2024 llama.cpp 7840u

From zooid Wiki
Revision as of 14:40, 13 April 2024 by DavidM (talk | contribs)
Jump to navigation Jump to search

I briefly had a Macbook M3 Max with 64GB. It was pretty good at running local LLMs, but couldn't stand the ergonomics and not being able to run Linux, so returned it.

I picked up a Thinkpad P16s with an AMD 7840u to give Linux hardware a chance to catch up with Apple silicon. It's an amazing computer for the price, and can run LLMs. Here's how I set up llama.cpp to use ROCm.

Install ROCm, set an env variable for the 780m: export HSA_OVERRIDE_GFX_VERSION=11.0.0

clone llama.cpp and compile it:

make -j16 LLAMA_HIPBLAS=1 LLAMA_HIP_UMA=1 AMDGPU_TARGETS=gfx1030 DLLAMA_HIP_UMA= ON

run it like this:

./main -m /home/vid/jan/models/mistral-ins-7b-q4/mistral-7b-instruct-v0.2.Q4_K_M .gguf -p "example code for a lit Web Component that reverses a string" -n 50 -e -ngl 16 -n -1


ggml_cuda_init: found 1 ROCm devices:
  Device 0: AMD Radeon Graphics, compute capability 11.0, VMM: no
llm_load_tensors: ggml ctx size =    0.22 MiB
llm_load_tensors: offloading 24 repeating layers to GPU
llm_load_tensors: offloaded 24/33 layers to GPU
llm_load_tensors:      ROCm0 buffer size =  2978.91 MiB
llm_load_tensors:        CPU buffer size =  4165.37 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: freq_base  = 1000000.0
llama_new_context_with_model: freq_scale = 1
llama_kv_cache_init:      ROCm0 KV buffer size =    48.00 MiB
llama_kv_cache_init:  ROCm_Host KV buffer size =    16.00 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:  ROCm_Host  output buffer size =     0.12 MiB
llama_new_context_with_model:      ROCm0 compute buffer size =   173.04 MiB
llama_new_context_with_model:  ROCm_Host compute buffer size =     9.01 MiB
llama_new_context_with_model: graph nodes  = 1030
llama_new_context_with_model: graph splits = 92

system_info: n_threads = 8 / 16 | AVX = 1 | AVX_VNNI = 0 | AVX2 = 1 | AVX512 = 1 | AVX512_VBMI = 1 | AVX512_VNNI = 1 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 1 | SSE3 = 1 | SSSE3 = 1 | VSX = 0 | MATMUL_INT8 = 0 |
sampling:
        repeat_last_n = 64, repeat_penalty = 1.000, frequency_penalty = 0.000, presence_penalty = 0.000
        top_k = 40, tfs_z = 1.000, top_p = 0.950, min_p = 0.050, typical_p = 1.000, temp = 0.800
        mirostat = 0, mirostat_lr = 0.100, mirostat_ent = 5.000
sampling order:
CFG -> Penalties -> top_k -> tfs_z -> typical_p -> top_p -> min_p -> temperature
generate: n_ctx = 512, n_batch = 2048, n_predict = -1, n_keep = 1


 simple example code for a lit Web Component that reverses a string input

Hi there! Here's a simple example of a Lit Web Component that reverses a string input:

```javascript
import { Component, html, css } from 'lit';

class ReverseString extends Component {
  static styles = css`
    input {
      padding: 10px;
      margin-bottom: 20px;
    }
  `;

  static properties = {
    value: { type: String }
  };

  constructor() {
    super();
    this.value = ;
  }
 
  render() {
    return html`
      <style>${this.constructor.styles}</style>
      <input @input=${this._handleInputChange} value=${this.value} type="text">
      < p>Reversed string: ${this._reverseString(this.value)}< /p>
    `;
  }
 
  _reverseString(str) {
    return str.split().reverse().join();
  }

  _handleInputChange(event) {
    this.value = event.target.value;
  }
}

customElements.define('reverse-string', ReverseString);
```

In this example, we define a custom Web Component called `reverse-string` that uses Lit for rendering and handling user input. The `ReverseString` class defines a render method that returns an HTML template with an input field and a paragraph that displays the reversed string. The component also defines a `_reverseString` method that reverses a given string using the `split`, `reverse`, and `join` array methods, and a `_handleInputChange` method that updates the component's value whenever the input changes. Finally, we use the `customElements.define` method to register our component with the browser.

You can use this component in your HTML like this:

```html
<reverse-string></reverse-string>
``` [end of text]

llama_print_timings:        load time =    2865.16 ms
llama_print_timings:      sample time =      13.64 ms /   442 runs   (    0.03 ms per token, 32407.07 tokens per second)
llama_print_timings: prompt eval time =    1281.98 ms /    14 tokens (   91.57 ms per token,    10.92 tokens per second)
llama_print_timings:        eval time =  100829.12 ms /   441 runs   (  228.64 ms per token,     4.37 tokens per second)
llama_print_timings:       total time =  102397.06 ms /   455 tokens
Log end

It's definitely not going to win any speed prizes even though is a smaller model, but it could be ok for non time sensitive results, or where using a tiny, faster model is useful.



RSS

"April 13 12, 2024" contains more than three components required for a date interpretation. Blikied on April 13 12, 2024