SemanticScuttle - klotz.me

klotz: vicuna*

0 bookmark(s) - Sort by: Date ↓ / Title / - Bookmarks from other users for this tag

1. Llama.cpp vicuna

   2023-06-17 Tags: llama.cpp, vicuna, llm by klotz
2. vicuna-installation-guide/README.md at main · vicuna-tools/vicuna-installation-guide · GitHub

   wget -c https://huggingface.co/eachadea/ggml-vicuna-7b-1.1/resolve/main/ggml-vic7b-uncensored-q5_1.bin

   2023-06-08 Tags: vicuna, llm, models, huggingface, github, chat by klotz
3. Try it Out! FastChat Vicuna: An Open-Source Chatbot Impressing GPT-4 | by Dr. Mandar Karhade, MD. PhD. | Geek Culture | Apr, 2023 | Medium

   2023-06-08 Tags: fastchat, vicuna, gpt-4, llm by klotz
4. lm-sys/FastChat: An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.

   2023-06-08 Tags: llm, vicuna by klotz
5. ehartford/Wizard-Vicuna-30B-Uncensored · Hugging Face

   2023-06-08 Tags: hugging face, wizard-vicuna, vicuna, llama, llm by klotz
6. TheBloke/Wizard-Vicuna-30B-Uncensored-GGML · Hugging Face

   Explanation of the new k-quant methods
   The new methods available are:
   
   GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
   GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
   GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
   GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
   GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
   GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

   2023-06-08 Tags: huggingface, llama, vicuna, quantization, k-quant, gpu, cpu, acceleration, llama.cpp by klotz
7. Llama, Alpaca and Vicuna: “Chatgpt” running on your laptop | by Jeremy Arancio | Apr, 2023 | Medium

   2023-06-07 Tags: llm, llama, alpaca, vicuna, chatgpt by klotz

Top of the page

First / Previous / Next / Last / Page 1 of 0