
synapsellm-7b-mistral-v0.5-preview2.Q4_1.gguf	Q4_1	4.24GB
synapsellm-7b-mistral-v0.5-preview2.Q5_0.gguf	Q5_0	4.65GB
synapsellm-7b-mistral-v0.5-preview2.Q5_K_S.gguf	Q5_K_S	4.65GB
synapsellm-7b-mistral-v0.5-preview2.Q5_K.gguf	Q5_K	4.78GB
synapsellm-7b-mistral-v0.5-preview2.Q5_K_M.gguf	Q5_K_M	4.78GB
synapsellm-7b-mistral-v0.5-preview2.Q5_1.gguf	Q5_1	5.07GB
synapsellm-7b-mistral-v0.5-preview2.Q6_K.gguf	Q6_K	5.53GB
synapsellm-7b-mistral-v0.5-preview2.Q8_0.gguf	Q8_0	7.17GB

Original model description:

language:

en license: apache-2.0 library_name: transformers tags:
code model-index:
name: synapsellm-7b-mistral-v0.5-preview2 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: 52.22 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 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: 75.54 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 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: 51.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 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: 55.47 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 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: 73.09 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 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: 27.6 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=WebraftAI/synapsellm-7b-mistral-v0.5-preview2 name: Open LLM Leaderboard

SynapseLLM:

SynapseLLM, a significant achievement by WebraftAI, represents a series of large language AI models designed to create robust, generalized, and decentralized information systems. This repository specifically houses the SynapseLLM finetuned version of Mistral. The finetuning process is conducted on a custom dataset, albeit limited in scope, focusing on code and normal question-answering scenarios. This adaptation showcases the model's versatility and applicability within specific domains, contributing to the broader landscape of AI advancements.

Model Details

SynapseLLM:

Parameters: 7B
Learning rate: 2e-4
Adapter used: Qlora
Precision: float16
Batch size: 32
Maximum gradient normal: 0.3
Optimizer: paged_adamw_32bit
Warmup Ratio: 0.03
Step(s) (trained): 2000
Epoch(s) (trained): 1

Model Description

This is a 7b parameter, decoder only transformer based finetuned model on Chat Q/A and Code instructions. It's a preview finetune on Mistral 7B v0.1 on a sample dataset of 1.54M rows comprising of 361k Maths Instruct Q/A, 143k GPT-3.5 Q/A, 140k General Code, 63k Python code, and 900k General Q/A (Through GPT-4) [Each row contains one instruction and one response]. This is a full model merged and compiled with trained adapters, so you can easily load this through transformers library.

Developed by: WebraftAI
Funded by: Webraft Cloud
Shared by: WebraftAI
Model type: Decoder-only Transformer
Language(s): English Only
License: Apache 2.0
Finetuned from model: Mistral-7b-v0.1

Prompt format:

This model follows the same prompt format as mistral instruct 7b v0.1 .The sample prompt is still given below:

text

<s>[INST] Hello, how are you? [/INST]

Example Code:

Here's an example code using transformers library provided by HF.

python

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WebraftAI/synapsellm-7b-mistral-v0.5-preview2")
model = AutoModelForCausalLM.from_pretrained("WebraftAI/synapsellm-7b-mistral-v0.5-preview2")

prompt= "<s>[INST] Hello!  [/INST] "

device = "cuda"

model_inputs = tokenizer([prompt], return_tensors="pt").to(device)
model.to(device)

generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
print(tokenizer.batch_decode(generated_ids)[0])

Model Bias:

This model has some bias areas, discussed below:

Model might output factually incorrect information.
Model does not follow system prompts.
Model does not have any kind of memory, researchers can experiment feeding memory.
Model is trained on different datas, so it can bias information or exclaim itself as gpt model.

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	55.93
AI2 Reasoning Challenge (25-Shot)	52.22
HellaSwag (10-Shot)	75.54
MMLU (5-Shot)	51.64
TruthfulQA (0-shot)	55.47
Winogrande (5-shot)	73.09
GSM8k (5-shot)	27.60

RichardErkhov/WebraftAI_-_synapsellm-7b-mistral-v0.5-preview2-gguf