Add NVFP4 quantized checkpoint
Browse files- .gitattributes +1 -0
- README.md +23 -0
- chat_template.jinja +103 -0
- config.json +89 -0
- generation_config.json +11 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +0 -0
- recipe.yaml +6 -0
- special_tokens_map.json +40 -0
- tokenizer.json +3 -0
- tokenizer_config.json +325 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- Rombo-Org/Optimized_Reasoning
|
| 4 |
+
base_model:
|
| 5 |
+
- zai-org/GLM-4.5-Air
|
| 6 |
+
---
|
| 7 |
+
# GLM-4.5-Air-nvfp4
|
| 8 |
+
|
| 9 |
+
**Format:** NVFP4 — weights & activations quantized to FP4 with dual scaling.
|
| 10 |
+
**Base model:** `zai-org/GLM-4.5-Air`
|
| 11 |
+
**How it was made:** One-shot calibration with LLM Compressor (NVFP4 recipe), long-seq calibration with Rombo-Org/Optimized_Reasoning.
|
| 12 |
+
|
| 13 |
+
> Notes: Keep `lm_head` in high precision; calibrate on long, domain-relevant sequences.
|
| 14 |
+
|
| 15 |
+
Check the original model card for information about this model.
|
| 16 |
+
|
| 17 |
+
# Running the model with VLLM in Docker
|
| 18 |
+
```sh
|
| 19 |
+
sudo docker run --runtime nvidia --gpus all -p 8000:8000 --ipc=host vllm/vllm-openai:nightly --model Firworks/GLM-4.5-Air-nvfp4 --dtype auto --max-model-len 32768
|
| 20 |
+
```
|
| 21 |
+
This was tested on a B200 cloud instance.
|
| 22 |
+
|
| 23 |
+
If there are other models you're interested in seeing quantized to NVFP4 for use on the DGX Spark, or other modern Blackwell (or newer) cards let me know. I'm trying to make more NVFP4 models available to allow more people to try them out.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[gMASK]<sop>
|
| 2 |
+
{%- if tools -%}
|
| 3 |
+
<|system|>
|
| 4 |
+
# Tools
|
| 5 |
+
|
| 6 |
+
You may call one or more functions to assist with the user query.
|
| 7 |
+
|
| 8 |
+
You are provided with function signatures within <tools></tools> XML tags:
|
| 9 |
+
<tools>
|
| 10 |
+
{% for tool in tools %}
|
| 11 |
+
{{ tool | tojson(ensure_ascii=False) }}
|
| 12 |
+
{% endfor %}
|
| 13 |
+
</tools>
|
| 14 |
+
|
| 15 |
+
For each function call, output the function name and arguments within the following XML format:
|
| 16 |
+
<tool_call>{function-name}
|
| 17 |
+
<arg_key>{arg-key-1}</arg_key>
|
| 18 |
+
<arg_value>{arg-value-1}</arg_value>
|
| 19 |
+
<arg_key>{arg-key-2}</arg_key>
|
| 20 |
+
<arg_value>{arg-value-2}</arg_value>
|
| 21 |
+
...
