Upload folder using huggingface_hub
Browse files- chat_template.jinja +66 -0
- config.json +41 -0
- generation_config.json +7 -0
- model-00001-of-00021.safetensors +3 -0
- model-00002-of-00021.safetensors +3 -0
- model-00003-of-00021.safetensors +3 -0
- model-00004-of-00021.safetensors +3 -0
- model-00005-of-00021.safetensors +3 -0
- model-00006-of-00021.safetensors +3 -0
- model-00007-of-00021.safetensors +3 -0
- model-00008-of-00021.safetensors +3 -0
- model-00009-of-00021.safetensors +3 -0
- model-00010-of-00021.safetensors +3 -0
- model-00011-of-00021.safetensors +3 -0
- model-00012-of-00021.safetensors +3 -0
- model-00013-of-00021.safetensors +3 -0
- model-00014-of-00021.safetensors +3 -0
- model-00015-of-00021.safetensors +3 -0
- model-00016-of-00021.safetensors +3 -0
- model-00017-of-00021.safetensors +3 -0
- model-00018-of-00021.safetensors +3 -0
- model-00019-of-00021.safetensors +3 -0
- model-00020-of-00021.safetensors +3 -0
- model-00021-of-00021.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +45 -0
- tokenizer.json +0 -0
- tokenizer_config.json +257 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if bos_token is defined and bos_token is not none %}{{- bos_token -}}{%- endif %}
|
| 2 |
+
{%- if tools %}
|
| 3 |
+
{{- '<|im_start|>system\n' }}
|
| 4 |
+
{%- if messages|length > 0 and messages[0].role == 'system' %}
|
| 5 |
+
{{- messages[0].content + '\n\n' }}
|
| 6 |
+
{%- endif %}
|
| 7 |
+
{{- "# 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>" }}
|
| 8 |
+
{%- for tool in tools %}
|
| 9 |
+
{{- "\n" }}
|
| 10 |
+
{{- tool | tojson }}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{{- "\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" }}
|
| 13 |
+
{%- else %}
|
| 14 |
+
{%- if messages|length > 0 and messages[0].role == 'system' %}
|
| 15 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 19 |
+
{%- for message in messages[::-1] %}
|
| 20 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 21 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 22 |
+
{%- set ns.multi_step_tool = false %}
|
| 23 |
+
{%- set ns.last_query_index = index %}
|
| 24 |
+
{%- endif %}
|
| 25 |
+
{%- endfor %}
|
| 26 |
+
{%- for message in messages %}
|
| 27 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 28 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 29 |
+
{%- elif message.role == "assistant" %}
|
| 30 |
+
{%- set content = message.content %}
|
| 31 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 32 |
+
{%- if message.tool_calls %}
|
| 33 |
+
{%- for tool_call in message.tool_calls %}
|
| 34 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 35 |
+
{{- '\n' }}
|
| 36 |
+
{%- endif %}
|
| 37 |
+
{%- if tool_call.function %}
|
| 38 |
+
{%- set tool_call = tool_call.function %}
|
| 39 |
+
{%- endif %}
|
| 40 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 41 |
+
{{- tool_call.name }}
|
| 42 |
+
{{- '", "arguments": ' }}
|
| 43 |
+
{%- if tool_call.arguments is string %}
|
| 44 |
+
{{- tool_call.arguments }}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- tool_call.arguments | tojson }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{{- '}\n</tool_call>' }}
|
| 49 |
+
{%- endfor %}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{{- '<|im_end|>\n' }}
|
| 52 |
+
{%- elif message.role == "tool" %}
|
| 53 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 54 |
+
{{- '<|im_start|>user' }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '\n<tool_response>\n' }}
|
| 57 |
+
{{- message.content }}
|
| 58 |
+
{{- '\n</tool_response>' }}
|
| 59 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- endif %}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{%- if add_generation_prompt %}
|
| 65 |
+
{{- '<|im_start|>assistant\n' }}
|
| 66 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"JambaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"attn_layer_offset": 4,
|
| 7 |
+
"attn_layer_period": 8,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"eos_token_id": 519,
|
| 11 |
+
"expert_layer_offset": 1,
|
| 12 |
+
"expert_layer_period": 2,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 4096,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 14336,
|
| 17 |
+
"mamba_conv_bias": true,
|
| 18 |
