Instructions to use RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use RichardErkhov/tyson0420_-_stack_codellama-7b-inst-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 RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/tyson0420_-_stack_codellama-7b-inst-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 RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf RichardErkhov/tyson0420_-_stack_codellama-7b-inst-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 RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf RichardErkhov/tyson0420_-_stack_codellama-7b-inst-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 RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M

Use Docker

docker model run hf.co/RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf with Ollama:
```
ollama run hf.co/RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf with Docker Model Runner:
```
docker model run hf.co/RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M
```

Lemonade

How to use RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull RichardErkhov/tyson0420_-_stack_codellama-7b-inst-gguf:Q4_K_M

Run and chat with the model

lemonade run user.tyson0420_-_stack_codellama-7b-inst-gguf-Q4_K_M

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Quantization made by Richard Erkhov.

Github

Discord

Request more models

stack_codellama-7b-inst - GGUF

Model creator: https://huggingface.co/tyson0420/
Original model: https://huggingface.co/tyson0420/stack_codellama-7b-inst/

Name	Quant method	Size
stack_codellama-7b-inst.Q2_K.gguf	Q2_K	2.36GB
stack_codellama-7b-inst.IQ3_XS.gguf	IQ3_XS	2.6GB
stack_codellama-7b-inst.IQ3_S.gguf	IQ3_S	2.75GB
stack_codellama-7b-inst.Q3_K_S.gguf	Q3_K_S	2.75GB
stack_codellama-7b-inst.IQ3_M.gguf	IQ3_M	2.9GB
stack_codellama-7b-inst.Q3_K.gguf	Q3_K	3.07GB
stack_codellama-7b-inst.Q3_K_M.gguf	Q3_K_M	3.07GB
stack_codellama-7b-inst.Q3_K_L.gguf	Q3_K_L	3.35GB
stack_codellama-7b-inst.IQ4_XS.gguf	IQ4_XS	3.4GB
stack_codellama-7b-inst.Q4_0.gguf	Q4_0	3.56GB
stack_codellama-7b-inst.IQ4_NL.gguf	IQ4_NL	3.58GB
stack_codellama-7b-inst.Q4_K_S.gguf	Q4_K_S	3.59GB
stack_codellama-7b-inst.Q4_K.gguf	Q4_K	3.8GB
stack_codellama-7b-inst.Q4_K_M.gguf	Q4_K_M	3.8GB
stack_codellama-7b-inst.Q4_1.gguf	Q4_1	3.95GB
stack_codellama-7b-inst.Q5_0.gguf	Q5_0	4.33GB
stack_codellama-7b-inst.Q5_K_S.gguf	Q5_K_S	4.33GB
stack_codellama-7b-inst.Q5_K.gguf	Q5_K	4.45GB
stack_codellama-7b-inst.Q5_K_M.gguf	Q5_K_M	4.45GB
stack_codellama-7b-inst.Q5_1.gguf	Q5_1	4.72GB
stack_codellama-7b-inst.Q6_K.gguf	Q6_K	5.15GB
stack_codellama-7b-inst.Q8_0.gguf	Q8_0	6.67GB

Original model description:

library_name: transformers tags: - code license: bigscience-openrail-m datasets: - tyson0420/stackexchange-4dpo-filby-clang-keywords language: - en metrics: - code_eval

Model Card for Model ID

Model Details

Evaluating generations... { "humaneval": { "pass@1": 0.32499999999999996, "pass@10": 0.4329268292682927 }, "config": { "prefix": "", "do_sample": true, "temperature": 0.2, "top_k": 0, "top_p": 0.95, "n_samples": 10, "eos": "<|endoftext|>", "seed": 0, "model": "tyson0420/stack_codellama-7b-inst", "modeltype": "causal", "peft_model": null, "revision": null, "use_auth_token": false, "trust_remote_code": false, "tasks": "humaneval", "instruction_tokens": null, "batch_size": 10, "max_length_generation": 512, "precision": "fp32", "load_in_8bit": false, "load_in_4bit": false, "left_padding": false, "limit": null, "limit_start": 0, "save_every_k_tasks": -1, "postprocess": true, "allow_code_execution": true, "generation_only": false, "load_generations_path": null, "load_data_path": null, "metric_output_path": "evaluation_results.json", "save_generations": false, "load_generations_intermediate_paths": null, "save_generations_path": "generations.json", "save_references": false, "save_references_path": "references.json", "prompt": "prompt", "max_memory_per_gpu": null, "check_references": false } }

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

Developed by: [tyson0420]

Downloads last month: 397

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support