Instructions to use legraphista/glm-4-9b-chat-IMat-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 legraphista/glm-4-9b-chat-IMat-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 legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

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 legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

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 legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

Use Docker

docker model run hf.co/legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

LM Studio
Jan

vLLM

How to use legraphista/glm-4-9b-chat-IMat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "legraphista/glm-4-9b-chat-IMat-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "legraphista/glm-4-9b-chat-IMat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

Ollama
How to use legraphista/glm-4-9b-chat-IMat-GGUF with Ollama:
```
ollama run hf.co/legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
```

Unsloth Studio

How to use legraphista/glm-4-9b-chat-IMat-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 legraphista/glm-4-9b-chat-IMat-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 legraphista/glm-4-9b-chat-IMat-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for legraphista/glm-4-9b-chat-IMat-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use legraphista/glm-4-9b-chat-IMat-GGUF with Docker Model Runner:
```
docker model run hf.co/legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S
```

Lemonade

How to use legraphista/glm-4-9b-chat-IMat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull legraphista/glm-4-9b-chat-IMat-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.glm-4-9b-chat-IMat-GGUF-Q4_K_S

List all available models

lemonade list

legraphista commited on Jun 20, 2024

Commit

a9502fa

verified ·

1 Parent(s): 07bbe2a

Upload imatrix.log with huggingface_hub

Browse files

Files changed (1) hide show

imatrix.log +112 -0

imatrix.log ADDED Viewed

	@@ -0,0 +1,112 @@

+llama_model_loader: loaded meta data with 24 key-value pairs and 283 tensors from glm-4-9b-chat-IMat-GGUF/glm-4-9b-chat.Q8_0.gguf.hardlink.gguf (version GGUF V3 (latest))
+llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output.
+llama_model_loader: - kv   0:                       general.architecture str              = chatglm
+llama_model_loader: - kv   1:                               general.name str              = glm-4-9b-chat
+llama_model_loader: - kv   2:                     chatglm.context_length u32              = 131072
+llama_model_loader: - kv   3:                   chatglm.embedding_length u32              = 4096
+llama_model_loader: - kv   4:                chatglm.feed_forward_length u32              = 13696
+llama_model_loader: - kv   5:                        chatglm.block_count u32              = 40
+llama_model_loader: - kv   6:               chatglm.attention.head_count u32              = 32
+llama_model_loader: - kv   7:            chatglm.attention.head_count_kv u32              = 2
+llama_model_loader: - kv   8:   chatglm.attention.layer_norm_rms_epsilon f32              = 0.000000
+llama_model_loader: - kv   9:                          general.file_type u32              = 7
+llama_model_loader: - kv  10:               chatglm.rope.dimension_count u32              = 64
+llama_model_loader: - kv  11:               tokenizer.ggml.add_bos_token bool             = false
+llama_model_loader: - kv  12:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  13:                         tokenizer.ggml.pre str              = chatglm-bpe
+llama_model_loader: - kv  14:                      tokenizer.ggml.tokens arr[str,151552]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  15:                  tokenizer.ggml.token_type arr[i32,151552]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  16:                      tokenizer.ggml.merges arr[str,151073]  = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",...
+llama_model_loader: - kv  17:            tokenizer.ggml.padding_token_id u32              = 151329
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 151329
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 151329
+llama_model_loader: - kv  20:                tokenizer.ggml.eot_token_id u32              = 151336
+llama_model_loader: - kv  21:            tokenizer.ggml.unknown_token_id u32              = 151329
