初始化项目，由ModelHub XC社区提供模型
Model: mrfakename/llamaphi-3-128k-instruct Source: Original Platform
This commit is contained in:
ModelHub XC
47
.gitattributes
vendored
Normal file
47
.gitattributes
vendored
Normal file
@@ -0,0 +1,47 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
10
README.md
Normal file
10
README.md
Normal file
@@ -0,0 +1,10 @@
|
||||
---
|
||||
license: mit
|
||||
language:
|
||||
- en
|
||||
---
|
||||
[Phi 3 128K instruct](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) weights in the Llama format.
|
||||
|
||||
All credit goes to @vonjack for their useful [conversion script](https://huggingface.co/vonjack/Phi-3-mini-4k-instruct-LLaMAfied) as well as index files which were used to make this.
|
||||
|
||||
Check out their version for the [4k model](https://huggingface.co/vonjack/Phi-3-mini-4k-instruct-LLaMAfied)!
|
||||
40
added_tokens.json
Normal file
40
added_tokens.json
Normal file
@@ -0,0 +1,40 @@
|
||||
{
|
||||
"<|/code|>": 32014,
|
||||
"<|/data|>": 32033,
|
||||
"<|/inst|>": 32037,
|
||||
"<|/query|>": 32031,
|
||||
"<|/sys|>": 32035,
|
||||
"<|assistant_mask|>": 32017,
|
||||
"<|assistant|>": 32001,
|
||||
"<|calc|>": 32012,
|
||||
"<|code|>": 32013,
|
||||
"<|continue|>": 32009,
|
||||
"<|data|>": 32032,
|
||||
"<|diff_marker|>": 32025,
|
||||
"<|disc_sep|>": 32029,
|
||||
"<|disc_start|>": 32028,
|
||||
"<|disc_thread|><|query|>": 32030,
|
||||
"<|endoftext|>": 32000,
|
||||
"<|end|>": 32007,
|
||||
"<|fim_middle|>": 32021,
|
||||
"<|fim_prefix|>": 32020,
|
||||
"<|fim_suffix|>": 32022,
|
||||
"<|function_call|>": 32005,
|
||||
"<|function_list|>": 32011,
|
||||
"<|function_output|>": 32003,
|
||||
"<|ghissue|>": 32026,
|
||||
"<|ghreview|>": 32027,
|
||||
"<|inst|>": 32036,
|
||||
"<|ipynb_marker|>": 32024,
|
||||
"<|message|>": 32019,
|
||||
"<|meta_start|>": 32023,
|
||||
"<|raw|>": 32008,
|
||||
"<|resource|>": 32016,
|
||||
"<|start|>": 32018,
|
||||
"<|step|>": 32002,
|
||||
"<|summary|>": 32015,
|
||||
"<|system|>": 32006,
|
||||
"<|sys|>": 32034,
|
||||
"<|tag|>": 32004,
|
||||
"<|user|>": 32010
|
||||
}
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 32000,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3072,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 32,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"sliding_window": 2047,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.40.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32064
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
26
convert.py
Normal file
26
convert.py
Normal file
@@ -0,0 +1,26 @@
|
||||
from transformers import AutoModelForCausalLM
|
||||
import torch
|
||||
from safetensors.torch import save_file
|
||||
|
||||
model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-3-mini-128k-instruct", trust_remote_code=True)
|
||||
|
||||
params = model.state_dict()
|
||||
params2 = {}
|
||||
|
||||
for r in params.keys():
|
||||
if "gate_up_proj" in r:
|
||||
(gate, up) = params[r].chunk(2)
|
||||
params2[r.replace("gate_up_proj", "gate_proj")] = gate
|
||||
params2[r.replace("gate_up_proj", "up_proj")] = up
|
||||
elif "qkv_proj" in r:
|
||||
(q, k, v) = params[r].chunk(3)
|
||||
params2[r.replace("qkv_proj", "q_proj")] = q
|
||||
params2[r.replace("qkv_proj", "k_proj")] = k
|
||||
params2[r.replace("qkv_proj", "v_proj")] = v
|
||||
else:
|
||||
params2[r] = params[r]
|
||||
|
||||
for r in params2.keys():
|
||||
params2[r] = torch.tensor(params2[r].clone().detach(), dtype=torch.bfloat16)
|
||||
|
||||
save_file(params2, "model-00001-of-00001.safetensors", metadata={"format": "pt"})
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": [
|
||||
32000,
|
||||
32007
|
||||
],
|
||||
"pad_token_id": 32000,
|
||||
"transformers_version": "4.39.3"
|
||||
}
|
||||
3
model-00001-of-00001.safetensors
Normal file
3
model-00001-of-00001.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4cf54b6c05234009723ac9648d712476049d5b33b51963b66cefcaa9388c88d9
|
||||
size 7642192824
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 7642192792
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00001.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
|
||||
"model.norm.weight": "model-00001-of-00001.safetensors"
|
||||
}
|
||||
}
|
||||
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|/inst|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93733
tokenizer.json
Normal file
93733
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
349
tokenizer_config.json
Normal file
349
tokenizer_config.json
Normal file
@@ -0,0 +1,349 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"32000": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "<|assistant|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32002": {
|
||||
"content": "<|step|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32003": {
|
||||
"content": "<|function_output|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32004": {
|
||||
"content": "<|tag|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32005": {
|
||||
"content": "<|function_call|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32006": {
|
||||
"content": "<|system|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32007": {
|
||||
"content": "<|end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32008": {
|
||||
"content": "<|raw|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32009": {
|
||||
"content": "<|continue|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32010": {
|
||||
"content": "<|user|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32011": {
|
||||
"content": "<|function_list|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32012": {
|
||||
"content": "<|calc|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32013": {
|
||||
"content": "<|code|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32014": {
|
||||
"content": "<|/code|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32015": {
|
||||
"content": "<|summary|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32016": {
|
||||
"content": "<|resource|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32017": {
|
||||
"content": "<|assistant_mask|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32018": {
|
||||
"content": "<|start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32019": {
|
||||
"content": "<|message|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32020": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32021": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32022": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32023": {
|
||||
"content": "<|meta_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32024": {
|
||||
"content": "<|ipynb_marker|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32025": {
|
||||
"content": "<|diff_marker|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32026": {
|
||||
"content": "<|ghissue|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32027": {
|
||||
"content": "<|ghreview|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32028": {
|
||||
"content": "<|disc_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32029": {
|
||||
"content": "<|disc_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32030": {
|
||||
"content": "<|disc_thread|><|query|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32031": {
|
||||
"content": "<|/query|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32032": {
|
||||
"content": "<|data|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32033": {
|
||||
"content": "<|/data|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32034": {
|
||||
"content": "<|sys|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32035": {
|
||||
"content": "<|/sys|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32036": {
|
||||
"content": "<|inst|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32037": {
|
||||
"content": "<|/inst|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|/inst|>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|end|>",
|
||||
"legacy": false,
|
||||
"model_max_length": 4096,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user