ship Mac-only: remove iPhone int4 (quality not at bar; runs but degraded)
Browse files- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/main.hash +0 -1
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/main.mlirb +0 -3
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/metadata.json +0 -3
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/metadata.json +0 -28
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/chat_template.jinja +0 -115
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/tokenizer.json +0 -3
- gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/tokenizer_config.json +0 -11
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/main.hash
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
���tq�E)-��0_+�������lٚf%
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/main.mlirb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0bb3b2e97471f5184502292dd9eb305f0e2bb1b908bcaa04eed7e26cd99a6625
|
| 3 |
-
size 5073467004
|
|
|
|
|
|
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/lfm2_5_8b_a1b_decode_int4km_gather.aimodel/metadata.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"assetVersion" : "2.0"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/metadata.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"metadata_version": "0.2",
|
| 3 |
-
"kind": "llm",
|
| 4 |
-
"name": "lfm2_5_8b_a1b_decode_int4km_gather",
|
| 5 |
-
"assets": {
|
| 6 |
-
"main": "lfm2_5_8b_a1b_decode_int4km_gather.aimodel"
|
| 7 |
-
},
|
| 8 |
-
"language": {
|
| 9 |
-
"tokenizer": "LiquidAI/LFM2.5-8B-A1B",
|
| 10 |
-
"vocab_size": 128000,
|
| 11 |
-
"max_context_length": 8192,
|
| 12 |
-
"embedded_tokenizer": true,
|
| 13 |
-
"function_map": {
|
| 14 |
-
"main": [
|
| 15 |
-
"main"
|
| 16 |
-
]
|
| 17 |
-
}
|
| 18 |
-
},
|
| 19 |
-
"source": {
|
| 20 |
-
"model_definition": "torch",
|
| 21 |
-
"hf_model_id": "LiquidAI/LFM2.5-8B-A1B"
|
| 22 |
-
},
|
| 23 |
-
"compression": null,
|
| 24 |
-
"compilation": {
|
| 25 |
-
"date": "2026-06-12T15:36:00.145342+00:00",
|
| 26 |
-
"targets": []
|
| 27 |
-
}
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/chat_template.jinja
DELETED
|
@@ -1,115 +0,0 @@
|
|
| 1 |
-
{{- bos_token -}}
|
| 2 |
-
{%- set preserve_thinking = preserve_thinking | default(false) -%}
|
| 3 |
-
|
| 4 |
-
{%- macro format_arg_value(arg_value) -%}
|
| 5 |
-
{%- if arg_value is string -%}
|
| 6 |
-
{{- "'" + arg_value + "'" -}}
|
| 7 |
-
{%- elif arg_value is mapping -%}
|
| 8 |
-
{{- arg_value | tojson -}}
|
| 9 |
-
{%- else -%}
|
| 10 |
-
{{- arg_value | string -}}
|
| 11 |
-
{%- endif -%}
|
| 12 |
-
{%- endmacro -%}
|
| 13 |
-
|
| 14 |
-
{%- macro parse_content(content) -%}
|
| 15 |
-
{%- if content is string -%}
|
| 16 |
-
{{- content -}}
|
| 17 |
-
{%- else -%}
|
| 18 |
-
{%- set _ns = namespace(result="") -%}
|
| 19 |
-
{%- for item in content -%}
|
| 20 |
-
{%- if item["type"] == "image" -%}
|
| 21 |
-
{%- set _ns.result = _ns.result + "<image>" -%}
|
| 22 |
-
{%- elif item["type"] == "text" -%}
|
| 23 |
-
{%- set _ns.result = _ns.result + item["text"] -%}
|
| 24 |
-
{%- else -%}
|
| 25 |
-
{%- set _ns.result = _ns.result + item | tojson -%}
|
| 26 |
-
{%- endif -%}
|
| 27 |
-
{%- endfor -%}
|
| 28 |
-
{{- _ns.result -}}
|
| 29 |
-
{%- endif -%}
|
| 30 |
-
{%- endmacro -%}
|
| 31 |
-
|
| 32 |
-
{%- macro render_tool_calls(tool_calls) -%}
|
| 33 |
-
{%- set tool_calls_ns = namespace(tool_calls=[]) -%}
|
| 34 |
-
{%- for tool_call in tool_calls -%}
|
| 35 |
-
{%- set func_name = tool_call["function"]["name"] -%}
|
| 36 |
-
{%- set func_args = tool_call["function"]["arguments"] -%}
|
| 37 |
-
{%- set args_ns = namespace(arg_strings=[]) -%}
|
| 38 |
-
{%- for arg_name, arg_value in func_args.items() -%}
|
| 39 |
-
{%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
|
| 40 |
-
{%- endfor -%}
|
| 41 |
-
{%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
