Instructions to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
llama cli -hf legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./llama-cli -hf legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S

Use Docker

docker model run hf.co/legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S

LM Studio
Jan

vLLM

How to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S

Ollama
How to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF with Ollama:
```
ollama run hf.co/legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
```

Unsloth Studio

How to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-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/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF to start chatting

Docker Model Runner
How to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF with Docker Model Runner:
```
docker model run hf.co/legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S
```

Lemonade

How to use legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull legraphista/Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF:Q4_K_S

Run and chat with the model

lemonade run user.Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF-Q4_K_S

List all available models

lemonade list

Atomic Chat

legraphista commited on May 31, 2024

Commit

582521a

verified ·

1 Parent(s): 8876689

Upload imatrix.log with huggingface_hub

Browse files

Files changed (1) hide show

imatrix.log +139 -0

imatrix.log ADDED Viewed

	@@ -0,0 +1,139 @@

+main: build = 3058 (30e238b2)
+main: built with cc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 for x86_64-linux-gnu
+main: seed  = 1717180036
+llama_model_loader: loaded meta data with 22 key-value pairs and 291 tensors from Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/Meta-Llama-3-8B-Instruct-abliterated-v3.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              = llama
+llama_model_loader: - kv   1:                               general.name str              = Meta-Llama-3-8B-Instruct-abliterated-v3
+llama_model_loader: - kv   2:                          llama.block_count u32              = 32
+llama_model_loader: - kv   3:                       llama.context_length u32              = 8192
+llama_model_loader: - kv   4:                     llama.embedding_length u32              = 4096
+llama_model_loader: - kv   5:                  llama.feed_forward_length u32              = 14336
+llama_model_loader: - kv   6:                 llama.attention.head_count u32              = 32
+llama_model_loader: - kv   7:              llama.attention.head_count_kv u32              = 8
+llama_model_loader: - kv   8:                       llama.rope.freq_base f32              = 500000.000000
+llama_model_loader: - kv   9:     llama.attention.layer_norm_rms_epsilon f32              = 0.000010
+llama_model_loader: - kv  10:                          general.file_type u32              = 0
+llama_model_loader: - kv  11:                           llama.vocab_size u32              = 128256
+llama_model_loader: - kv  12:                 llama.rope.dimension_count u32              = 128
+llama_model_loader: - kv  13:                       tokenizer.ggml.model str              = gpt2
+llama_model_loader: - kv  14:                         tokenizer.ggml.pre str              = llama-bpe
+llama_model_loader: - kv  15:                      tokenizer.ggml.tokens arr[str,128256]  = ["!", "\"", "#", "$", "%", "&", "'", ...
+llama_model_loader: - kv  16:                  tokenizer.ggml.token_type arr[i32,128256]  = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ...
+llama_model_loader: - kv  17:                      tokenizer.ggml.merges arr[str,280147]  = ["Ġ Ġ", "Ġ ĠĠĠ", "ĠĠ ĠĠ", "...
+llama_model_loader: - kv  18:                tokenizer.ggml.bos_token_id u32              = 128000
+llama_model_loader: - kv  19:                tokenizer.ggml.eos_token_id u32              = 128009
+llama_model_loader: - kv  20:                    tokenizer.chat_template str              = {% set loop_messages = messages %}{% ...
+llama_model_loader: - kv  21:               general.quantization_version u32              = 2
+llama_model_loader: - type  f32:  291 tensors
+llm_load_vocab: special tokens cache size = 256
+llm_load_vocab: token to piece cache size = 1.5928 MB
+llm_load_print_meta: format           = GGUF V3 (latest)
+llm_load_print_meta: arch             = llama
+llm_load_print_meta: vocab type       = BPE
+llm_load_print_meta: n_vocab          = 128256
+llm_load_print_meta: n_merges         = 280147
+llm_load_print_meta: n_ctx_train      = 8192
+llm_load_print_meta: n_embd           = 4096
+llm_load_print_meta: n_head           = 32
+llm_load_print_meta: n_head_kv        = 8
+llm_load_print_meta: n_layer          = 32
+llm_load_print_meta: n_rot            = 128
+llm_load_print_meta: n_embd_head_k    = 128
+llm_load_print_meta: n_embd_head_v    = 128
+llm_load_print_meta: n_gqa            = 4
+llm_load_print_meta: n_embd_k_gqa     = 1024
+llm_load_print_meta: n_embd_v_gqa     = 1024
+llm_load_print_meta: f_norm_eps       = 0.0e+00
