Instructions to use bartowski/AlchemistCoder-L-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bartowski/AlchemistCoder-L-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="bartowski/AlchemistCoder-L-7B-GGUF",
	filename="AlchemistCoder-L-7B-IQ2_M.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use bartowski/AlchemistCoder-L-7B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/AlchemistCoder-L-7B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/AlchemistCoder-L-7B-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/AlchemistCoder-L-7B-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Ollama
How to use bartowski/AlchemistCoder-L-7B-GGUF with Ollama:
```
ollama run hf.co/bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/AlchemistCoder-L-7B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/AlchemistCoder-L-7B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for bartowski/AlchemistCoder-L-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for bartowski/AlchemistCoder-L-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use bartowski/AlchemistCoder-L-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M
```

Lemonade

How to use bartowski/AlchemistCoder-L-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/AlchemistCoder-L-7B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AlchemistCoder-L-7B-GGUF-Q4_K_M

List all available models

lemonade list

bartowski commited on May 31, 2024

Commit

e299430

verified ·

1 Parent(s): 6688a1d

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -4

README.md CHANGED Viewed

@@ -31,17 +31,18 @@ No chat template specified so default is used. This may be incorrect, check orig
 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
 | [AlchemistCoder-L-7B-Q8_0.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q8_0.gguf) | Q8_0 | 7.16GB | Extremely high quality, generally unneeded but max available quant. |
 | [AlchemistCoder-L-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q5_K_M.gguf) | Q5_K_M | 4.78GB | High quality, *recommended*. |
-| [AlchemistCoder-L-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q4_K_M.gguf) | Q4_K_M | 4.08GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
 | [AlchemistCoder-L-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ4_XS.gguf) | IQ4_XS | 3.61GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [AlchemistCoder-L-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_M.gguf) | Q3_K_M | 3.29GB | Even lower quality. |
 | [AlchemistCoder-L-7B-IQ3_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_M.gguf) | IQ3_M | 3.11GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
 | [AlchemistCoder-L-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_S.gguf) | Q3_K_S | 2.94GB | Low quality, not recommended. |
 | [AlchemistCoder-L-7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_XXS.gguf) | IQ3_XXS | 2.58GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
 | [AlchemistCoder-L-7B-Q2_K.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q2_K.gguf) | Q2_K | 2.53GB | Very low quality but surprisingly usable. |
-| [AlchemistCoder-L-7B-IQ2_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ2_M.gguf) | IQ2_M | 2.35GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
-| [AlchemistCoder-L-7B-IQ2_XXS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF//main/AlchemistCoder-L-7B-IQ2_XXS.gguf) | IQ2_XXS |  | Lower quality, uses SOTA techniques to be usable. |
-| [AlchemistCoder-L-7B-IQ1_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF//main/AlchemistCoder-L-7B-IQ1_M.gguf) | IQ1_M |  | Extremely low quality, *not* recommended. |
 ## Downloading using huggingface-cli

 | Filename | Quant type | File Size | Description |
 | -------- | ---------- | --------- | ----------- |
 | [AlchemistCoder-L-7B-Q8_0.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q8_0.gguf) | Q8_0 | 7.16GB | Extremely high quality, generally unneeded but max available quant. |
+| [AlchemistCoder-L-7B-Q6_K.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q6_K.gguf) | Q6_K | 5.53GB | High quality, *recommended*. |
 | [AlchemistCoder-L-7B-Q5_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q5_K_M.gguf) | Q5_K_M | 4.78GB | High quality, *recommended*. |
+| [AlchemistCoder-L-7B-Q5_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q5_K_S.gguf) | Q5_K_S | 4.65GB | High quality, *recommended*. |
+| [AlchemistCoder-L-7B-Q4_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q4_K_M.gguf) | Q4_K_M | 4.08GB | High quality, *recommended*. |
+| [AlchemistCoder-L-7B-Q4_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q4_K_S.gguf) | Q4_K_S | 3.86GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
 | [AlchemistCoder-L-7B-IQ4_XS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ4_XS.gguf) | IQ4_XS | 3.61GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [AlchemistCoder-L-7B-Q3_K_L.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_M.gguf) | Q3_K_M | 3.29GB | Even lower quality. |
 | [AlchemistCoder-L-7B-Q3_K_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_M.gguf) | Q3_K_M | 3.29GB | Even lower quality. |
 | [AlchemistCoder-L-7B-IQ3_M.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_M.gguf) | IQ3_M | 3.11GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
 | [AlchemistCoder-L-7B-Q3_K_S.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q3_K_S.gguf) | Q3_K_S | 2.94GB | Low quality, not recommended. |
 | [AlchemistCoder-L-7B-IQ3_XXS.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-IQ3_XXS.gguf) | IQ3_XXS | 2.58GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
 | [AlchemistCoder-L-7B-Q2_K.gguf](https://huggingface.co/bartowski/AlchemistCoder-L-7B-GGUF/blob/main/AlchemistCoder-L-7B-Q2_K.gguf) | Q2_K | 2.53GB | Very low quality but surprisingly usable. |
 ## Downloading using huggingface-cli