Instructions to use sabbbbir/qwen-models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sabbbbir/qwen-models with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("sabbbbir/qwen-models", dtype="auto")

llama-cpp-python

How to use sabbbbir/qwen-models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="sabbbbir/qwen-models",
	filename="checkpoints/qwen3_6_35b/Qwen_Qwen3.6-35B-A3B-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use sabbbbir/qwen-models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sabbbbir/qwen-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sabbbbir/qwen-models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf sabbbbir/qwen-models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf sabbbbir/qwen-models: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 sabbbbir/qwen-models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf sabbbbir/qwen-models: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 sabbbbir/qwen-models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sabbbbir/qwen-models:Q4_K_M

Use Docker

docker model run hf.co/sabbbbir/qwen-models:Q4_K_M

LM Studio
Jan
Ollama
How to use sabbbbir/qwen-models with Ollama:
```
ollama run hf.co/sabbbbir/qwen-models:Q4_K_M
```

Unsloth Studio new

How to use sabbbbir/qwen-models 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 sabbbbir/qwen-models 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 sabbbbir/qwen-models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sabbbbir/qwen-models to start chatting

Pi new

How to use sabbbbir/qwen-models with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sabbbbir/qwen-models: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": "sabbbbir/qwen-models:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use sabbbbir/qwen-models with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf sabbbbir/qwen-models: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 sabbbbir/qwen-models:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use sabbbbir/qwen-models with Docker Model Runner:
```
docker model run hf.co/sabbbbir/qwen-models:Q4_K_M
```

Lemonade

How to use sabbbbir/qwen-models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sabbbbir/qwen-models:Q4_K_M

Run and chat with the model

lemonade run user.qwen-models-Q4_K_M

List all available models

lemonade list

sabbbbir commited on 10 days ago

Commit

51157f2

verified ·

1 Parent(s): 936ec58

Auto-push: step 10

Browse files

Files changed (6) hide show

README.md +1 -1
checkpoint-5/README.md +2 -2
checkpoint-5/adapter_config.json +5 -5
checkpoint-5/adapter_model.safetensors +1 -1
checkpoint-5/optimizer.pt +1 -1
checkpoint-5/trainer_state.json +2 -2

README.md CHANGED Viewed

@@ -3,8 +3,8 @@ library_name: transformers
 model_name: ckpt
 tags:
 - generated_from_trainer
-- trl
 - sft
 licence: license
 ---

 model_name: ckpt
 tags:
 - generated_from_trainer
 - sft
+- trl
 licence: license
 ---

checkpoint-5/README.md CHANGED Viewed

@@ -1,9 +1,9 @@
 ---
-base_model: /root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/c033e06a30d9a2afd45137e926cb77015c470e25/checkpoints/qwen3_6_27b
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:/root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/c033e06a30d9a2afd45137e926cb77015c470e25/checkpoints/qwen3_6_27b
 - lora
 - sft
 - transformers

 ---
+base_model: /root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/936ec5831cd1882184f34c45189997d741c42657/checkpoints/qwen3_6_27b
 library_name: peft
 pipeline_tag: text-generation
 tags:
+- base_model:adapter:/root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/936ec5831cd1882184f34c45189997d741c42657/checkpoints/qwen3_6_27b
 - lora
 - sft
 - transformers

checkpoint-5/adapter_config.json CHANGED Viewed

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "/root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/c033e06a30d9a2afd45137e926cb77015c470e25/checkpoints/qwen3_6_27b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -30,12 +30,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "o_proj",
     "q_proj",
     "v_proj",
-    "down_proj",
-    "up_proj",
-    "gate_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
+  "base_model_name_or_path": "/root/.cache/huggingface/hub/models--sabbbbir--qwen-models/snapshots/936ec5831cd1882184f34c45189997d741c42657/checkpoints/qwen3_6_27b",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
   "revision": null,
   "target_modules": [
     "k_proj",
+    "up_proj",
     "q_proj",
     "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

checkpoint-5/adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be4301920225e6f992d3c015ce91938db711d44d0319ca26df04a79d49ff6fc
 size 79759520

 version https://git-lfs.github.com/spec/v1
+oid sha256:17d5d9a33d06ed70307a4bfb4c9671ee18b026e8fd4eeb4a2dff0dcc1eed91fd
 size 79759520

checkpoint-5/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8844756f56ee07e66e536d65757b2fab3d661a8b051f9d4f80f7122d995f21e
 size 81547303

 version https://git-lfs.github.com/spec/v1
+oid sha256:172f44adbf9ed597fe62009c000161823bada70ee2cb4307ed08a63094c49aa6
 size 81547303

checkpoint-5/trainer_state.json CHANGED Viewed

@@ -11,9 +11,9 @@
   "log_history": [
     {
       "epoch": 0.02661343978709248,
-      "grad_norm": 120.0,
       "learning_rate": 5e-05,
-      "loss": 58.57597045898437,
       "step": 5
     }
   ],

   "log_history": [
     {
       "epoch": 0.02661343978709248,
+      "grad_norm": 117.0,
       "learning_rate": 5e-05,
+      "loss": 58.58668212890625,
       "step": 5
     }
   ],