Instructions to use seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use seanbailey518/Step3-VL-10B-GGUF with Ollama:
```
ollama run hf.co/seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
```

Unsloth Studio

How to use seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-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 seanbailey518/Step3-VL-10B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for seanbailey518/Step3-VL-10B-GGUF to start chatting

How to use seanbailey518/Step3-VL-10B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "seanbailey518/Step3-VL-10B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use seanbailey518/Step3-VL-10B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "seanbailey518/Step3-VL-10B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use seanbailey518/Step3-VL-10B-GGUF with Docker Model Runner:
```
docker model run hf.co/seanbailey518/Step3-VL-10B-GGUF:Q4_K_M
```

Lemonade

How to use seanbailey518/Step3-VL-10B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Step3-VL-10B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use seanbailey518/Step3-VL-10B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default seanbailey518/Step3-VL-10B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

What version of llama.cpp are you using?

by AndyLeaf666 - opened Feb 4

Discussion

AndyLeaf666

Feb 4

What version of llama.cpp are you using? I'm getting an error when I try to run it with version 12.4.

sean-edgerunner-ai

Feb 5

I am still working out the kinks. I've gotten the text models to perform inference no problem but still figuring out the mmproj. These ended up being a PoC for a separate script, had no idea it would get this much attention! I will update with my fork once it's working on both text and image.

MrDevolver

Feb 14

•

edited Feb 14

I am still working out the kinks. I've gotten the text models to perform inference no problem but still figuring out the mmproj. These ended up being a PoC for a separate script, had no idea it would get this much attention! I will update with my fork once it's working on both text and image.

Hey, any news on this? This seems to be a pretty good small model. It would be awesome to have proper support in LM Studio (llamacpp based).

DmitrySv

Mar 4

clip_model_loader: has vision encoder
clip_ctx: CLIP using CUDA0 backend
clip_init: failed to load model '.\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf': load_hparams: unknown projector type: step3vl

mtmd_init_from_file: error: Failed to load CLIP model from .\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf

Without -mm .\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf works fine. Tested on llama-b7954-bin-win-cuda-12.4-x64 and llama-b8194-bin-win-cuda-12.4-x64

kraven1109

Mar 5

clip_model_loader: has vision encoder
clip_ctx: CLIP using CUDA0 backend
clip_init: failed to load model '.\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf': load_hparams: unknown projector type: step3vl

mtmd_init_from_file: error: Failed to load CLIP model from .\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf
Without -mm .\LLM\mtmd\mmproj-Step3-VL-10b-F16.gguf works fine. Tested on llama-b7954-bin-win-cuda-12.4-x64 and llama-b8194-bin-win-cuda-12.4-x64

hey, could you try my version? i successfully convert it, it requires change both llama.cpp and the python conversion file, I also uploaded the binary (p13 on my repo)

DmitrySv

Mar 28

hey, could you try my version? i successfully convert it, it requires change both llama.cpp and the python conversion file, I also uploaded the binary (p13 on my repo)

load_tensors: loading model tensors, this can take a while... (mmap = false, direct_io = false)
load_tensors: offloading output layer to GPU
load_tensors: offloading 35 repeating layers to GPU
load_tensors: offloaded 37/37 layers to GPU
load_tensors:          CPU model buffer size =   486.86 MiB
load_tensors:        CUDA0 model buffer size =  5921.78 MiB
.......................................................................................
common_init_result: added </s> logit bias = -inf
common_init_result: added <|endoftext|> logit bias = -inf
common_init_result: added <|im_end|> logit bias = -inf
common_init_result: added <|fim_pad|> logit bias = -inf
common_init_result: added <|repo_name|> logit bias = -inf
common_init_result: added <|file_sep|> logit bias = -inf
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 8192
llama_context: n_ctx_seq     = 8192
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 2048
llama_context: causal_attn   = 1
llama_context: flash_attn    = enabled
llama_context: kv_unified    = false
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_seq (8192) < n_ctx_train (65536) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.58 MiB
llama_kv_cache:      CUDA0 KV buffer size =  1152.00 MiB
llama_kv_cache: size = 1152.00 MiB (  8192 cells,  36 layers,  1/1 seqs), K (f16):  576.00 MiB, V (f16):  576.00 MiB
sched_reserve: reserving ...
sched_reserve:      CUDA0 compute buffer size =  1219.00 MiB
sched_reserve:  CUDA_Host compute buffer size =   128.05 MiB
sched_reserve: graph nodes  = 1267
sched_reserve: graph splits = 2
sched_reserve: reserve took 24.19 ms, sched copies = 1
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)
D:\Apps\git_cloned_repos\llama.cpp\ggml\src\ggml-cuda\ggml-cuda.cu:97: CUDA error
ggml_cuda_compute_forward: MUL_MAT failed

I also tried with original's ggml-cuda.dll - almost the same:

load_tensors: loading model tensors, this can take a while... (mmap = false, direct_io = false)
load_tensors: offloading output layer to GPU
load_tensors: offloading 35 repeating layers to GPU
load_tensors: offloaded 37/37 layers to GPU
load_tensors:          CPU model buffer size =   486.86 MiB
load_tensors:        CUDA0 model buffer size =  5921.78 MiB
.......................................................................................
common_init_result: added </s> logit bias = -inf
common_init_result: added <|endoftext|> logit bias = -inf
common_init_result: added <|im_end|> logit bias = -inf
common_init_result: added <|fim_pad|> logit bias = -inf
common_init_result: added <|repo_name|> logit bias = -inf
common_init_result: added <|file_sep|> logit bias = -inf
llama_context: constructing llama_context
llama_context: n_seq_max     = 1
llama_context: n_ctx         = 8192
llama_context: n_ctx_seq     = 8192
llama_context: n_batch       = 2048
llama_context: n_ubatch      = 2048
llama_context: causal_attn   = 1
llama_context: flash_attn    = enabled
llama_context: kv_unified    = false
llama_context: freq_base     = 1000000.0
llama_context: freq_scale    = 1
llama_context: n_ctx_seq (8192) < n_ctx_train (65536) -- the full capacity of the model will not be utilized
llama_context:  CUDA_Host  output buffer size =     0.58 MiB
llama_kv_cache:      CUDA0 KV buffer size =  1152.00 MiB
llama_kv_cache: size = 1152.00 MiB (  8192 cells,  36 layers,  1/1 seqs), K (f16):  576.00 MiB, V (f16):  576.00 MiB
sched_reserve: reserving ...
sched_reserve:      CUDA0 compute buffer size =  1219.00 MiB
sched_reserve:  CUDA_Host compute buffer size =   128.05 MiB
sched_reserve: graph nodes  = 1267
sched_reserve: graph splits = 2
sched_reserve: reserve took 68.77 ms, sched copies = 1
common_init_from_params: warming up the model with an empty run - please wait ... (--no-warmup to disable)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment