Audio-Text-to-Text
Transformers
Safetensors
English
Korean
fastslm
feature-extraction
audio
text-generation
custom_code
Eval Results
Instructions to use okestro-ai-lab/FastSLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use okestro-ai-lab/FastSLM with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("okestro-ai-lab/FastSLM", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload FastALM model (hf_model folder)
Browse files- .ipynb_checkpoints/config-checkpoint.json +30 -0
- __init__.py +7 -0
- __pycache__/__init__.cpython-310.pyc +0 -0
- __pycache__/configuration_fast_alm.cpython-310.pyc +0 -0
- __pycache__/configuration_fastalm.cpython-310.pyc +0 -0
- __pycache__/modeling_fast_alm.cpython-310.pyc +0 -0
- __pycache__/modeling_fastalm.cpython-310.pyc +0 -0
- __pycache__/modeling_whisper.cpython-310.pyc +0 -0
- chat_template.jinja +89 -0
- config.json +1 -1
- generation_config.json +8 -1
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"FastALMForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"compression_size": 50,
|
| 6 |
+
"embed_dim": 2560,
|
| 7 |
+
"encoder_mode": "large-v3",
|
| 8 |
+
"llm_modules": [
|
| 9 |
+
"q_proj",
|
| 10 |
+
"k_proj",
|
| 11 |
+
"v_proj",
|
| 12 |
+
"o_proj",
|
| 13 |
+
"gate_proj",
|
| 14 |
+
"up_proj",
|
| 15 |
+
"down_proj"
|
| 16 |
+
],
|
| 17 |
+
"lora": true,
|
| 18 |
+
"lora_a": 64,
|
| 19 |
+
"lora_r": 16,
|
| 20 |
+
"model_name": "Qwen/Qwen3-4B",
|
| 21 |
+
"model_type": "fastalm",
|
| 22 |
+
"speech_dim": 1280,
|
| 23 |
+
"stage_tokens": [
|
| 24 |
+
80,
|
| 25 |
+
80,
|
| 26 |
+
80
|
| 27 |
+
],
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.53.1"
|
| 30 |
+
}
|
__init__.py
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from .configuration_fastalm import FastALMConfig
|
| 2 |
+
from .modeling_fastalm import FastALMForConditionalGeneration # FastALMForCausalLM
|
| 3 |
+
|
| 4 |
+
from transformers import AutoConfig, AutoModelForCausalLM
|
| 5 |
+
|
| 6 |
+
AutoConfig.register("fastalm", FastALMConfig)
|
| 7 |
+
AutoModelForCausalLM.register(FastALMConfig, FastALMForConditionalGeneration)
|
__pycache__/__init__.cpython-310.pyc
ADDED
|
Binary file (395 Bytes). View file
|
|
|
__pycache__/configuration_fast_alm.cpython-310.pyc
ADDED
|
Binary file (1.16 kB). View file
|
|
|
__pycache__/configuration_fastalm.cpython-310.pyc
ADDED
|
Binary file (1.7 kB). View file
|
|
|
__pycache__/modeling_fast_alm.cpython-310.pyc
ADDED
|
Binary file (14.8 kB). View file
|
|
|
__pycache__/modeling_fastalm.cpython-310.pyc
ADDED
|
Binary file (15.7 kB). View file
|
|
|
__pycache__/modeling_whisper.cpython-310.pyc
ADDED
|
Binary file (7.01 kB). View file
|
|
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
],
|
| 5 |
"encoder_config": {
|
| 6 |
"compression_size": 50,
|
|
|
|
| 7 |
"model_type": "fastalm_speech_encoder",
|
| 8 |
"n_ctx": 1500,
|
| 9 |
"n_head": 20,
|
|
@@ -57,7 +58,6 @@
|
|
| 57 |
],
|
| 58 |
"lora_a": 64,
|
| 59 |
"lora_r": 16,
|
| 60 |
-
"low_resource": false,
|
| 61 |
"model_type": "fastalm",
|
| 62 |
"torch_dtype": "float32",
|
| 63 |
"transformers_version": "4.51.3"
|
|
|
|
| 4 |
],
|
| 5 |
"encoder_config": {
|
| 6 |
"compression_size": 50,
|
| 7 |
+
"low_resource": false,
|
| 8 |
"model_type": "fastalm_speech_encoder",
|
| 9 |
"n_ctx": 1500,
|
| 10 |
"n_head": 20,
|
|
|
|
| 58 |
],
|
| 59 |
"lora_a": 64,
|
| 60 |
"lora_r": 16,
|
|
|
|
| 61 |
"model_type": "fastalm",
|
| 62 |
"torch_dtype": "float32",
|
| 63 |
"transformers_version": "4.51.3"
|
generation_config.json
CHANGED
|
@@ -1,4 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"transformers_version": "4.51.3"
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": 151645,
|
| 4 |
+
"max_new_tokens": 512,
|
| 5 |
+
"bos_token_id":151644,
|
| 6 |
+
"pad_token_id": 151643,
|
| 7 |
+
"temperature": 0.2,
|
| 8 |
+
"top_k": 20,
|
| 9 |
+
"top_p": 0.95,
|
| 10 |
"transformers_version": "4.51.3"
|
| 11 |
}
|
model-00001-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4954711528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:426986e9842279f5c1f36a7047b342aa0d8081ec3255567e5081eb35098710ea
|
| 3 |
size 4954711528
|
model-00002-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4983450856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6c8e338a248d5a5866942c4e5ebcbc8770ee233abb547d42d1128080bd700fd
|
| 3 |
size 4983450856
|
model-00003-of-00003.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1805593888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b14003d714cf0227c8d220d4c9bbe3d1ecbc72065023d6c76de8bc39ac0463c
|
| 3 |
size 1805593888
|