|
| 42 |
-
{%- endfor -%}
|
| 43 |
-
{{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
|
| 44 |
-
{%- endmacro -%}
|
| 45 |
-
|
| 46 |
-
{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
|
| 47 |
-
{%- if messages[0]["role"] == "system" -%}
|
| 48 |
-
{%- if messages[0].get("content") -%}
|
| 49 |
-
{%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
|
| 50 |
-
{%- endif -%}
|
| 51 |
-
{%- set messages = messages[1:] -%}
|
| 52 |
-
{%- endif -%}
|
| 53 |
-
{%- if tools -%}
|
| 54 |
-
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
| 55 |
-
{%- for tool in tools -%}
|
| 56 |
-
{%- if tool is not string -%}
|
| 57 |
-
{%- set tool = tool | tojson -%}
|
| 58 |
-
{%- endif -%}
|
| 59 |
-
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
| 60 |
-
{%- if not loop.last -%}
|
| 61 |
-
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
| 62 |
-
{%- endif -%}
|
| 63 |
-
{%- endfor -%}
|
| 64 |
-
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
| 65 |
-
{%- endif -%}
|
| 66 |
-
{%- if ns.system_prompt -%}
|
| 67 |
-
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
| 68 |
-
{%- endif -%}
|
| 69 |
-
{%- for message in messages -%}
|
| 70 |
-
{%- if message["role"] == "user" -%}
|
| 71 |
-
{%- set ns.last_user_index = loop.index0 -%}
|
| 72 |
-
{%- endif -%}
|
| 73 |
-
{%- endfor -%}
|
| 74 |
-
{%- for message in messages -%}
|
| 75 |
-
{{- "<|im_start|>" + message.role + "\n" -}}
|
| 76 |
-
{%- if message.role == "assistant" -%}
|
| 77 |
-
{%- generation -%}
|
| 78 |
-
{%- if message.thinking is defined and (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 79 |
-
{{- "<think>" + message.thinking + "</think>" -}}
|
| 80 |
-
{%- endif -%}
|
| 81 |
-
{%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
|
| 82 |
-
{%- set _has_cfm = false -%}
|
| 83 |
-
{%- if message.content is defined -%}
|
| 84 |
-
{%- set content = parse_content(message.content) -%}
|
| 85 |
-
{%- if not (preserve_thinking or loop.index0 > ns.last_user_index) -%}
|
| 86 |
-
{%- if "</think>" in content -%}
|
| 87 |
-
{%- set content = content.split("</think>")[-1] | trim -%}
|
| 88 |
-
{%- endif -%}
|
| 89 |
-
{%- endif -%}
|
| 90 |
-
{%- if message.tool_calls is defined and content.endswith(_cfm_tag) -%}
|
| 91 |
-
{%- set _has_cfm = true -%}
|
| 92 |
-
{%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
|
| 93 |
-
{{- content[:_trunc_len] -}}
|
| 94 |
-
{%- else -%}
|
| 95 |
-
{{- content -}}
|
| 96 |
-
{%- endif -%}
|
| 97 |
-
{%- endif -%}
|
| 98 |
-
{%- if message.tool_calls is defined -%}
|
| 99 |
-
{{- render_tool_calls(message.tool_calls) -}}
|
| 100 |
-
{%- endif -%}
|
| 101 |
-
{%- if _has_cfm -%}
|
| 102 |
-
{{- _cfm_tag -}}
|
| 103 |
-
{%- endif -%}
|
| 104 |
-
{{- "<|im_end|>\n" -}}
|
| 105 |
-
{%- endgeneration -%}
|
| 106 |
-
{%- else %}
|
| 107 |
-
{%- if message.get("content") -%}
|
| 108 |
-
{{- parse_content(message["content"]) -}}
|
| 109 |
-
{%- endif -%}
|
| 110 |
-
{{- "<|im_end|>\n" -}}
|
| 111 |
-
{%- endif %}
|
| 112 |
-
{%- endfor -%}
|
| 113 |
-
{%- if add_generation_prompt -%}
|
| 114 |
-
{{- "<|im_start|>assistant\n" -}}
|
| 115 |
-
{%- endif -%}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/tokenizer.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
|
| 3 |
-
size 17905598
|
|
|
|
|
|
|
|
|
|
|
|
gpu-pipelined/lfm2_5_8b_a1b_decode_int4km_gather/tokenizer/tokenizer_config.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"backend": "tokenizers",
|
| 3 |
-
"bos_token": "<|startoftext|>",
|
| 4 |
-
"clean_up_tokenization_spaces": false,
|
| 5 |
-
"eos_token": "<|im_end|>",
|
| 6 |
-
"is_local": true,
|
| 7 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
-
"pad_token": "<|pad|>",
|
| 9 |
-
"tokenizer_class": "TokenizersBackend",
|
| 10 |
-
"use_default_system_prompt": false
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|