+llm_load_print_meta: f_norm_rms_eps   = 1.0e-05
+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             = 14336
+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  = 500000.0
+llm_load_print_meta: freq_scale_train = 1
+llm_load_print_meta: n_yarn_orig_ctx  = 8192
+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      = all F32
+llm_load_print_meta: model params     = 8.03 B
+llm_load_print_meta: model size       = 29.92 GiB (32.00 BPW)
+llm_load_print_meta: general.name     = Meta-Llama-3-8B-Instruct-abliterated-v3
+llm_load_print_meta: BOS token        = 128000 '<|begin_of_text|>'
+llm_load_print_meta: EOS token        = 128009 '<|eot_id|>'
+llm_load_print_meta: LF token         = 128 'Ä'
+llm_load_print_meta: EOT token        = 128009 '<|eot_id|>'
+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 =    0.30 MiB
+llm_load_tensors: offloading 25 repeating layers to GPU
+llm_load_tensors: offloaded 25/33 layers to GPU
+llm_load_tensors:        CPU buffer size = 30633.02 MiB
+llm_load_tensors:      CUDA0 buffer size = 20800.78 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  = 500000.0
+llama_new_context_with_model: freq_scale = 1
+llama_kv_cache_init:  CUDA_Host KV buffer size =    14.00 MiB
+llama_kv_cache_init:      CUDA0 KV buffer size =    50.00 MiB
+llama_new_context_with_model: KV self size  =   64.00 MiB, K (f16):   32.00 MiB, V (f16):   32.00 MiB
+llama_new_context_with_model:  CUDA_Host  output buffer size =     0.49 MiB
+llama_new_context_with_model:      CUDA0 compute buffer size =  2262.50 MiB
+llama_new_context_with_model:  CUDA_Host compute buffer size =     9.01 MiB
+llama_new_context_with_model: graph nodes  = 1030
+llama_new_context_with_model: graph splits = 81
+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 43.286 ms
+compute_imatrix: computing over 125 chunks with batch_size 512
+compute_imatrix: 0.95 seconds per pass - ETA 1.97 minutes
+[1]6.9550,[2]5.3356,[3]4.7552,[4]5.9521,[5]6.1848,[6]5.1251,[7]5.4806,[8]6.0734,[9]6.3479,
+save_imatrix: stored collected data after 10 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[10]5.7481,[11]6.2474,[12]6.8020,[13]7.2853,[14]7.7500,[15]8.0496,[16]8.3208,[17]8.4896,[18]8.1779,[19]7.7503,
+save_imatrix: stored collected data after 20 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[20]7.7376,[21]7.9144,[22]7.8401,[23]8.1850,[24]8.1189,[25]8.4858,[26]8.5075,[27]8.6020,[28]8.8274,[29]8.8420,
+save_imatrix: stored collected data after 30 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[30]8.8338,[31]8.3433,[32]7.8930,[33]7.6610,[34]7.4806,[35]7.5676,[36]7.6583,[37]7.5818,[38]7.6711,[39]7.8510,
+save_imatrix: stored collected data after 40 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[40]7.9494,[41]8.0367,[42]8.1563,[43]8.3924,[44]8.4976,[45]8.6365,[46]8.5058,[47]8.6491,[48]8.7266,[49]8.8290,
+save_imatrix: stored collected data after 50 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[50]8.7036,[51]8.8046,[52]8.9486,[53]9.0414,[54]9.1195,[55]9.2159,[56]9.2503,[57]9.3136,[58]9.3203,[59]9.3317,
+save_imatrix: stored collected data after 60 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[60]9.2757,[61]9.2573,[62]9.2973,[63]9.3396,[64]9.2324,[65]9.1891,[66]9.2019,[67]9.1651,[68]9.1452,[69]9.1161,
+save_imatrix: stored collected data after 70 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[70]9.1018,[71]9.0830,[72]9.0810,[73]9.0395,[74]8.9719,[75]8.9643,[76]8.9738,[77]8.9422,[78]8.9248,[79]8.9677,
+save_imatrix: stored collected data after 80 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[80]9.0023,[81]8.9934,[82]8.9942,[83]9.0198,[84]8.8886,[85]8.8820,[86]8.8776,[87]8.8927,[88]8.9199,[89]8.9228,
+save_imatrix: stored collected data after 90 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[90]8.8580,[91]8.7803,[92]8.7008,[93]8.6376,[94]8.5770,[95]8.5155,[96]8.4698,[97]8.4813,[98]8.5218,[99]8.6150,
+save_imatrix: stored collected data after 100 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[100]8.7030,[101]8.7701,[102]8.9084,[103]8.9515,[104]8.9945,[105]8.8945,[106]8.8884,[107]8.8311,[108]8.7640,[109]8.6835,
+save_imatrix: stored collected data after 110 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[110]8.7344,[111]8.8007,[112]8.8050,[113]8.8203,[114]8.8743,[115]8.9218,[116]8.9400,[117]8.9711,[118]8.9996,[119]8.9310,
+save_imatrix: stored collected data after 120 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+[120]8.9453,[121]8.9654,[122]8.9965,[123]9.0460,[124]9.0738,[125]9.1103,
+save_imatrix: stored collected data after 125 chunks in Meta-Llama-3-8B-Instruct-abliterated-v3-IMat-GGUF/imatrix.dat
+llama_print_timings:        load time =    2807.25 ms
+llama_print_timings:      sample time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings: prompt eval time =  109298.58 ms / 64000 tokens (    1.71 ms per token,   585.55 tokens per second)
+llama_print_timings:        eval time =       0.00 ms /     1 runs   (    0.00 ms per token,      inf tokens per second)
+llama_print_timings:       total time =  111984.69 ms / 64001 tokens
+Final estimate: PPL = 9.1103 +/- 0.14568