|
| 22 |
+
</tool_call>{%- endif -%}
|
| 23 |
+
{%- macro visible_text(content) -%}
|
| 24 |
+
{%- if content is string -%}
|
| 25 |
+
{{- content }}
|
| 26 |
+
{%- elif content is iterable and content is not mapping -%}
|
| 27 |
+
{%- for item in content -%}
|
| 28 |
+
{%- if item is mapping and item.type == 'text' -%}
|
| 29 |
+
{{- item.text }}
|
| 30 |
+
{%- elif item is string -%}
|
| 31 |
+
{{- item }}
|
| 32 |
+
{%- endif -%}
|
| 33 |
+
{%- endfor -%}
|
| 34 |
+
{%- else -%}
|
| 35 |
+
{{- content }}
|
| 36 |
+
{%- endif -%}
|
| 37 |
+
{%- endmacro -%}
|
| 38 |
+
{%- set ns = namespace(last_user_index=-1) %}
|
| 39 |
+
{%- for m in messages %}
|
| 40 |
+
{%- if m.role == 'user' %}
|
| 41 |
+
{% set ns.last_user_index = loop.index0 -%}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- endfor %}
|
| 44 |
+
{% for m in messages %}
|
| 45 |
+
{%- if m.role == 'user' -%}<|user|>
|
| 46 |
+
{{ visible_text(m.content) }}
|
| 47 |
+
{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}}
|
| 48 |
+
{%- elif m.role == 'assistant' -%}
|
| 49 |
+
<|assistant|>
|
| 50 |
+
{%- set reasoning_content = '' %}
|
| 51 |
+
{%- set content = visible_text(m.content) %}
|
| 52 |
+
{%- if m.reasoning_content is string %}
|
| 53 |
+
{%- set reasoning_content = m.reasoning_content %}
|
| 54 |
+
{%- else %}
|
| 55 |
+
{%- if '</think>' in content %}
|
| 56 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 57 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{%- if loop.index0 > ns.last_user_index and reasoning_content -%}
|
| 61 |
+
{{ '\n<think>' + reasoning_content.strip() + '</think>'}}
|
| 62 |
+
{%- else -%}
|
| 63 |
+
{{ '\n<think></think>' }}
|
| 64 |
+
{%- endif -%}
|
| 65 |
+
{%- if content.strip() -%}
|
| 66 |
+
{{ '\n' + content.strip() }}
|
| 67 |
+
{%- endif -%}
|
| 68 |
+
{% if m.tool_calls %}
|
| 69 |
+
{% for tc in m.tool_calls %}
|
| 70 |
+
{%- if tc.function %}
|
| 71 |
+
{%- set tc = tc.function %}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{{ '\n<tool_call>' + tc.name }}
|
| 74 |
+
{% set _args = tc.arguments %}
|
| 75 |
+
{% for k, v in _args.items() %}
|
| 76 |
+
<arg_key>{{ k }}</arg_key>
|
| 77 |
+
<arg_value>{{ v | tojson(ensure_ascii=False) if v is not string else v }}</arg_value>
|
| 78 |
+
{% endfor %}
|
| 79 |
+
</tool_call>{% endfor %}
|
| 80 |
+
{% endif %}
|
| 81 |
+
{%- elif m.role == 'tool' -%}
|
| 82 |
+
{%- if m.content is string -%}
|
| 83 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 84 |
+
{{- '<|observation|>' }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '\n<tool_response>\n' }}
|
| 87 |
+
{{- m.content }}
|
| 88 |
+
{{- '\n</tool_response>' }}
|
| 89 |
+
{%- else -%}
|
| 90 |
+
<|observation|>{% for tr in m.content %}
|
| 91 |
+
|
| 92 |
+
<tool_response>
|
| 93 |
+
{{ tr.output if tr.output is defined else tr }}
|
| 94 |
+
</tool_response>{% endfor -%}
|
| 95 |
+
{% endif -%}
|
| 96 |
+
{%- elif m.role == 'system' -%}
|
| 97 |
+
<|system|>
|
| 98 |
+
{{ visible_text(m.content) }}
|
| 99 |
+
{%- endif -%}
|
| 100 |
+
{%- endfor -%}
|
| 101 |
+
{%- if add_generation_prompt -%}
|
| 102 |
+
<|assistant|>{{- '\n<think></think>' if (enable_thinking is defined and not enable_thinking) else '' -}}
|
| 103 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Glm4MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": true,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": [
|
| 9 |
+
151329,
|
| 10 |
+
151336,
|
| 11 |
+
151338
|
| 12 |
+
],
|
| 13 |
+
"first_k_dense_replace": 1,
|
| 14 |
+
"head_dim": 128,
|
| 15 |
+
"hidden_act": "silu",
|
| 16 |
+
"hidden_size": 4096,
