(Trained with Unsloth)
Browse files- chat_template.jinja +45 -0
- config.json +61 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token -}}
|
| 2 |
+
{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
|
| 3 |
+
{%- set ns = namespace(system_prompt="") -%}
|
| 4 |
+
{%- if messages[0]["role"] == "system" -%}
|
| 5 |
+
{%- set ns.system_prompt = messages[0]["content"] -%}
|
| 6 |
+
{%- set messages = messages[1:] -%}
|
| 7 |
+
{%- endif -%}
|
| 8 |
+
{%- if tools -%}
|
| 9 |
+
{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
|
| 10 |
+
{%- for tool in tools -%}
|
| 11 |
+
{%- if tool is not string -%}
|
| 12 |
+
{%- set tool = tool | tojson -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- set ns.system_prompt = ns.system_prompt + tool -%}
|
| 15 |
+
{%- if not loop.last -%}
|
| 16 |
+
{%- set ns.system_prompt = ns.system_prompt + ", " -%}
|
| 17 |
+
{%- endif -%}
|
| 18 |
+
{%- endfor -%}
|
| 19 |
+
{%- set ns.system_prompt = ns.system_prompt + "]" -%}
|
| 20 |
+
{%- endif -%}
|
| 21 |
+
{%- if ns.system_prompt -%}
|
| 22 |
+
{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
|
| 23 |
+
{%- endif -%}
|
| 24 |
+
{%- set ns.last_assistant_index = -1 -%}
|
| 25 |
+
{%- for message in messages -%}
|
| 26 |
+
{%- if message["role"] == "assistant" -%}
|
| 27 |
+
{%- set ns.last_assistant_index = loop.index0 -%}
|
| 28 |
+
{%- endif -%}
|
| 29 |
+
{%- endfor -%}
|
| 30 |
+
{%- for message in messages -%}
|
| 31 |
+
{{- "<|im_start|>" + message["role"] + "\n" -}}
|
| 32 |
+
{%- set content = message["content"] -%}
|
| 33 |
+
{%- if content is not string -%}
|
| 34 |
+
{%- set content = content | tojson -%}
|
| 35 |
+
{%- endif -%}
|
| 36 |
+
{%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
|
| 37 |
+
{%- if "</think>" in content -%}
|
| 38 |
+
{%- set content = content.split("</think>")[-1] | trim -%}
|
| 39 |
+
{%- endif -%}
|
| 40 |
+
{%- endif -%}
|
| 41 |
+
{{- content + "<|im_end|>\n" -}}
|
| 42 |
+
{%- endfor -%}
|
| 43 |
+
{%- if add_generation_prompt -%}
|
| 44 |
+
{{- "<|im_start|>assistant\n" -}}
|
| 45 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Lfm2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"block_auto_adjust_ff_dim": true,
|
| 6 |
+
"block_dim": 2048,
|
| 7 |
+
"block_ff_dim": 12288,
|
| 8 |
+
"block_ffn_dim_multiplier": 1.0,
|
| 9 |
+
"block_mlp_init_scale": 1.0,
|
| 10 |
+
"block_multiple_of": 256,
|
| 11 |
+
"block_norm_eps": 1e-05,
|
| 12 |
+
"block_out_init_scale": 1.0,
|
| 13 |
+
"block_use_swiglu": true,
|
| 14 |
+
"block_use_xavier_init": true,
|
| 15 |
+
"bos_token_id": 1,
|
| 16 |
+
"conv_L_cache": 3,
|
| 17 |
+
"conv_bias": false,
|
| 18 |
+
"conv_dim": 2048,
|
| 19 |
+
"conv_use_xavier_init": true,
|
| 20 |
+
"torch_dtype": "bfloat16",
|
| 21 |
+
"eos_token_id": 7,
|
| 22 |
+
"hidden_size": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 12288,
|
| 25 |
+
"layer_types": [
|
| 26 |
+
"conv",
|
| 27 |
+
"conv",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"conv",
|
| 30 |
+
"conv",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"conv",
|
| 33 |
+
