mistralai/Mistral-7B-v0.3
Text Generation
β’
Updated
β’
119k
β’
450
Nicolay Rusnachenko
nicolay-r
AI & ML interests
Information Retrievalγ»Medical Multimodal NLP (πΌ+π) Research Fellow @BU_Researchγ»software developer http://arekit.ioγ»PhD in NLP
Recent Activity
liked
a model
about 13 hours ago
mistralai/Mistral-7B-v0.3
liked
a model
about 13 hours ago
mistralai/Mistral-Small-3.1-24B-Instruct-2503
posted
an
update
4 days ago
π’ Several weeks ago Microsoft announced Phi-4. My most-recent list of LLM models have had only wrapper for Phi-2, so it was time to update! With this post, happy to share that Phi-4 wrapper is now available at nlp-thirdgate for adopting Chain-of-Thought reasoning:
π€ https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_phi4.py
π https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_phi4.py
Findings on adaptation: I was able to reproduce only the pipeline based model launching. This version is for textual llm only. Microsoft also released multimodal Phi-4 which is out of scope of this wrapper.
π nlp-thirdgate: https://lnkd.in/ef-wBnNn
Organizations
None yet
nicolay-r's activity
liked
2
models
about 13 hours ago
posted
an
update
4 days ago
Post
580
π’ Several weeks ago Microsoft announced Phi-4. My most-recent list of LLM models have had only wrapper for Phi-2, so it was time to update! With this post, happy to share that Phi-4 wrapper is now available at nlp-thirdgate for adopting Chain-of-Thought reasoning:
π€ https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_phi4.py
π https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_phi4.py
Findings on adaptation: I was able to reproduce only the pipeline based model launching. This version is for textual llm only. Microsoft also released multimodal Phi-4 which is out of scope of this wrapper.
π nlp-thirdgate: https://lnkd.in/ef-wBnNn
π€ https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_phi4.py
π https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_phi4.py
Findings on adaptation: I was able to reproduce only the pipeline based model launching. This version is for textual llm only. Microsoft also released multimodal Phi-4 which is out of scope of this wrapper.
π nlp-thirdgate: https://lnkd.in/ef-wBnNn
posted
an
update
5 days ago
Post
1089
π’ Delighted to announce the updated version of the no-string framework for chain-of-thought application over JSONL/CSV data:
https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.2
π§ Fixes:
- Fixed issues with batching mode
- Fixed problem with parsing and passing args in shell mode
β οΈ Limitation: bathing mode is still available only via API.
π Quick Start with Gemma-3 in batching mode: https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb
https://github.com/nicolay-r/bulk-chain/releases/tag/0.25.2
π§ Fixes:
- Fixed issues with batching mode
- Fixed problem with parsing and passing args in shell mode
β οΈ Limitation: bathing mode is still available only via API.
π Quick Start with Gemma-3 in batching mode: https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb
replied to
their
post
5 days ago
The important comment is to use the very latest version of the bulk-chain from github which fixes the bug for double-inference in batching.
posted
an
update
6 days ago
Post
1535
π’ With the recent release of Gemma-3, If you interested to play with textual chain-of-though, the notebook below is a wrapper over the the model (native transformers inference API) for passing the predefined schema of promps in batching mode.
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb
Limitation: schema supports texts only (for now), while gemma-3 is a text+image to text.
Model: google/gemma-3-1b-it
Provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_gemma3.py
https://github.com/nicolay-r/nlp-thirdgate/blob/master/tutorials/llm_gemma_3.ipynb
Limitation: schema supports texts only (for now), while gemma-3 is a text+image to text.
Model: google/gemma-3-1b-it
Provider: https://github.com/nicolay-r/nlp-thirdgate/blob/master/llm/transformers_gemma3.py
-
- 1 reply
liked
3
models
7 days ago
reacted to
onekq's
post with π
7 days ago
Post
1393
The performance of deepseek-r1-distill-qwen-32b is abysmal. I know Qwen instruct (not coder) is quite poor on coding. As such, I have low expectation on other R1 repro works also based on Qwen instruct too.
onekq-ai/r1-reproduction-works-67a93f2fb8b21202c9eedf0b
This makes it particularly mysterious what went into QwQ-32B? Why did it work so well? Was it trained from scratch? Anyone has insights about this?
onekq-ai/WebApp1K-models-leaderboard
This makes it particularly mysterious what went into QwQ-32B? Why did it work so well? Was it trained from scratch? Anyone has insights about this?
onekq-ai/WebApp1K-models-leaderboard
- 5 replies
@ritvik77 , sounds good on your plans! Meanwhile looking forward to adapt 7B version to experiment in radiology domain. Happy to read more on that and once and if it gets to the paper, so I can populate the survey of the related advances.
@ritvik77 , excited to run into this! Is the paper and studies behind it on arxiv or elsewhere?
reacted to
ritvik77's
post with π₯
8 days ago
Post
1514
Try it out:
ritvik77/Medical_Doctor_AI_LoRA-Mistral-7B-Instruct_FullModel
π©Ί Medical Diagnosis AI Model - Powered by Mistral-7B & LoRA π
πΉ Model Overview:
Base Model: Mistral-7B (7.7 billion parameters)
Fine-Tuning Method: LoRA (Low-Rank Adaptation)
Quantization: bnb_4bit (reduces memory footprint while retaining performance)
πΉ Parameter Details:
Original Mistral-7B Parameters: 7.7 billion
LoRA Fine-Tuned Parameters: 4.48% of total model parameters (340 million) Final Merged Model Size (bnb_4bit Quantized): ~4.5GB
This can help you in making a AI agent for healthcare, if you need to finetune it for JSON function/tool calling format you can use some medical function calling dataset to again fine fine tine on it.
π©Ί Medical Diagnosis AI Model - Powered by Mistral-7B & LoRA π
πΉ Model Overview:
Base Model: Mistral-7B (7.7 billion parameters)
Fine-Tuning Method: LoRA (Low-Rank Adaptation)
Quantization: bnb_4bit (reduces memory footprint while retaining performance)
πΉ Parameter Details:
Original Mistral-7B Parameters: 7.7 billion
LoRA Fine-Tuned Parameters: 4.48% of total model parameters (340 million) Final Merged Model Size (bnb_4bit Quantized): ~4.5GB
This can help you in making a AI agent for healthcare, if you need to finetune it for JSON function/tool calling format you can use some medical function calling dataset to again fine fine tine on it.
-
- 3 replies
liked
a
model
8 days ago
how to perform batch inference for llama-3.2-1B-Instruct
1
#28 opened 4 months ago
by
helmoz
reacted to
clem's
post with β€οΈ
9 days ago
Post
4663
10,000+ models based on Deepseek R1 have been publicly shared on Hugging Face! Which ones are your favorite ones: https://huggingface.co/models?sort=trending&search=r1. Truly game-changer!
reacted to
Jaward's
post with π₯π
9 days ago
Post
2557
Lightweight (nanoGPT) implementation of hybrid norm - an intuitive normalization method that combines the strength of both pre-norm (i.e QKV-norm in MHA) and post-norm in the feed-forward network.
Code: https://github.com/Jaykef/ai-algorithms/blob/main/hybrid_normalization.ipynb
Code: https://github.com/Jaykef/ai-algorithms/blob/main/hybrid_normalization.ipynb
@ychen , I see. I was expecting your findings were a part of the phd program. Take your time with publications then, since it is common while at Phd. It would be great to have a paper during the masters and all the best with it!
@ychen Good luck with your studies and pleased for affecting on your advances in it. Are you on google scholar or github with personal advances in this domain?