Safetensors
GGUF
Turkish
llama
Llama-3
instruct
finetune
chatml
gpt4
synthetic data
distillation
function calling
json mode
axolotl
roleplaying
chat
Instructions to use tda45/TdAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use tda45/TdAI with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="tda45/TdAI", filename="llama.cpp/models/ggml-vocab-aquila.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use tda45/TdAI with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf tda45/TdAI # Run inference directly in the terminal: llama cli -hf tda45/TdAI
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf tda45/TdAI # Run inference directly in the terminal: ./llama-cli -hf tda45/TdAI
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf tda45/TdAI # Run inference directly in the terminal: ./build/bin/llama-cli -hf tda45/TdAI
Use Docker
docker model run hf.co/tda45/TdAI
- LM Studio
- Jan
- Ollama
How to use tda45/TdAI with Ollama:
ollama run hf.co/tda45/TdAI
- Unsloth Studio
How to use tda45/TdAI with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tda45/TdAI to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for tda45/TdAI to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for tda45/TdAI to start chatting
- Atomic Chat new
- Docker Model Runner
How to use tda45/TdAI with Docker Model Runner:
docker model run hf.co/tda45/TdAI
- Lemonade
How to use tda45/TdAI with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull tda45/TdAI
Run and chat with the model
lemonade run user.TdAI-{{QUANT_TAG}}List all available models
lemonade list
| // | |
| // llama_memory_hybrid | |
| // | |
| // utilizes instances of llama_memory_recurrent and llama_kv_cache to | |
| // support models where each layer may be either attention-based or recurrent | |
| class llama_memory_hybrid : public llama_memory_i { | |
| public: | |
| llama_memory_hybrid( | |
| const llama_model & model, | |
| /* attn */ | |
| ggml_type type_k, | |
| ggml_type type_v, | |
| bool v_trans, | |
| uint32_t kv_size, | |
| uint32_t n_pad, | |
| uint32_t n_swa, | |
| llama_swa_type swa_type, | |
| /* recurrent */ | |
| ggml_type type_r, | |
| ggml_type type_s, | |
| uint32_t rs_size, | |
| /* common */ | |
| uint32_t n_seq_max, | |
| uint32_t n_rs_seq, | |
| bool offload, | |
| bool unified, | |
| /* layer filters */ | |
| const layer_filter_cb & filter_attn = nullptr, | |
| const layer_filter_cb & filter_recr = nullptr); | |
| ~llama_memory_hybrid() = default; | |
| // | |
| // llama_memory_i | |
| // | |
| llama_memory_context_ptr init_batch( | |
| llama_batch_allocr & balloc, | |
| uint32_t n_ubatch, | |
| bool embd_all) override; | |
| llama_memory_context_ptr init_full() override; | |
| llama_memory_context_ptr init_update(llama_context * lctx, bool optimize) override; | |
| bool get_can_shift() const override; | |
| void clear(bool data) override; | |
| bool seq_rm (llama_seq_id seq_id, llama_pos p0, llama_pos p1) override; | |
| void seq_cp (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) override; | |
| void seq_keep(llama_seq_id seq_id) override; | |
| void seq_add (llama_seq_id seq_id, llama_pos p0, llama_pos p1, llama_pos shift) override; | |
| void seq_div (llama_seq_id seq_id, llama_pos p0, llama_pos p1, int d) override; | |
| llama_pos seq_pos_min(llama_seq_id seq_id) const override; | |
| llama_pos seq_pos_max(llama_seq_id seq_id) const override; | |
| std::map<ggml_backend_buffer_type_t, size_t> memory_breakdown() const override; | |
| // state write/load | |
| void state_write(llama_io_write_i & io, llama_seq_id seq_id = -1, llama_state_seq_flags flags = 0) const override; | |
| void state_read (llama_io_read_i & io, llama_seq_id seq_id = -1, llama_state_seq_flags flags = 0) override; | |
| // | |
| // llama_memory_hybrid specific API | |
| // | |
| llama_kv_cache * get_mem_attn() const; | |
| llama_memory_recurrent * get_mem_recr() const; | |
| private: | |
| const llama_hparams & hparams; | |
| const std::unique_ptr<llama_kv_cache> mem_attn; | |
| const std::unique_ptr<llama_memory_recurrent> mem_recr; | |
| }; | |
| class llama_memory_hybrid_context : public llama_memory_context_i { | |
| public: | |
| using slot_info_vec_t = llama_kv_cache::slot_info_vec_t; | |
| // init failure | |
| explicit llama_memory_hybrid_context(llama_memory_status status); | |
| // init full | |
| explicit llama_memory_hybrid_context(llama_memory_hybrid * mem); | |
| // init update | |
| explicit llama_memory_hybrid_context( | |
| llama_memory_hybrid * mem, | |
| llama_context * lctx, | |
| bool optimize); | |
| // init success | |
| llama_memory_hybrid_context( | |
| llama_memory_hybrid * mem, | |
| slot_info_vec_t sinfos_attn, | |
| std::vector<llama_ubatch> ubatches); | |
| ~llama_memory_hybrid_context() = default; | |
| bool next() override; | |
| bool apply() override; | |
| llama_memory_status get_status() const override; | |
| const llama_ubatch & get_ubatch() const override; | |
| // | |
| // llama_memory_hybrid_context | |
| // | |
| const llama_kv_cache_context * get_attn() const; | |
| const llama_memory_recurrent_context * get_recr() const; | |
| private: | |
| // the index of the next ubatch to process | |
| size_t i_next = 0; | |
| std::vector<llama_ubatch> ubatches; | |
| const llama_memory_context_ptr ctx_attn; | |
| const llama_memory_context_ptr ctx_recr; | |
| const llama_memory_status status; | |
| }; | |