Instructions to use kanye/ye with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kanye/ye with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="kanye/ye", device_map="auto")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("kanye/ye") model = AutoModelForCausalLM.from_pretrained("kanye/ye", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use kanye/ye with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "kanye/ye" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kanye/ye", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/kanye/ye
- SGLang
How to use kanye/ye 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 "kanye/ye" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kanye/ye", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "kanye/ye" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "kanye/ye", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use kanye/ye with Docker Model Runner:
docker model run hf.co/kanye/ye
Resolved merge conflicts
Browse files- AWQ/config.json +0 -25
- AWQ/generation_config.json +0 -6
- AWQ/pytorch_model.bin +0 -3
- AWQ/quant_config.json +0 -6
- AWQ/special_tokens_map.json +0 -28
- AWQ/tokenizer.json +0 -0
- AWQ/tokenizer.model +0 -3
- AWQ/tokenizer_config.json +0 -44
- AshhLimaRP-Mistral-7B.Q4_K_M.gguf +0 -3
- AshhLimaRP-Mistral-7B.Q6_K.gguf +0 -3
- SillyTavern Presets/LimaRP-Alpaca_Context-Template.json +0 -11
- SillyTavern Presets/LimaRP-Alpaca_Instruct-Mode.json +0 -18
- adapter_model.bin +0 -3
AWQ/config.json
DELETED
|
@@ -1,25 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "/home/anon/AI-Models/LLM/AshhLimaRP-Mistral-7B/",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"MistralForCausalLM"
|
| 5 |
-
],
|
| 6 |
-
"bos_token_id": 1,
|
| 7 |
-
"eos_token_id": 2,
|
| 8 |
-
"hidden_act": "silu",
|
| 9 |
-
"hidden_size": 4096,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"intermediate_size": 14336,
|
| 12 |
-
"max_position_embeddings": 32768,
|
| 13 |
-
"model_type": "mistral",
|
| 14 |
-
"num_attention_heads": 32,
|
| 15 |
-
"num_hidden_layers": 32,
|
| 16 |
-
"num_key_value_heads": 8,
|
| 17 |
-
"rms_norm_eps": 1e-05,
|
| 18 |
-
"rope_theta": 10000.0,
|
| 19 |
-
"sliding_window": 4096,
|
| 20 |
-
"tie_word_embeddings": false,
|
| 21 |
-
"torch_dtype": "float16",
|
| 22 |
-
"transformers_version": "4.34.1",
|
| 23 |
-
"use_cache": true,
|
| 24 |
-
"vocab_size": 32000
|
| 25 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/generation_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 1,
|
| 4 |
-
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.34.1"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/pytorch_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:251bc4a6827d76cf70be0b653370d3c2026908b4d3cbb8cb0d577677570eacc2
|
| 3 |
-
size 4151034841
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/quant_config.json
DELETED
|
@@ -1,6 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"zero_point": true,
|
| 3 |
-
"q_group_size": 128,
|
| 4 |
-
"w_bit": 4,
|
| 5 |
-
"version": "GEMM"
|
| 6 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/special_tokens_map.json
DELETED
|
@@ -1,28 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<unk>",
|
| 4 |
-
"<s>",
|
| 5 |
-
"</s>"
|
| 6 |
-
],
|
| 7 |
-
"bos_token": {
|
| 8 |
-
"content": "<s>",
|
| 9 |
-
"lstrip": false,
|
| 10 |
-
"normalized": false,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"single_word": false
|
| 13 |
-
},
|
| 14 |
-
"eos_token": {
|
| 15 |
-
"content": "</s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
-