+llama_model_loader: - kv  22:                    tokenizer.chat_template str              = ChatGLM4
+llama_model_loader: - kv  23:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  121 tensors
+llama_model_loader: - type q8_0:  162 tensors
+llm_load_vocab: special tokens cache size = 223
+llm_load_vocab: token to piece cache size = 0.9732 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = chatglm
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 151552
+llm_load_print_meta: n_merges         = 151073
+llm_load_print_meta: n_ctx_train      = 131072
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 2
+llm_load_print_meta: n_layer          = 40
+llm_load_print_meta: n_rot            = 64
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 16
+llm_load_print_meta: n_embd_k_gqa     = 256
+llm_load_print_meta: n_embd_v_gqa     = 256
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.6e-07
+llm_load_print_meta: f_clamp_kqv      = 0.0e+00
+llm_load_print_meta: f_max_alibi_bias = 0.0e+00
+llm_load_print_meta: f_logit_scale    = 0.0e+00
+llm_load_print_meta: n_ff             = 13696
+llm_load_print_meta: n_expert         = 0
+llm_load_print_meta: n_expert_used    = 0
+llm_load_print_meta: causal attn      = 1
+llm_load_print_meta: pooling type     = 0
+llm_load_print_meta: rope type        = 0
+llm_load_print_meta: rope scaling     = linear
+llm_load_print_meta: freq_base_train  = 10000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_ctx_orig_yarn  = 131072
+llm_load_print_meta: rope_finetuned   = unknown
+llm_load_print_meta: ssm_d_conv       = 0
+llm_load_print_meta: ssm_d_inner      = 0
+llm_load_print_meta: ssm_d_state      = 0
+llm_load_print_meta: ssm_dt_rank      = 0
+llm_load_print_meta: model type       = 8B
+llm_load_print_meta: model ftype      = Q8_0
+llm_load_print_meta: model params     = 9.40 B
+llm_load_print_meta: model size       = 9.30 GiB (8.50 BPW)
+llm_load_print_meta: general.name     = glm-4-9b-chat
+llm_load_print_meta: BOS token        = 151329 '<|endoftext|>'
+llm_load_print_meta: EOS token        = 151329 '<|endoftext|>'
+llm_load_print_meta: UNK token        = 151329 '<|endoftext|>'
+llm_load_print_meta: PAD token        = 151329 '<|endoftext|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 151336 '<|user|>'
+ggml_cuda_init: GGML_CUDA_FORCE_MMQ:   no
+ggml_cuda_init: CUDA_USE_TENSOR_CORES: yes
+ggml_cuda_init: found 1 CUDA devices:
+  Device 0: NVIDIA GeForce RTX 4090, compute capability 8.9, VMM: yes
+llm_load_tensors: ggml ctx size =    0.31 MiB
+llm_load_tensors: offloading 40 repeating layers to GPU
+llm_load_tensors: offloading non-repeating layers to GPU
+llm_load_tensors: offloaded 41/41 layers to GPU
+llm_load_tensors:        CPU buffer size =   629.00 MiB
+llm_load_tensors:      CUDA0 buffer size =  8897.23 MiB
+.................................................................................
+llama_new_context_with_model: n_ctx      = 512
+llama_new_context_with_model: n_batch    = 512
+llama_new_context_with_model: n_ubatch   = 512
+llama_new_context_with_model: flash_attn = 0
+llama_new_context_with_model: freq_base  = 10000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:      CUDA0 KV buffer size =    20.00 MiB
+llama_new_context_with_model: KV self size  =   20.00 MiB, K (f16):   10.00 MiB, V (f16):   10.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.58 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =   304.00 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1606
+llama_new_context_with_model: graph splits = 2
+system_info: n_threads = 25 / 32 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | AVX512_BF16 = 1 | FMA = 1 | NEON = 0 | SVE = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 | LLAMAFILE = 1 |
+compute_imatrix: tokenizing the input ..
+compute_imatrix: tokenization took 122.54 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.65 seconds per pass - ETA 1.35 minutes
+[1]7.9954,[2]6.0663,[3]5.9242,[4]7.2853,[5]7.2095,[6]6.0079,[7]6.4837,[8]6.8565,[9]7.0213,
+save_imatrix: stored collected data after 10 chunks in glm-4-9b-chat-IMat-GGUF/imatrix.dat
+[10]6.1378,[11]6.7411,[12]7.3944,[13]7.8688,[14]8.1976,[15]8.6583,[16]9.1342,[17]9.4154,[18]9.1001,[19]8.6114,
+save_imatrix: stored collected data after 20 chunks in glm-4-9b-chat-IMat-GGUF/imatrix.dat
+[20]8.5978,nan detected in blk.18.attn_output.weight