Text Generation
Transformers
Safetensors
olmo3
code
livecodebench
sft
lora-merged
nothink
conversational
Instructions to use modrill/code-nothink-o7b-20260908 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use modrill/code-nothink-o7b-20260908 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="modrill/code-nothink-o7b-20260908") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("modrill/code-nothink-o7b-20260908") model = AutoModelForCausalLM.from_pretrained("modrill/code-nothink-o7b-20260908", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use modrill/code-nothink-o7b-20260908 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "modrill/code-nothink-o7b-20260908" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/code-nothink-o7b-20260908", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/modrill/code-nothink-o7b-20260908
- SGLang
How to use modrill/code-nothink-o7b-20260908 with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "modrill/code-nothink-o7b-20260908" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/code-nothink-o7b-20260908", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "modrill/code-nothink-o7b-20260908" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modrill/code-nothink-o7b-20260908", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use modrill/code-nothink-o7b-20260908 with Docker Model Runner:
docker model run hf.co/modrill/code-nothink-o7b-20260908
Add O7B-NOTHINK merged full weights + eval tokenizer (DEV256 NoThink)
Browse files- BUNDLE_MANIFEST.json +52 -0
- OFFICIAL_MERGE_RECEIPT.json +1 -0
- README.md +55 -0
- chat_template.jinja +16 -0
- config.json +75 -0
- generation_config.json +4 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +189 -0
- vocab.json +0 -0
BUNDLE_MANIFEST.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template_sha256": "03348cf1aab6c187117df83b81525a2c688934636a63b1c4a0acf9b2488c210e",
|
| 3 |
+
"content_sha256": "33d099e5a93f3c02c042b149363879c5026a9abcd8e27d64cb20039c10fa08f2",
|
| 4 |
+
"files": [
|
| 5 |
+
{
|
| 6 |
+
"bytes": 1646,
|
| 7 |
+
"path": "chat_template.jinja",
|
| 8 |
+
"sha256": "03348cf1aab6c187117df83b81525a2c688934636a63b1c4a0acf9b2488c210e"
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"bytes": 1631,
|
| 12 |
+
"path": "config.json",
|
| 13 |
+
"sha256": "c395e580e9e181b271048bbef57d0316ea7f2aea17761340c7cc6ccec6241119"
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"bytes": 203,
|
| 17 |
+
"path": "generation_config.json",
|
| 18 |
+
"sha256": "1a9b3935357116c75f806d1defbd9893281a8f4a94aefeca708f31303e94aa7e"
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"bytes": 916646,
|
| 22 |
+
"path": "merges.txt",
|
| 23 |
+
"sha256": "b6fe424e334903f7fb84d3a106d9730455f4744b9fe3c21ee136d97a00e72502"
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"bytes": 581,
|
| 27 |
+
"path": "special_tokens_map.json",
|
| 28 |
+
"sha256": "78afb564e81264029b25f9caf24bda2521d5bdaeff5cd3fdbc01d3da2e8ce2f2"
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"bytes": 7137177,
|
| 32 |
+
"path": "tokenizer.json",
|
| 33 |
+
"sha256": "73fd5254624f39a88e3faac6a8e11300fc3c735ed37880d4f4f08db898eaecca"
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"bytes": 4319,
|
| 37 |
+
"path": "tokenizer_config.json",
|
| 38 |
+
"sha256": "e7ea56bef75ad5257b13dc09bfe3033e8cd742eb42233e9b57726d53be9f7ead"
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"bytes": 1611056,
|
| 42 |
+
"path": "vocab.json",
|
| 43 |
+
"sha256": "9e14712c91b37c7aab74b1306baa46ac342d620637a4b44523cdc3aec7d24195"
|
| 44 |
+
}
|
| 45 |
+
],
|
| 46 |
+
"mode": "think",
|
| 47 |
+
"schema": "CODE_SFT_TOKENIZER_RUNTIME_BUNDLE_V1",
|
| 48 |
+
"source_repo": "allenai/Olmo-3-7B-Think",
|
| 49 |
+