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 10944,
|
| 19 |
+
"max_position_embeddings": 131072,
|
| 20 |
+
"model_type": "glm4_moe",
|
| 21 |
+
"moe_intermediate_size": 1408,
|
| 22 |
+
"n_group": 1,
|
| 23 |
+
"n_routed_experts": 128,
|
| 24 |
+
"n_shared_experts": 1,
|
| 25 |
+
"norm_topk_prob": true,
|
| 26 |
+
"num_attention_heads": 96,
|
| 27 |
+
"num_experts_per_tok": 8,
|
| 28 |
+
"num_hidden_layers": 46,
|
| 29 |
+
"num_key_value_heads": 8,
|
| 30 |
+
"num_nextn_predict_layers": 1,
|
| 31 |
+
"pad_token_id": 151329,
|
| 32 |
+
"partial_rotary_factor": 0.5,
|
| 33 |
+
"quantization_config": {
|
| 34 |
+
"config_groups": {
|
| 35 |
+
"group_0": {
|
| 36 |
+
"format": "nvfp4-pack-quantized",
|
| 37 |
+
"input_activations": {
|
| 38 |
+
"actorder": null,
|
| 39 |
+
"block_structure": null,
|
| 40 |
+
"dynamic": "local",
|
| 41 |
+
"group_size": 16,
|
| 42 |
+
"num_bits": 4,
|
| 43 |
+
"observer": "minmax",
|
| 44 |
+
"observer_kwargs": {},
|
| 45 |
+
"strategy": "tensor_group",
|
| 46 |
+
"symmetric": true,
|
| 47 |
+
"type": "float"
|
| 48 |
+
},
|
| 49 |
+
"output_activations": null,
|
| 50 |
+
"targets": [
|
| 51 |
+
"Linear"
|
| 52 |
+
],
|
| 53 |
+
"weights": {
|
| 54 |
+
"actorder": null,
|
| 55 |
+
"block_structure": null,
|
| 56 |
+
"dynamic": false,
|
| 57 |
+
"group_size": 16,
|
| 58 |
+
"num_bits": 4,
|
| 59 |
+
"observer": "minmax",
|
| 60 |
+
"observer_kwargs": {},
|
| 61 |
+
"strategy": "tensor_group",
|
| 62 |
+
"symmetric": true,
|
| 63 |
+
"type": "float"
|
| 64 |
+
}
|
| 65 |
+
}
|
| 66 |
+
},
|
| 67 |
+
"format": "nvfp4-pack-quantized",
|
| 68 |
+
"global_compression_ratio": null,
|
| 69 |
+
"ignore": [
|
| 70 |
+
"lm_head"
|
| 71 |
+
],
|
| 72 |
+
"kv_cache_scheme": null,
|
| 73 |
+
"quant_method": "compressed-tensors",
|
| 74 |
+
"quantization_status": "compressed",
|
| 75 |
+
"sparsity_config": {},
|
| 76 |
+
"transform_config": {},
|
| 77 |
+
"version": "0.12.2"
|
| 78 |
+
},
|
| 79 |
+
"rms_norm_eps": 1e-05,
|
| 80 |
+
"rope_scaling": null,
|
| 81 |
+
"rope_theta": 1000000,
|
| 82 |
+
"routed_scaling_factor": 1.0,
|
| 83 |
+
"tie_word_embeddings": false,
|
| 84 |
+
"topk_group": 1,
|
| 85 |
+
"transformers_version": "4.56.2",
|
| 86 |
+
"use_cache": true,
|
| 87 |
+
"use_qk_norm": false,
|
| 88 |
+
"vocab_size": 151552
|
| 89 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151329,
|
| 6 |
+
151336,
|
| 7 |
+
151338
|
| 8 |
+
],
|
| 9 |
+
"pad_token_id": 151329,
|
| 10 |
+
"transformers_version": "4.56.2"
|
| 11 |
+
}
|
model-00001-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:873372b8885c9a6af14bc87537ed99507ad930ff6ffd7bd736bcbb4f813eb288
|
| 3 |
+
size 5000398608
|
model-00002-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f734ea595c963fc8b0fbcdcc121c56303b9ad73856241dc2739c07a1a9699094
|
| 3 |
+
size 5000108792
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:309584311c67eaf30d291de0bf3616581ddfe7311f426593de2f8da6b3dd9d07
|
| 3 |
+
size 4999750072
|
model-00004-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d33d4bc54e3faaa0c31a5fcbfab4a7f925bb49340fe73a7401321a64d9f3f456
|
| 3 |
+
size 4999754064
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3c484985071435d8d0be7a3732a4cc592d2558e13cd9f68035e872aaa71affb
|
| 3 |
+
size 4998961480
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cae8811d22809b4156f21a3c0f006d653b3906f5fed6574f46d1e087b64d397f
|
| 3 |
+
size 4999754096
|
model-00007-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:657bfdf1996135075b714692398d6366c0832b083f6000cc727cc1bc630843a0
|
| 3 |
+
size 4999754104
