Instructions to use Ex0bit/GLM-4.7-Flash-PRISM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/GLM-4.7-Flash-PRISM with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Ex0bit/GLM-4.7-Flash-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM")
model = AutoModelForCausalLM.from_pretrained("Ex0bit/GLM-4.7-Flash-PRISM")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

llama-cpp-python

How to use Ex0bit/GLM-4.7-Flash-PRISM with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/GLM-4.7-Flash-PRISM",
	filename="GLM-4.7-Flash-PRISM-GGUFs/GLM-4.7-Flash-PRISM-IQ4_NL.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Ex0bit/GLM-4.7-Flash-PRISM with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

LM Studio
Jan

vLLM

How to use Ex0bit/GLM-4.7-Flash-PRISM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/GLM-4.7-Flash-PRISM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

SGLang

How to use Ex0bit/GLM-4.7-Flash-PRISM with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Ex0bit/GLM-4.7-Flash-PRISM" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Ex0bit/GLM-4.7-Flash-PRISM" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/GLM-4.7-Flash-PRISM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Ex0bit/GLM-4.7-Flash-PRISM with Ollama:
```
ollama run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
```

Unsloth Studio new

How to use Ex0bit/GLM-4.7-Flash-PRISM 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 Ex0bit/GLM-4.7-Flash-PRISM 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 Ex0bit/GLM-4.7-Flash-PRISM to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/GLM-4.7-Flash-PRISM to start chatting

Pi new

How to use Ex0bit/GLM-4.7-Flash-PRISM with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/GLM-4.7-Flash-PRISM: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": "Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/GLM-4.7-Flash-PRISM with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/GLM-4.7-Flash-PRISM: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 Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Ex0bit/GLM-4.7-Flash-PRISM with Docker Model Runner:
```
docker model run hf.co/Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M
```

Lemonade

How to use Ex0bit/GLM-4.7-Flash-PRISM with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/GLM-4.7-Flash-PRISM:Q4_K_M

Run and chat with the model

lemonade run user.GLM-4.7-Flash-PRISM-Q4_K_M

List all available models

lemonade list

Ex0bit commited on Jan 30

Commit

5481592

verified ·

1 Parent(s): 9948413

Add config.json to root for TGI compatibility

Browse files

Files changed (1) hide show

config.json +104 -0

config.json ADDED Viewed

	@@ -0,0 +1,104 @@

+{
+  "architectures": [
+    "Glm4MoeLiteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "eos_token_id": [
+    154820,
+    154827,
+    154829
+  ],
+  "first_k_dense_replace": 1,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "kv_lora_rank": 512,
+  "max_position_embeddings": 202752,
+  "mlp_layer_types": [
+    "dense",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse",
+    "sparse"
+  ],
+  "model_type": "glm4_moe_lite",
+  "moe_intermediate_size": 1536,
+  "n_group": 1,
+  "n_routed_experts": 64,
+  "n_shared_experts": 1,
+  "norm_topk_prob": true,
+  "num_attention_heads": 20,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 47,
+  "num_key_value_heads": 20,
+  "num_nextn_predict_layers": 1,
+  "pad_token_id": 154820,
+  "partial_rotary_factor": 1.0,
+  "pretraining_tp": 1,
+  "q_lora_rank": 768,
+  "qk_head_dim": 256,
+  "qk_nope_head_dim": 192,
+  "qk_rope_head_dim": 64,
+  "rms_norm_eps": 1e-05,
+  "rope_interleave": true,
+  "rope_parameters": {
+    "partial_rotary_factor": 1.0,
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "routed_scaling_factor": 1.8,
+  "tie_word_embeddings": false,
+  "topk_group": 1,
+  "topk_method": "noaux_tc",
+  "transformers_version": "5.0.0.dev0",
+  "use_cache": true,
+  "v_head_dim": 256,
+  "vocab_size": 154880
+}