Update binary files

#2
by Alcpz - opened
README.md CHANGED
@@ -49,27 +49,21 @@ Optionally, float16 ggufs can be downloaded and used by replacing `Q8_0` with `F
49
 
50
  ## Binaries
51
 
52
- `runners` folder contain runners for ubuntu-x64 and macos-arm64.
53
  ```console
54
  runners
55
  β”œβ”€β”€ android-arm64
56
- β”‚Β Β  └── bin
57
- β”‚Β Β  β”œβ”€β”€ llama-lfm2-audio
58
- β”‚Β Β  └── llama-mtmd-cli
59
  β”œβ”€β”€ macos-arm64
60
- β”‚Β Β  └── bin
61
- β”‚Β Β  β”œβ”€β”€ llama-lfm2-audio
62
- β”‚Β Β  └── llama-mtmd-cli
63
  β”œβ”€β”€ ubuntu-arm64
64
- β”‚Β Β  └── bin
65
- β”‚Β Β  β”œβ”€β”€ llama-lfm2-audio
66
- β”‚Β Β  └── llama-mtmd-cli
67
  └── ubuntu-x64
68
- └── bin
69
- β”œβ”€β”€ llama-lfm2-audio
70
- └── llama-mtmd-cli
71
  ```
72
 
 
 
73
  ## Run using `llama-lfm2-audio`
74
 
75
  There are 3 supported modes
@@ -84,14 +78,14 @@ The mode is defined by system prompt. There are limitations on system prompt and
84
  ASR requires `-sys "Perform ASR."` and `--audio audio.wav` for input. It will print text to console
85
 
86
  ```console
87
- bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform ASR." --audio $INPUT_WAV
88
  ```
89
 
90
  ### TTS
91
 
92
  TTS requires `-sys "Perform TTS."`, `-p "What is this obsession people have with books?"` for input, and `--output output.wav` for output. It will save audio to `output.wav`.
93
  ```console
94
- bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform TTS." -p "What is this obsession people have with books?" --output $OUTPUT_WAV
95
  ```
96
 
97
  ### Interleaved
@@ -99,7 +93,7 @@ bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-au
99
  Interleaved produces both, text and audio as output, and can consume text or audio as input.
100
 
101
  ```console
102
- bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Respond with interleaved text and audio." --audio $INPUT_WAV --output $OUTPUT_WAV
103
  ```
104
 
105
  ## Run ASR using `llama-mtmd-cli`
@@ -107,7 +101,7 @@ bin/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-au
107
  Build `llama-mtmd-cli` following the standard build procedure.
108
 
109
  ```console
110
- bin/llama-mtmd-cli -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -p "<__media__>" -sys "Perform ASR." --audio $INPUT_WAV
111
  ```
112
 
113
  ### Debug
 
49
 
50
  ## Binaries
51
 
52
+ `runners` folder contain runners for andoird-arm64, macos-arm64, ubuntu-arm64, and ubuntu-x64.
53
  ```console
54
  runners
55
  β”œβ”€β”€ android-arm64
56
+ β”‚ └── lfm2-audio-android-arm64.zip
 
 
57
  β”œβ”€β”€ macos-arm64
58
+ β”‚ └── lfm2-audio-macos-arm64.zip
 
 
59
  β”œβ”€β”€ ubuntu-arm64
60
+ β”‚ └── lfm2-audio-ubuntu-arm64.zip
 
 
61
  └── ubuntu-x64
62
+ └── lfm2-audio-ubuntu-x64.zip
 
 
63
  ```
64
 
65
+ Each package contains `llama-lfm2-audio` and `llama-mtmd-cli` binaries.
66
+
67
  ## Run using `llama-lfm2-audio`
68
 
69
  There are 3 supported modes
 
78
  ASR requires `-sys "Perform ASR."` and `--audio audio.wav` for input. It will print text to console
79
 
80
  ```console
81
+ lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform ASR." --audio $INPUT_WAV
82
  ```
83
 
84
  ### TTS
85
 
86
  TTS requires `-sys "Perform TTS."`, `-p "What is this obsession people have with books?"` for input, and `--output output.wav` for output. It will save audio to `output.wav`.
87
  ```console
88
+ lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Perform TTS." -p "What is this obsession people have with books?" --output $OUTPUT_WAV
89
  ```
90
 
91
  ### Interleaved
 
93
  Interleaved produces both, text and audio as output, and can consume text or audio as input.
94
 
95
  ```console
96
+ lfm2-audio-<platform>/llama-lfm2-audio -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -mv $CKPT/audiodecoder-LFM2-Audio-1.5B-Q8_0.gguf -sys "Respond with interleaved text and audio." --audio $INPUT_WAV --output $OUTPUT_WAV
97
  ```
98
 
99
  ## Run ASR using `llama-mtmd-cli`
 
101
  Build `llama-mtmd-cli` following the standard build procedure.
102
 
103
  ```console
104
+ lfm2-audio-<platform>/llama-mtmd-cli -m $CKPT/LFM2-Audio-1.5B-Q8_0.gguf --mmproj $CKPT/mmproj-audioencoder-LFM2-Audio-1.5B-Q8_0.gguf -p "<__media__>" -sys "Perform ASR." --audio $INPUT_WAV
105
  ```
106
 
107
  ### Debug
runners/android-arm64/{bin/llama-lfm2-audio β†’ lfm2-audio-android-arm64.zip} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f97aa5aa27164d62aa27e40475af842ac42a82e02ac6c8254e60c5038c44791
3
- size 5044440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf22f0ea2598adf9e686720d33a7ad180368b272e297d1186e72d545a547c80
3
+ size 4159454
runners/{android-arm64/bin/llama-mtmd-cli β†’ macos-arm64/lfm2-audio-macos-arm64.zip} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81486d06bd9665966e1507e00a87c9435738504ee9a373e57a391e386232cad4
3
- size 5003512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cd724550d2518c33d5a0bf6c452da921299a0420f07ede80fb06695d541786b
3
+ size 3462697
runners/ubuntu-arm64/bin/llama-lfm2-audio DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fdc95d710e7be853a718aa197dad984104abc093b75520ada0aa1c5d6fe681e
3
- size 7090768
 
 
 
 
runners/ubuntu-arm64/bin/llama-mtmd-cli DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fdf69405afcc6ec9fe92a392bb230d3a604b6866449d97723926b5e051a1fb
3
- size 7090768
 
 
 
 
runners/{macos-arm64/bin/llama-lfm2-audio β†’ ubuntu-arm64/lfm2-audio-ubuntu-arm64.zip} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:78278a3efd856219a1bd3a511765aaff728dbd523875f8e060f254a473b03f7f
3
- size 6250368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53a14a2b2c4fc480f202100dda9fdf8268f88b8e655dbf688396ca3e4fdea925
3
+ size 5232143
runners/ubuntu-x64/bin/llama-lfm2-audio DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:778f8ac2bbed5b9493ba34f7d1c3fbe8c8367976d956f589adcda7be186402e6
3
- size 6260480
 
 
 
 
runners/ubuntu-x64/bin/llama-mtmd-cli DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:86626d7b7f10344bc1a9c8eed4685b34dc8b76c05ac4d87189483eac357aba87
3
- size 6178528
 
 
 
 
runners/{macos-arm64/bin/llama-mtmd-cli β†’ ubuntu-x64/lfm2-audio-ubuntu-x64.zip} RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1abdc10cc3fc1297504ae05d83f8db3cf2cc133f21aa9924117a8af69c2a177d
3
- size 6185872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f76116e2a4010de10fc5a61a0da5f77020a465478e18ac7fcdabde8e47ebe05
3
+ size 6282015