+
"mamba_d_conv": 4,
|
| 19 |
+
"mamba_d_state": 16,
|
| 20 |
+
"mamba_dt_rank": 256,
|
| 21 |
+
"mamba_expand": 2,
|
| 22 |
+
"mamba_proj_bias": false,
|
| 23 |
+
"max_position_embeddings": 262144,
|
| 24 |
+
"model_type": "jamba",
|
| 25 |
+
"num_attention_heads": 32,
|
| 26 |
+
"num_experts": 16,
|
| 27 |
+
"num_experts_per_tok": 2,
|
| 28 |
+
"num_hidden_layers": 32,
|
| 29 |
+
"num_key_value_heads": 8,
|
| 30 |
+
"num_logits_to_keep": 1,
|
| 31 |
+
"output_router_logits": false,
|
| 32 |
+
"pad_token_id": 0,
|
| 33 |
+
"rms_norm_eps": 1e-06,
|
| 34 |
+
"router_aux_loss_coef": 0.001,
|
| 35 |
+
"sliding_window": null,
|
| 36 |
+
"tie_word_embeddings": false,
|
| 37 |
+
"transformers_version": "4.56.1",
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"use_mamba_kernels": true,
|
| 40 |
+
"vocab_size": 65536
|
| 41 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.56.1"
|
| 7 |
+
}
|
model-00001-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb2d0eb53e408d95ff5b3362c90b4ccb26312e76671c70d9a3e20b2af9183ae9
|
| 3 |
+
size 4976132240
|
model-00002-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9062c03810292f47eb6eceaf705719bd0da3e8d11749527f70c3fe5a34cc7a37
|
| 3 |
+
size 4915879064
|
model-00003-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f21b79e58fd11c70ef89648f84dcb3cd11e6bcad01d1eecab7c70d29a97bf2e7
|
| 3 |
+
size 4976148368
|
model-00004-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b64afd60f838459de1a9a05828cdbece770e91d875ba626aa313f35474a9949e
|
| 3 |
+
size 4908563840
|
model-00005-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5468721ccbb479f38a55fde0281df3ac37c2fc9e1b3db8ed7215e67c9943ab36
|
| 3 |
+
size 4900103160
|
model-00006-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc12ff1820fb5955ce9a133a642abf2a1ed1aec7fdc24a26e0ad2075cff67a2d
|
| 3 |
+
size 4899462728
|
model-00007-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3179392697f759c9581e546f948d0e32afc0f41eec9fde1bb64041871f826763
|
| 3 |
+
size 4931429728
|
model-00008-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98171c6436f072b7e1cf2eef651dbba0946fdd5ec0c530c9ccd7384704fe5afa
|
| 3 |
+
size 4887322400
|
model-00009-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95cd600b773da63302de04cfed3eea078af03fd670dc81051ef531d85a80defe
|
| 3 |
+
size 4997054416
|
model-00010-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1966f006892b5bd1c533bd81fc315b2f69953286f2755dbaf3e59d6956341f5
|
| 3 |
+
size 4909244752
|
model-00011-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6aa4195f51341d89314d745b7d9d360e70cdb58146b97c429dd385e4470fff1a
|
| 3 |
+
size 4887175464
|
model-00012-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5815cf84fc1bc793d172ed86b02868eda0fa06dc3699257200714b2125a15b8
|
| 3 |
+
size 4912200296
|
model-00013-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ff06d00ae7ea5ff332cefe7721bc1f3640df54be2a91c640b34968940924de2
|
| 3 |
+
size 4937702464
|
model-00014-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f249bea1ec5346f984af28424859fcb04494289b8e066384f50a14abbdc2a9f7
|
| 3 |
+
size 4888026832
|
model-00015-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:28efc43c462fea37852d4f1f6da47a72b5bc813dee984a77d157ec6af08443f4
|
| 3 |
+
size 4916657824
|
model-00016-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd758a46eeeef9774737e52f24fadc29d148ad73bb179f3bd194a2497d1c4dea
|
| 3 |
+
size 4883808864
|
model-00017-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:910e92e9b42d8ddf21bd44bda6d1991229cbd15d6d14ac7c0bf9378457a3d5bd
|
| 3 |
+
size 4899988024
|
model-00018-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:272d9e2f73857eff3c379924913b4ccda7f5befcac1063b2750e008b7043b54d
|
| 3 |
+
size 4950991480
|
model-00019-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b71bca1fc08474d950bd5e4fb2ecb5fe36ab2f1555a8385e93686dbcd7f7f89
|
| 3 |
+
size 4904674336
|
model-00020-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05a100caaa7a5ecccaec357630e9833fe13c2c269cdf18fc3f6bad2fcbc8db29
|
| 3 |
+
size 4992097232
|
model-00021-of-00021.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:daf5f9011e0609311f28b20e15221d0e6158fc0a72189a4dd39effa4ab3c4d86
|
| 3 |
+
size 4666140744
