whatmodel.sh / LMCocktail-10.7B-v1
LMCocktail-10.7B-v1
↗ share
+ contribute
LMCocktail-10.7B-v1 is an open-weights language model from Yhyu13, released December 2023. Its published size is 10.73B parameters. Licence: llama2.
Catalogue identity notes
Maker repo Yhyu13/LMCocktail-10.7B-v1 @79ec3a4: licence tag llama2. 10,731,524,096 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2023-12: month the maker's Hugging Face repo was created (createdAt 2023-12-20).
$ how it compares
The LLMs ranked either side of LMCocktail-10.7B-v1, out of 1132 with a score.
| # | model | score | where |
|---|---|---|---|
| 844 |  Phi-3-vision-128k-instruct | 41±2 | local |
| 845 | Starling-LM-7B-alpha-ExPO | 41±2 | local |
| 846 | LMCocktail-10.7B-v1 | 41±2 | local |
| 847 |  OpenChat 3.5 | 41±2 | local |
| 848 |  InternVL2-4B | 41±2 | local |
$ what it's good at
chat & writing▁▁▁▄▆▅▆█▆▆▆▂ #368 of 466 * · 98% of its score · 2 tests
Beats Gemma 4 E4B, OpenThinker3 7B, Gemma 4 E2B here, though they rank higher overall. Trails LFM2 350M, Gemma 3 1B, Flan-T5 XXL here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AlpacaEval 2 length-controlled | 18.9% ✎ | ▁▂▂▃▆▆█▆▄▄▁▁ beats 50/122 | 90% |
| AlpacaEval 1.0 win rate (vs text-davinci-003, GPT-4 judge) | 92.2% ✎ | ▂▂·▆·▇▃▆█▆▄▂ beats 34/45 | 8.3% |
$ where to run it
llama.cpp · recommended
version
- Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.macOS / Linux
curl -LsSf https://llama.app/install.sh | shWindowsirm https://llama.app/install.ps1 | iex - Run LMCocktail-10.7B-v1 · needs ~6.5 GB · from huggingface.co/TheBlokechat in the terminal
llama cli -hf TheBloke/LMCocktail-10.7B-v1-GGUF:Q4_K_M - Or start a local server and open the address it prints (http://localhost:9931)
llama serve -hf TheBloke/LMCocktail-10.7B-v1-GGUF:Q4_K_M
LM Studio
version
- Install LM Studio · Open the app once before using the lms command.
- Run LMCocktail-10.7B-v1 · needs ~6.5 GB · from huggingface.co/TheBloke
- Or download it in the terminal
lms get https://huggingface.co/TheBloke/LMCocktail-10.7B-v1-GGUF@Q4_K_M -y - Then run lms ls to see its name, and lms chat followed by that name
Ollama
version
- Install Ollama
download it (macOS / Windows) ↗
Linuxcurl -fsSL https://ollama.com/install.sh | sh - Run LMCocktail-10.7B-v1 · needs ~6.5 GB · from huggingface.co/TheBlokechat in the terminal
ollama run hf.co/TheBloke/LMCocktail-10.7B-v1-GGUF:Q4_K_M
Other ways to run it
- Run it as published · needs ~21.46 GB · from huggingface.co/Yhyu13 (official)
uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Yhyu13/LMCocktail-10.7B-v1', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"
Official weights and documentation: huggingface.co/Yhyu13 ↗
$ how the score was worked out · AlpacaEval 1.0 and 2.0 leader… 98%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository) | 2 | 98% |
| prior · pull toward the middle | 2% | |
| weighted average | = 41.4 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json