"unk_token": {
|
| 22 |
-
"content": "<unk>",
|
| 23 |
-
"lstrip": false,
|
| 24 |
-
"normalized": false,
|
| 25 |
-
"rstrip": false,
|
| 26 |
-
"single_word": false
|
| 27 |
-
}
|
| 28 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/tokenizer.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
AWQ/tokenizer.model
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
-
size 493443
|
|
|
|
|
|
|
|
|
|
|
|
AWQ/tokenizer_config.json
DELETED
|
@@ -1,44 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<unk>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<s>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
}
|
| 27 |
-
},
|
| 28 |
-
"additional_special_tokens": [
|
| 29 |
-
"<unk>",
|
| 30 |
-
"<s>",
|
| 31 |
-
"</s>"
|
| 32 |
-
],
|
| 33 |
-
"bos_token": "<s>",
|
| 34 |
-
"clean_up_tokenization_spaces": false,
|
| 35 |
-
"eos_token": "</s>",
|
| 36 |
-
"legacy": true,
|
| 37 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
-
"pad_token": null,
|
| 39 |
-
"sp_model_kwargs": {},
|
| 40 |
-
"spaces_between_special_tokens": false,
|
| 41 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
-
"unk_token": "<unk>",
|
| 43 |
-
"use_default_system_prompt": true
|
| 44 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
AshhLimaRP-Mistral-7B.Q4_K_M.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:b67868935b2399a0a6433f8b4fd417a62274f01188c6495bc4bdcc6b894148fc
|
| 3 |
-
size 4368438912
|
|
|
|
|
|
|
|
|
|
|
|
AshhLimaRP-Mistral-7B.Q6_K.gguf
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0074d49d059b590eb11f624abf956c309091ce66f5295461187cb0116f9f4a8c
|
| 3 |
-
size 5942064768
|
|
|
|
|
|
|
|
|
|
|
|
SillyTavern Presets/LimaRP-Alpaca_Context-Template.json
DELETED
|
@@ -1,11 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"story_string": "{{system}}{{char}}'s Persona: {{description}}\n\n{{#if persona}}{{user}}'s Persona: {{persona}}\n\n{{/if}}\n{{#if scenario}}Scenario: {{scenario}}\n\n{{/if}}\n{{#if loreBefore}}Background information: {{loreBefore}}\n\n{{/if}}\nPlay the role of {{char}}. With scene and characters now described, you must engage in a roleplay conversation with {{user}} below this line. Never write for {{user}} in your responses.",
|
| 3 |
-
"example_separator": "",
|
| 4 |
-
"chat_start": "",
|
| 5 |
-
"always_force_name2": false,
|
| 6 |
-
"trim_sentences": false,
|
| 7 |
-
"include_newline": false,
|
| 8 |
-
"custom_stopping_strings": "",
|
| 9 |
-
"custom_stopping_strings_macro": true,
|
| 10 |
-
"name": "LimaRP-Alpaca"
|
| 11 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
SillyTavern Presets/LimaRP-Alpaca_Instruct-Mode.json
DELETED
|
@@ -1,18 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"wrap": true,
|
| 3 |
-
"names": true,
|
| 4 |
-
"system_prompt": "",
|
| 5 |
-
"system_sequence": "<<SYSTEM>>",
|
| 6 |
-
"stop_sequence": "###",
|
| 7 |
-
"input_sequence": "\n### Input:",
|
| 8 |
-
"output_sequence": "\n### Response:",
|
| 9 |
-
"separator_sequence": "",
|
| 10 |
-
"macro": true,
|
| 11 |
-
"names_force_groups": false,
|
| 12 |
-
"last_output_sequence": "\n### Response: (length = short)",
|
| 13 |
-
"activation_regex": "",
|
| 14 |
-
"system_sequence_prefix": "\n### Instruction:",
|
| 15 |
-
"system_sequence_suffix": "",
|
| 16 |
-
"first_output_sequence": "",
|
| 17 |
-
"name": "LimaRP-Alpaca"
|
| 18 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
adapter_model.bin
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:8a8b38d58b554cdf248a4822c2a31a10aac47a4815882c3983424bdba1493421
|
| 3 |
-
size 2684516749
|
|
|
|
|
|
|
|
|
|
|
|