"source_revision": "d97e442d7cc678210054dbcc9b440894d62c89a4",
|
| 50 |
+
"status": "COMPLETE",
|
| 51 |
+
"tokenizer_sha256": "73fd5254624f39a88e3faac6a8e11300fc3c735ed37880d4f4f08db898eaecca"
|
| 52 |
+
}
|
OFFICIAL_MERGE_RECEIPT.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"adapter_tree_sha256":"d70a59bec8b109611187ccb5887cb31745155bd14de81f0bf2ff565861961a6f","base_model_path":"/workspace/code-sft-infra/models/olmo-3-1025-7b","checkpoint_manifest_sha256":"f761225b4665bda461be9d6bc7be830fb8b1c65fe0441ebd0ce7874f89fc8163","checkpoint_path":"/workspace/code-sft-runs/t30b2507-q4b-tn-v2-lr1e4-e1-20260907/arms/O7B-NOTHINK/out/O7B-NOTHINK/a81bae42db3975be1671e27b9c9a56da1a9f980f/olmo3-lcb-noprefill/17cdfd955548e8b7104d20976dc87521529a3878e6cca9f0b1446a64500ddd7a/step-000140-tokens-9371874","label":"v4-o7b-nothink","merged_at_unix":1788870515.9084604,"merged_model_path":"/workspace/code-sft-runs/rstar-eval/official-dev256/v4-o7b-nothink/scratch/step-000140-tokens-9371874-merged-full","merged_tree_sha256":"ba2ad2eedf581c32db0ed157021cfa60be251d9b72c8f360eb12d95a5db84745","receipt_sha256":"1cdb8e89250bd870d4a61b3330653a80ac409805ceeefe56db2ed52b527d4b94","schema":"CODE_SFT_OFFICIAL_DEV256_MERGE_RECEIPT_V1"}
|
README.md
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: allenai/Olmo-3-1025-7B
|
| 4 |
+
tags:
|
| 5 |
+
- code
|
| 6 |
+
- livecodebench
|
| 7 |
+
- sft
|
| 8 |
+
- lora-merged
|
| 9 |
+
- nothink
|
| 10 |
+
library_name: transformers
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Olmo-3-1025-7B Code V4 NoThink (merged)
|
| 14 |
+
|
| 15 |
+
**Arm ID:** `O7B-NOTHINK`
|
| 16 |
+
**Run ID:** `t30b2507-o7b-nothink-v4-tail151643`
|
| 17 |
+
|
| 18 |
+
Merged full bf16 weights used for the official DEV256 NoThink evaluation. Tokenizer files in this repo are the **eval-caliber** bundle (`olmo3-lcb-noprefill`); they overlay any tokenizer files that were present in the merge directory.
|
| 19 |
+
|
| 20 |
+
**Single-seed exploratory result, not a preregistered confirmatory claim.**
|
| 21 |
+
|
| 22 |
+
## Base model
|
| 23 |
+
|
| 24 |
+
- Hugging Face: [`allenai/Olmo-3-1025-7B`](https://huggingface.co/allenai/Olmo-3-1025-7B)
|
| 25 |
+
- Revision: `a81bae42db3975be1671e27b9c9a56da1a9f980f` (from `RUN_IDENTITY.json` / local snapshot `/workspace/code-sft-infra/models/olmo-3-1025-7b`)
|
| 26 |
+
|
| 27 |
+
## Training
|
| 28 |
+
|
| 29 |
+
- Method: LoRA r64 / α128 on seven projections (`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`), then merged into full-model bf16 safetensors
|
| 30 |
+
- Data: NoThink code SFT (paired V4, physical 2-epoch concat)
|
| 31 |
+
- Endpoint (score): **step 140**, **9,371,874** assistant tokens — endpoint-as-score, no checkpoint picking
|
| 32 |
+
- Train seed 42; LR `1e-4`; context 8192; AdamW; cosine by assistant-token dose
|
| 33 |
+
- Host: local GPU box; eval tokenizer renderer `olmo3-lcb-noprefill`
|
| 34 |
+
|
| 35 |
+
## Evaluation
|
| 36 |
+
|
| 37 |
+
- Suite: official LiveCodeBench **DEV256**
|
| 38 |
+
- Seed **3407**, mode **NoThink**, `max_model_len` **8192**, vLLM **0.28.0**
|
| 39 |
+
- Metric: sandbox pass@1 = passed / 256
|
| 40 |
+
- This arm: **46/256 (18.0%)**, caps **107**
|
| 41 |
+
- Base (`allenai/Olmo-3-1025-7B`, same NoThink protocol): **20/256 (7.8%)**, caps **95**
|
| 42 |
+
- McNemar exact p = **6.9e-05**
|
| 43 |
+
|
| 44 |
+
## Inference notes
|
| 45 |
+
|
| 46 |
+
- Use **this repository's** tokenizer and `chat_template.jinja`.
|
| 47 |
+
- This chat template is the **no-prefill `<think>`** variant (`olmo3-lcb-noprefill`): do not prefill `<think>` at the start of the assistant turn.
|
| 48 |
+
- Stop token ids: **100257** (`<|endoftext|>`) and **100265** (`<|im_end|>`).
|
| 49 |
+
- Eval sampling used temperature 0.7, top_p 0.8, top_k 20.
