Hugging Face's logo

google
/
gemma-7b

Text Generation
Transformers
Safetensors
GGUF
gemma
text-generation-inference
Inference Endpoints
Model card Files Community
113

Quantization

#21
by sayhan - opened
Discussion
sayhan
•
edited Feb 21, 2024

Has anyone successfully quantized the Gemma models? I attempted to apply quantization through llama.cpp to make them run on my laptop, but unfortunately, I'm unable to execute the quantized versions.

In LM Studio, I received the following error:

"llama.cpp error: 'create_tensor: tensor 'output.weight' not found'"

and AssertionError on oobabooga/text-generation-webui (model loader option was configured to 'llama.cpp')

Edit: Okay, I realized the obvious reason - their current builds simply don't support this model yet.

sayhan changed discussion status to closed
leokster

I have the same problem. Is there a workaround?

paradoxnafi

I am encountering the same problem while trying to load 7B Q2_K model. Points to note that I am on a laptop with 8GB ram.
Here is the complete error log

`

{
  "cause": "llama.cpp error: 'create_tensor: tensor 'output.weight' not found'",
  "errorData": {
    "n_ctx": 2048,
    "n_batch": 512,
    "n_gpu_layers": 10
  },
  "data": {
    "memory": {
      "ram_capacity": "7.50 GB",
      "ram_unused": "7.50 GB"
    },
    "gpu": {
      "type": "IntelOpenCL",
      "vram_recommended_capacity": 0,
      "vram_unused": 0
    },
    "os": {
      "platform": "linux",
      "version": "6.7.5-arch1-1",
      "supports_avx2": true
    },
    "app": {
      "version": "0.2.15",
      "downloadsDir": "/home/user/.cache/lm-studio/models"
    },
    "model": {}
  },
  "title": "Failed to load model",
  "systemDiagnostics": {
    "memory": {
      "ram_capacity": 8058425344,
      "ram_unused": 8058425344
    },
    "gpu": {
      "type": "IntelOpenCL",
      "vram_recommended_capacity": 0,
      "vram_unused": 0
    },
    "os": {
      "platform": "linux",
      "version": "6.7.5-arch1-1",
      "supports_avx2": true
    },
    "app": {
      "version": "0.2.15",
      "downloadsDir": "/home/user/.cache/lm-studio/models"
    },
    "model": {
      "gguf_preview": {
        "name": ".",
        "arch": "llama",
        "quant": "Q2_K",
        "context_length": 8192,
        "embedding_length": 3072,
        "num_layers": 28,
        "rope": {
          "freq_base": 10000,
          "dimension_count": 192
        },
        "head_count": 16,
        "head_count_kv": 16
      },
      "filesize": 3094375360,
      "config": {
        "path": "/home/user/.cache/lm-studio/models/mlabonne/gemma-7b-it-GGUF/gemma-7b-it.Q2_K.gguf",
        "loadConfig": {
          "n_ctx": 2048,
          "n_batch": 512,
          "rope_freq_base": 0,
          "rope_freq_scale": 0,
          "n_gpu_layers": 10,
          "use_mlock": true,
          "main_gpu": 0,
          "tensor_split": [
            0
          ],
          "seed": -1,
          "f16_kv": true,
          "use_mmap": true,
          "no_kv_offload": false,
          "num_experts_used": 0
        }
      }
    }
  }
}``` 
`
donbalear

Same problem

"llama.cpp error: 'create_tensor: tensor 'output.weight' not found'"
{
"memory": {
"ram_capacity": "31.36 GB",
"ram_unused": "22.47 GB"
},
"gpu": {
"type": "AmdOpenCL",
"vram_recommended_capacity": "6.00 GB",
"vram_unused": "5.01 GB"
},
"os": {
"platform": "win32",
"version": "10.0.22621",
"supports_avx2": true
},
"app": {
"version": "0.2.16",

},
"model": {}
}

sayhan

@leokster @paradoxnafi @donbalear Did you use this script to convert the model files to GGUF?
https://github.com/ggerganov/llama.cpp/pull/5647

Sign up or log in to comment