Instructions to use Mauro6519/DeepSeek-R1-Medical-COT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Mauro6519/DeepSeek-R1-Medical-COT with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Mauro6519/DeepSeek-R1-Medical-COT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Mauro6519/DeepSeek-R1-Medical-COT 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 Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Mauro6519/DeepSeek-R1-Medical-COT: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 Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Mauro6519/DeepSeek-R1-Medical-COT: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 Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M

Use Docker

docker model run hf.co/Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M

LM Studio
Jan
Ollama
How to use Mauro6519/DeepSeek-R1-Medical-COT with Ollama:
```
ollama run hf.co/Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
```

Unsloth Studio

How to use Mauro6519/DeepSeek-R1-Medical-COT 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 Mauro6519/DeepSeek-R1-Medical-COT 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 Mauro6519/DeepSeek-R1-Medical-COT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Mauro6519/DeepSeek-R1-Medical-COT to start chatting

Docker Model Runner
How to use Mauro6519/DeepSeek-R1-Medical-COT with Docker Model Runner:
```
docker model run hf.co/Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M
```

Lemonade

How to use Mauro6519/DeepSeek-R1-Medical-COT with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Mauro6519/DeepSeek-R1-Medical-COT:Q4_K_M

Run and chat with the model

lemonade run user.DeepSeek-R1-Medical-COT-Q4_K_M

List all available models

lemonade list

Atomic Chat

Mauro6519 commited on Feb 8, 2025

Commit

ab6c351

verified ·

1 Parent(s): 00e45ec

Upload model trained with Unsloth

Browse files

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +6 -6
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "down_proj",
-    "up_proj",
     "q_proj",
     "v_proj",
-    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/deepseek-r1-distill-qwen-14b-unsloth-bnb-4bit",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "q_proj",
+    "down_proj",
     "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:098f04ded6e74a25461382fde179e486c9144a5b9e13900eee0959fccd9154f7
-size 167832240

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d418a0e71ff4e1368ef5168ddc8486f4493bf6e0955b3aa8a3ee344c51c2e29
+size 275341720