NousResearch/Hermes-2-Pro-Mistral-7B-GGUF
Updated
•
9.6k
•
227
Jenish-23
Jenish-23
·
AI & ML interests
Personal and Study
Recent Activity
new activity
about 2 months ago
OpenGVLab/InternVL2_5-4B-AWQ:Is it possible to use this model with huggingface's transformers library?
liked
a model
10 months ago
NousResearch/Hermes-2-Pro-Mistral-7B-GGUF
liked
a model
10 months ago
NousResearch/Hermes-2-Pro-Mistral-7B
Organizations
None yet
Jenish-23's activity
Is it possible to use this model with huggingface's transformers library?
1
#2 opened about 2 months ago
by
Jenish-23
liked
3
models
10 months ago
liked
a
dataset
11 months ago
liked
5
models
11 months ago
Are there any examples or notebooks showing how to use AWQ in LORA fine-tuning a LLM? Or just use AWQ model from huggingface directly? I'm asking as neither the docs nor the Release notes explain anything.
reacted to
smangrul's
post with 👍
11 months ago
Post
🚨 New Release of 🤗PEFT!
1. New methods for merging LoRA weights. Refer this HF Post for more details: https://huggingface.co/posts/smangrul/850816632583824
2. AWQ and AQLM support for LoRA. You can now:
- Train adapters on top of 2-bit quantized models with AQLM
- Train adapters on top of powerful AWQ quantized models
Note for inference you can't merge the LoRA weights into the base model!
3. DoRA support: Enabling DoRA is as easy as adding
4. Improved documentation, particularly docs regarding PEFT LoRA+DeepSpeed and PEFT LoRA+FSDP! 📄 Check out the docs at https://huggingface.co/docs/peft/index.
5. Full Release Notes: https://github.com/huggingface/peft/releases/tag/v0.9.0
1. New methods for merging LoRA weights. Refer this HF Post for more details: https://huggingface.co/posts/smangrul/850816632583824
2. AWQ and AQLM support for LoRA. You can now:
- Train adapters on top of 2-bit quantized models with AQLM
- Train adapters on top of powerful AWQ quantized models
Note for inference you can't merge the LoRA weights into the base model!
3. DoRA support: Enabling DoRA is as easy as adding
use_dora=True to your LoraConfig. Find out more about this method here: https://arxiv.org/abs/2402.093534. Improved documentation, particularly docs regarding PEFT LoRA+DeepSpeed and PEFT LoRA+FSDP! 📄 Check out the docs at https://huggingface.co/docs/peft/index.
5. Full Release Notes: https://github.com/huggingface/peft/releases/tag/v0.9.0
-
- 5 replies
reacted to
akhaliq's
post with 👍
12 months ago
Post
MobileLLM
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (2402.14905)
paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a practical choice for mobile deployment. Contrary to prevailing belief emphasizing the pivotal role of data and parameter quantity in determining model quality, our investigation underscores the significance of model architecture for sub-billion scale LLMs. Leveraging deep and thin architectures, coupled with embedding sharing and grouped-query attention mechanisms, we establish a strong baseline network denoted as MobileLLM, which attains a remarkable 2.7%/4.3% accuracy boost over preceding 125M/350M state-of-the-art models. Additionally, we propose an immediate block-wise weight sharing approach with no increase in model size and only marginal latency overhead. The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0.7%/0.8% than MobileLLM 125M/350M. Moreover, MobileLLM model family shows significant improvements compared to previous sub-billion models on chat benchmarks, and demonstrates close correctness to LLaMA-v2 7B in API calling tasks, highlighting the capability of small models for common on-device use cases.
Optimizing Sub-billion Parameter Language Models for On-Device Use Cases
MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (2402.14905)
paper addresses the growing need for efficient large language models (LLMs) on mobile devices, driven by increasing cloud costs and latency concerns. We focus on designing top-quality LLMs with fewer than a billion parameters, a practical choice for mobile deployment. Contrary to prevailing belief emphasizing the pivotal role of data and parameter quantity in determining model quality, our investigation underscores the significance of model architecture for sub-billion scale LLMs. Leveraging deep and thin architectures, coupled with embedding sharing and grouped-query attention mechanisms, we establish a strong baseline network denoted as MobileLLM, which attains a remarkable 2.7%/4.3% accuracy boost over preceding 125M/350M state-of-the-art models. Additionally, we propose an immediate block-wise weight sharing approach with no increase in model size and only marginal latency overhead. The resultant models, denoted as MobileLLM-LS, demonstrate a further accuracy enhancement of 0.7%/0.8% than MobileLLM 125M/350M. Moreover, MobileLLM model family shows significant improvements compared to previous sub-billion models on chat benchmarks, and demonstrates close correctness to LLaMA-v2 7B in API calling tasks, highlighting the capability of small models for common on-device use cases.
commented
a
paper
12 months ago
upvoted
a
paper
12 months ago
reacted to
mrfakename's
post with 👍
12 months ago
Post
Hugging Face announces Cosmo 1B, a fully open sourced Phi competitor with an open sourced dataset. The dataset references various articles and textbooks as "seed data" to generate conversations. Licensed under the Apache 2.0 license. The dataset, dubbed "Cosmopedia," is published on the Hugging Face Hub under the Apache 2.0 license. It was generated using Mixtral 8x7B with various sources (AutoMathText, OpenStax, WikiHow, etc) as "seed data."
Model: HuggingFaceTB/cosmo-1b
Dataset: HuggingFaceTB/cosmopedia
Model: HuggingFaceTB/cosmo-1b
Dataset: HuggingFaceTB/cosmopedia
upvoted
a
paper
12 months ago
reacted to
akhaliq's
post with 👍
12 months ago
Post
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement (2402.14658)
The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter.
OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement (2402.14658)
The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpreter across key benchmarks such as HumanEval, MBPP, and their enhanced versions from EvalPlus reveals its exceptional performance. Notably, OpenCodeInterpreter-33B achieves an accuracy of 83.2 (76.4) on the average (and plus versions) of HumanEval and MBPP, closely rivaling GPT-4's 84.2 (76.2) and further elevates to 91.6 (84.6) with synthesized human feedback from GPT-4. OpenCodeInterpreter brings the gap between open-source code generation models and proprietary systems like GPT-4 Code Interpreter.
- 1 reply
liked
a
model
12 months ago
updated
a
collection
12 months ago