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d06523067e38e6e0a195a6b72703078d07d2ed2fa5e2a78a3410e269c52e7bee
|
| 3 |
+
size 4999754064
|
model-00009-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08158f08ddf9aa38eb0a68409762d32291f13c90e9b24d18a857e7ee1b58c5d0
|
| 3 |
+
size 4999754104
|
model-00010-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e8a6d7a463c670909ed0195ea4b6bc3278c4440f93a8e5a5055109cfdf39d4
|
| 3 |
+
size 4998961376
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9311ed9833e58eef8947bbf1fc7b0c965241080dfb6d33bc89699730ac87ef5d
|
| 3 |
+
size 4999754152
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a29711993595f306078f39ed2901ed11ee4e812919474df3e344a8e77a40652b
|
| 3 |
+
size 4999754064
|
model-00013-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddf308cb58440fe6559f32e4fd19400d4d471c63f58d70f7c4183c575b6b36d0
|
| 3 |
+
size 1936919000
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
recipe.yaml
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
default_stage:
|
| 2 |
+
default_modifiers:
|
| 3 |
+
QuantizationModifier:
|
| 4 |
+
targets: [Linear]
|
| 5 |
+
ignore: [lm_head]
|
| 6 |
+
scheme: NVFP4
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"[MASK]",
|
| 5 |
+
"[gMASK]",
|
| 6 |
+
"[sMASK]",
|
| 7 |
+
"<sop>",
|
| 8 |
+
"<eop>",
|
| 9 |
+
"<|system|>",
|
| 10 |
+
"<|user|>",
|
| 11 |
+
"<|assistant|>",
|
| 12 |
+
"<|observation|>",
|
| 13 |
+
"<|begin_of_image|>",
|
| 14 |
+
"<|end_of_image|>",
|
| 15 |
+
"<|begin_of_video|>",
|
| 16 |
+
"<|end_of_video|>",
|
| 17 |
+
"<|begin_of_audio|>",
|
| 18 |
+
"<|end_of_audio|>",
|
| 19 |
+
"<|begin_of_transcription|>",
|
| 20 |
+
"<|end_of_transcription|>",
|
| 21 |
+
"<|code_prefix|>",
|
| 22 |
+
"<|code_middle|>",
|
| 23 |
+
"<|code_suffix|>",
|
| 24 |
+
"/nothink"
|
| 25 |
+
],
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|endoftext|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"pad_token": {
|
| 34 |
+
"content": "<|endoftext|>",
|
| 35 |
+
"lstrip": false,
|
| 36 |
+
"normalized": false,
|
| 37 |
+
"rstrip": false,
|
| 38 |
+
"single_word": false
|
| 39 |
+
}
|
| 40 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba
|
| 3 |
+
size 19970700
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,325 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"151329": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"151330": {
|
| 12 |
+
"content": "[MASK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"151331": {
|
| 20 |
+
"content": "[gMASK]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"151332": {
|
| 28 |
+
"content": "[sMASK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"151333": {
|
| 36 |
+
"content": "<sop>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"151334": {
|
| 44 |
+
"content": "<eop>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"151335": {
|
| 52 |
+
"content": "<|system|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"151336": {
|
| 60 |
+
"content": "<|user|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"151337": {
|
| 68 |
+
"content": "<|assistant|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"151338": {
|
| 76 |
+
"content": "<|observation|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"151339": {
|
| 84 |
+
"content": "<|begin_of_image|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"151340": {
|
| 92 |
+
"content": "<|end_of_image|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"151341": {
|
| 100 |
+
"content": "<|begin_of_video|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"151342": {
|
| 108 |
+