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"bos_token": {
|
| 18 |
+
"content": "<|startoftext|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"eos_token": {
|
| 25 |
+
"content": "<|im_end|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"pad_token": {
|
| 32 |
+
"content": "<|pad|>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|unk|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,257 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|pad|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|startoftext|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"3": {
|
| 23 |
+
"content": "<|unk|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"518": {
|
| 31 |
+
"content": "<|im_start|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"519": {
|
| 39 |
+
"content": "<|im_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"520": {
|
| 47 |
+
"content": "<|object_ref_start|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"521": {
|
| 55 |
+
"content": "<|object_ref_end|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"522": {
|
| 63 |
+
"content": "<|box_start|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"523": {
|
| 71 |
+
"content": "<|box_end|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"524": {
|
| 79 |
+
"content": "<|quad_start|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"525": {
|
| 87 |
+
"content": "<|quad_end|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"526": {
|
| 95 |
+
"content": "<|vision_start|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": true
|
| 101 |
+
},
|
| 102 |
+
"527": {
|
| 103 |
+
"content": "<|vision_end|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": true
|
| 109 |
+
},
|
| 110 |
+
"528": {
|
| 111 |
+
"content": "<|vision_pad|>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"529": {
|
| 119 |
+
"content": "<|image_pad|>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"530": {
|
| 127 |
+
"content": "<|video_pad|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"531": {
|
| 135 |
+
"content": "<tool_call>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"532": {
|
| 143 |
+
"content": "</tool_call>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"533": {
|
| 151 |
+
"content": "<|fim_prefix|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"534": {
|
| 159 |
+
"content": "<|fim_middle|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"535": {
|
| 167 |
+
"content": "<|fim_suffix|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"536": {
|
| 175 |
+
"content": "<|fim_pad|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"537": {
|
| 183 |
+
"content": "<|repo_name|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"538": {
|
| 191 |
+
"content": "<|file_sep|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"539": {
|
| 199 |
+
"content": "<tool_response>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
},
|
| 206 |
+
"540": {
|
| 207 |
+
"content": "</tool_response>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": false
|
| 213 |
+
},
|
| 214 |
+
"541": {
|
| 215 |
+
"content": "<think>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": false
|
| 221 |
+
},
|
| 222 |
+
"542": {
|
| 223 |
+
"content": "</think>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": false
|
| 229 |
+
}
|
| 230 |
+
},
|
| 231 |
+
"additional_special_tokens": [
|
| 232 |
+
"<|im_start|>",
|
| 233 |
+
"<|im_end|>",
|
| 234 |
+
"<|object_ref_start|>",
|
| 235 |
+
"<|object_ref_end|>",
|
| 236 |
+
"<|box_start|>",
|
| 237 |
+
"<|box_end|>",
|
| 238 |
+
"<|quad_start|>",
|
| 239 |
+
"<|quad_end|>",
|
| 240 |
+
"<|vision_start|>",
|
| 241 |
+
"<|vision_end|>",
|
| 242 |
+
"<|vision_pad|>",
|
| 243 |
+
"<|image_pad|>",
|
| 244 |
+
"<|video_pad|>"
|
| 245 |
+
],
|
| 246 |
+
"bos_token": "<|startoftext|>",
|
| 247 |
+
"clean_up_tokenization_spaces": false,
|
| 248 |
+
"eos_token": "<|im_end|>",
|
| 249 |
+
"extra_special_tokens": {},
|
| 250 |
+
"legacy": true,
|
| 251 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 252 |
+
"pad_token": "<|pad|>",
|
| 253 |
+
"spaces_between_special_tokens": false,
|
| 254 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 255 |
+
"unk_token": "<|unk|>",
|
| 256 |
+
"use_default_system_prompt": false
|
| 257 |
+
}
|