Upload folder using huggingface_hub
Browse files- chat_template.jinja +26 -0
- config.json +34 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% if not add_generation_prompt is defined %}
|
| 2 |
+
{% set add_generation_prompt = false %}
|
| 3 |
+
{% endif %}
|
| 4 |
+
{%- set ns = namespace(found=false) -%}
|
| 5 |
+
{%- for message in messages -%}
|
| 6 |
+
{%- if message['role'] == 'system' -%}
|
| 7 |
+
{%- set ns.found = true -%}
|
| 8 |
+
{%- endif -%}
|
| 9 |
+
{%- endfor -%}
|
| 10 |
+
{{bos_token}}{%- if not ns.found -%}
|
| 11 |
+
{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\n'}}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{%- for message in messages %}
|
| 14 |
+
{%- if message['role'] == 'system' %}
|
| 15 |
+
{{ message['content'] }}
|
| 16 |
+
{%- else %}
|
| 17 |
+
{%- if message['role'] == 'user' %}
|
| 18 |
+
{{'### Instruction:\n' + message['content'] + '\n'}}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{{'### Response:\n' + message['content'] + '\n<|EOT|>\n'}}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- endfor %}
|
| 24 |
+
{% if add_generation_prompt %}
|
| 25 |
+
{{'### Response:'}}
|
| 26 |
+
{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 32013,
|
| 8 |
+
"dtype": "float16",
|
| 9 |
+
"eos_token_id": 32021,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 5504,
|
| 15 |
+
"max_position_embeddings": 16384,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"num_key_value_heads": 16,
|
| 21 |
+
"pad_token_id": null,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"factor": 4.0,
|
| 26 |
+
"rope_theta": 100000,
|
| 27 |
+
"rope_type": "linear",
|
| 28 |
+
"type": "linear"
|
| 29 |
+
},
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"transformers_version": "5.9.0",
|
| 32 |
+
"use_cache": true,
|
| 33 |
+
"vocab_size": 32256
|
| 34 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 32013,
|
| 4 |
+
"eos_token_id": 32021,
|
| 5 |
+
"transformers_version": "5.9.0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7107adde29d5b43d20ebcaeb3859a0373c5f7bdf0afad2149732e808ac0cd497
|
| 3 |
+
size 2692968904
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": null,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|EOT|>",
|
| 7 |
+
"is_local": false,
|
| 8 |
+
"local_files_only": false,
|
| 9 |
+
"model_max_length": 16384,
|
| 10 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"sp_model_kwargs": {},
|
| 12 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 13 |
+
"unk_token": null,
|
| 14 |
+
"use_default_system_prompt": false
|
| 15 |
+
}
|