"content": "<|end_of_video|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"151343": {
|
| 116 |
+
"content": "<|begin_of_audio|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"151344": {
|
| 124 |
+
"content": "<|end_of_audio|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"151345": {
|
| 132 |
+
"content": "<|begin_of_transcription|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"151346": {
|
| 140 |
+
"content": "<|end_of_transcription|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"151347": {
|
| 148 |
+
"content": "<|code_prefix|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"151348": {
|
| 156 |
+
"content": "<|code_middle|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"151349": {
|
| 164 |
+
"content": "<|code_suffix|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"151350": {
|
| 172 |
+
"content": "<think>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"151351": {
|
| 180 |
+
"content": "</think>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"151352": {
|
| 188 |
+
"content": "<tool_call>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"151353": {
|
| 196 |
+
"content": "</tool_call>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"151354": {
|
| 204 |
+
"content": "<tool_response>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"151355": {
|
| 212 |
+
"content": "</tool_response>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"151356": {
|
| 220 |
+
"content": "<arg_key>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": false
|
| 226 |
+
},
|
| 227 |
+
"151357": {
|
| 228 |
+
"content": "</arg_key>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": false
|
| 234 |
+
},
|
| 235 |
+
"151358": {
|
| 236 |
+
"content": "<arg_value>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": false
|
| 242 |
+
},
|
| 243 |
+
"151359": {
|
| 244 |
+
"content": "</arg_value>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": false
|
| 250 |
+
},
|
| 251 |
+
"151360": {
|
| 252 |
+
"content": "/nothink",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"151361": {
|
| 260 |
+
"content": "<|begin_of_box|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": false
|
| 266 |
+
},
|
| 267 |
+
"151362": {
|
| 268 |
+
"content": "<|end_of_box|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"151363": {
|
| 276 |
+
"content": "<|image|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"151364": {
|
| 284 |
+
"content": "<|video|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
}
|
| 291 |
+
},
|
| 292 |
+
"additional_special_tokens": [
|
| 293 |
+
"<|endoftext|>",
|
| 294 |
+
"[MASK]",
|
| 295 |
+
"[gMASK]",
|
| 296 |
+
"[sMASK]",
|
| 297 |
+
"<sop>",
|
| 298 |
+
"<eop>",
|
| 299 |
+
"<|system|>",
|
| 300 |
+
"<|user|>",
|
| 301 |
+
"<|assistant|>",
|
| 302 |
+
"<|observation|>",
|
| 303 |
+
"<|begin_of_image|>",
|
| 304 |
+
"<|end_of_image|>",
|
| 305 |
+
"<|begin_of_video|>",
|
| 306 |
+
"<|end_of_video|>",
|
| 307 |
+
"<|begin_of_audio|>",
|
| 308 |
+
"<|end_of_audio|>",
|
| 309 |
+
"<|begin_of_transcription|>",
|
| 310 |
+
"<|end_of_transcription|>",
|
| 311 |
+
"<|code_prefix|>",
|
| 312 |
+
"<|code_middle|>",
|
| 313 |
+
"<|code_suffix|>",
|
| 314 |
+
"/nothink"
|
| 315 |
+
],
|
| 316 |
+
"clean_up_tokenization_spaces": false,
|
| 317 |
+
"do_lower_case": false,
|
| 318 |
+
"eos_token": "<|endoftext|>",
|
| 319 |
+
"extra_special_tokens": {},
|
| 320 |
+
"model_max_length": 128000,
|
| 321 |
+
"pad_token": "<|endoftext|>",
|
| 322 |
+
"padding_side": "left",
|
| 323 |
+
"remove_space": false,
|
| 324 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 325 |
+
}
|