|
| 50 |
+
|
| 51 |
+
## Weight checksum
|
| 52 |
+
|
| 53 |
+
- `model.safetensors` (14,596,063,960 bytes): `sha256:ce853010b5de765a4f0a393cc77fe84d24305b567486473dd3ef8028fa4c9e1f`
|
| 54 |
+
|
| 55 |
+
`OFFICIAL_MERGE_RECEIPT.json` is included for merge provenance. LoRA adapter checkpoints are **not** in this repo.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set has_system = messages|selectattr('role', 'equalto', 'system')|list|length > 0 %}{% if not has_system %}{{ '<|im_start|>system
|
| 2 |
+
You are OLMo, a helpful function-calling AI assistant built by Ai2. Your date cutoff is November 2024, and your model weights are available at https://huggingface.co/allenai. You do not currently have access to any functions. <functions></functions><|im_end|>
|
| 3 |
+
' }}{% endif %}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|im_start|>system
|
| 4 |
+
' + message['content'] }}{% if message.get('functions', none) is not none %}{{ ' <functions>' + message['functions'] + '</functions><|im_end|>
|
| 5 |
+
' }}{% else %}{{ ' You do not currently have access to any functions. <functions></functions><|im_end|>
|
| 6 |
+
' }}{% endif %}{% elif message['role'] == 'user' %}{% if message.get('functions', none) is not none %}{{ '<|im_start|>user
|
| 7 |
+
' + message['content'] + '
|
| 8 |
+
' + '<functions>' + message['functions'] + '</functions><|im_end|>
|
| 9 |
+
' }}{% else %}{{ '<|im_start|>user
|
| 10 |
+
' + message['content'] + '<|im_end|>
|
| 11 |
+
' }}{% endif %}{% elif message['role'] == 'assistant' %}{{ '<|im_start|>assistant
|
| 12 |
+
' }}{% if message.get('content', none) is not none %}{{ message['content'] }}{% endif %}{% if message.get('function_calls', none) is not none %}{{ '<function_calls>' + message['function_calls'] + '</function_calls>' }}{% endif %}{% if not loop.last %}{{ '<|im_end|>' + '
|
| 13 |
+
' }}{% else %}{{ eos_token }}{% endif %}{% elif message['role'] == 'environment' %}{{ '<|im_start|>environment
|
| 14 |
+
' + message['content'] + '<|im_end|>
|
| 15 |
+
' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|im_start|>assistant
|
| 16 |
+
' }}{% endif %}{% endfor %}
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"full_attention": {
|
| 57 |
+
"attention_factor": 1.2079441541679836,
|
| 58 |
+
"beta_fast": 32,
|
| 59 |
+
"beta_slow": 1,
|
| 60 |
+
"factor": 8.0,
|
| 61 |
+
"original_max_position_embeddings": 8192,
|
| 62 |
+
"rope_theta": 500000,
|
| 63 |
+
"rope_type": "yarn"
|
| 64 |
+
},
|
| 65 |
+
"sliding_attention": {
|
| 66 |
+
"rope_theta": 500000.0,
|
| 67 |
+
"rope_type": "default"
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"sliding_window": 4096,
|
| 71 |
+
"tie_word_embeddings": false,
|
| 72 |
+
"transformers_version": "5.16.1",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 100278
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "5.16.1"
|
| 4 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce853010b5de765a4f0a393cc77fe84d24305b567486473dd3ef8028fa4c9e1f
|
| 3 |
+
size 14596063960
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|pad|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"100256": {
|
| 5 |
+
"content": "<|extra_id_0|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": false
|
| 11 |
+
},
|
| 12 |
+
"100257": {
|
| 13 |
+
"content": "<|endoftext|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"100258": {
|
| 21 |
+
"content": "<|fim_prefix|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"100259": {
|
| 29 |
+
"content": "<|fim_middle|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"100260": {
|
| 37 |
+
"content": "<|fim_suffix|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"100261": {
|
| 45 |
+
"content": "|||PHONE_NUMBER|||",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"100262": {
|
| 53 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"100263": {
|
| 61 |
+
"content": "|||IP_ADDRESS|||",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"100264": {
|
| 69 |
+
"content": "<|im_start|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"100265": {
|
| 77 |
+
"content": "<|im_end|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"100266": {
|
| 85 |
+
"content": "<|extra_id_1|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"100267": {
|
| 93 |
+
"content": "<|extra_id_2|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"100268": {
|
| 101 |
+
"content": "<|extra_id_3|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"100269": {
|
| 109 |
+
"content": "<|extra_id_4|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"100270": {
|
| 117 |
+
"content": "<|extra_id_5|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"100271": {
|
| 125 |
+
"content": "<|extra_id_6|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"100272": {
|
| 133 |
+
"content": "<|extra_id_7|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"100273": {
|
| 141 |
+
"content": "<|extra_id_8|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"100274": {
|
| 149 |
+
"content": "<|extra_id_9|>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"100275": {
|
| 157 |
+
"content": "<|extra_id_10|>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"100276": {
|
| 165 |
+
"content": "<|endofprompt|>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"100277": {
|
| 173 |
+
"content": "<|pad|>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
}
|
| 180 |
+
},
|
| 181 |
+
"bos_token": "<|endoftext|>",
|
| 182 |
+
"clean_up_tokenization_spaces": false,
|
| 183 |
+
"eos_token": "<|endoftext|>",
|
| 184 |
+
"extra_special_tokens": {},
|
| 185 |
+
"model_max_length": 65536,
|
| 186 |
+
"pad_token": "<|pad|>",
|
| 187 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 188 |
+
"unk_token": "<|endoftext|>"
|
| 189 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|