"conv",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"conv",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"conv",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"conv",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"conv"
|
| 42 |
+
],
|
| 43 |
+
"max_position_embeddings": 128000,
|
| 44 |
+
"model_type": "lfm2",
|
| 45 |
+
"norm_eps": 1e-05,
|
| 46 |
+
"num_attention_heads": 32,
|
| 47 |
+
"num_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pad_token_id": 0,
|
| 51 |
+
"rope_parameters": {
|
| 52 |
+
"rope_theta": 1000000.0,
|
| 53 |
+
"rope_type": "default"
|
| 54 |
+
},
|
| 55 |
+
"tie_embedding": true,
|
| 56 |
+
"transformers_version": "5.0.0.dev0",
|
| 57 |
+
"unsloth_version": "2026.1.2",
|
| 58 |
+
"use_cache": false,
|
| 59 |
+
"use_pos_enc": true,
|
| 60 |
+
"vocab_size": 65536
|
| 61 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"bos_token": "<|startoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
+
"eos_token": "<|im_end|>",
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"legacy": false,
|
| 8 |
+
"model_input_names": [
|
| 9 |
+
"input_ids",
|
| 10 |
+
"attention_mask"
|
| 11 |
+
],
|
| 12 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 13 |
+
"model_specific_special_tokens": {},
|
| 14 |
+
"pad_token": "<|pad|>",
|
| 15 |
+
"padding_side": "left",
|
| 16 |
+
"sp_model_kwargs": {},
|
| 17 |
+
"spaces_between_special_tokens": false,
|
| 18 |
+
"tokenizer_class": "TokenizersBackend",
|
| 19 |
+
"use_default_system_prompt": false,
|
| 20 |
+
"use_fast": true,
|
| 21 |
+
"chat_template": "{{- bos_token -}}\n{%- set keep_past_thinking = keep_past_thinking | default(false) -%}\n{%- set ns = namespace(system_prompt=\"\") -%}\n{%- if messages[0][\"role\"] == \"system\" -%}\n {%- set ns.system_prompt = messages[0][\"content\"] -%}\n {%- set messages = messages[1:] -%}\n{%- endif -%}\n{%- if tools -%}\n {%- set ns.system_prompt = ns.system_prompt + (\"\\n\" if ns.system_prompt else \"\") + \"List of tools: [\" -%}\n {%- for tool in tools -%}\n {%- if tool is not string -%}\n {%- set tool = tool | tojson -%}\n {%- endif -%}\n {%- set ns.system_prompt = ns.system_prompt + tool -%}\n {%- if not loop.last -%}\n {%- set ns.system_prompt = ns.system_prompt + \", \" -%}\n {%- endif -%}\n {%- endfor -%}\n {%- set ns.system_prompt = ns.system_prompt + \"]\" -%}\n{%- endif -%}\n{%- if ns.system_prompt -%}\n {{- \"<|im_start|>system\\n\" + ns.system_prompt + \"<|im_end|>\\n\" -}}\n{%- endif -%}\n{%- set ns.last_assistant_index = -1 -%}\n{%- for message in messages -%}\n {%- if message[\"role\"] == \"assistant\" -%}\n {%- set ns.last_assistant_index = loop.index0 -%}\n {%- endif -%}\n{%- endfor -%}\n{%- for message in messages -%}\n {{- \"<|im_start|>\" + message[\"role\"] + \"\\n\" -}}\n {%- set content = message[\"content\"] -%}\n {%- if content is not string -%}\n {%- set content = content | tojson -%}\n {%- endif -%}\n {%- if message[\"role\"] == \"assistant\" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}\n {%- if \"</think>\" in content -%}\n {%- set content = content.split(\"</think>\")[-1] | trim -%}\n {%- endif -%}\n {%- endif -%}\n {{- content + \"<|im_end|>\\n\" -}}\n{%- endfor -%}\n{%- if add_generation_prompt -%}\n {{- \"<|im_start|>assistant\\n\" -}}\n{%- endif -%}"
|
| 22 |
+
}
|