Instructions to use shibatch/tinymqa1m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shibatch/tinymqa1m with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shibatch/tinymqa1m", dtype="auto") - llama-cpp-python
How to use shibatch/tinymqa1m with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="shibatch/tinymqa1m", filename="tinymqa1m.BF16.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 shibatch/tinymqa1m with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf shibatch/tinymqa1m:Q4_K_M # Run inference directly in the terminal: llama-cli -hf shibatch/tinymqa1m:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf shibatch/tinymqa1m:Q4_K_M # Run inference directly in the terminal: llama-cli -hf shibatch/tinymqa1m:Q4_K_M
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 shibatch/tinymqa1m:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf shibatch/tinymqa1m:Q4_K_M
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 shibatch/tinymqa1m:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf shibatch/tinymqa1m:Q4_K_M
Use Docker
docker model run hf.co/shibatch/tinymqa1m:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use shibatch/tinymqa1m with Ollama:
ollama run hf.co/shibatch/tinymqa1m:Q4_K_M
- Unsloth Studio
How to use shibatch/tinymqa1m 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 shibatch/tinymqa1m 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 shibatch/tinymqa1m to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for shibatch/tinymqa1m to start chatting
- Docker Model Runner
How to use shibatch/tinymqa1m with Docker Model Runner:
docker model run hf.co/shibatch/tinymqa1m:Q4_K_M
- Lemonade
How to use shibatch/tinymqa1m with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull shibatch/tinymqa1m:Q4_K_M
Run and chat with the model
lemonade run user.tinymqa1m-Q4_K_M
List all available models
lemonade list
Upload folder using huggingface_hub
Browse files- .gitattributes +21 -0
- hf/config.json +32 -0
- hf/generation_config.json +10 -0
- hf/model.safetensors +3 -0
- hf/special_tokens_map.json +6 -0
- hf/tokenizer.model +3 -0
- hf/tokenizer_config.json +10 -0
- tinymqa1m.BF16.gguf +3 -0
- tinymqa1m.F16.gguf +3 -0
- tinymqa1m.F32.gguf +3 -0
- tinymqa1m.IQ3_S.gguf +3 -0
- tinymqa1m.IQ3_XXS.gguf +3 -0
- tinymqa1m.IQ4_NL.gguf +3 -0
- tinymqa1m.IQ4_XS.gguf +3 -0
- tinymqa1m.Q2_K.gguf +3 -0
- tinymqa1m.Q3_K_L.gguf +3 -0
- tinymqa1m.Q3_K_M.gguf +3 -0
- tinymqa1m.Q3_K_S.gguf +3 -0
- tinymqa1m.Q4_0.gguf +3 -0
- tinymqa1m.Q4_1.gguf +3 -0
- tinymqa1m.Q4_K_M.gguf +3 -0
- tinymqa1m.Q4_K_S.gguf +3 -0
- tinymqa1m.Q5_K_M.gguf +3 -0
- tinymqa1m.Q5_K_S.gguf +3 -0
- tinymqa1m.Q6_K.gguf +3 -0
- tinymqa1m.Q8_0.gguf +3 -0
- tinymqa1m.TQ1_0.gguf +3 -0
- tinymqa1m.TQ2_0.gguf +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,24 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tinymqa1m.BF16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tinymqa1m.F16.gguf filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
tinymqa1m.F32.gguf filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
tinymqa1m.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
tinymqa1m.IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
tinymqa1m.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
tinymqa1m.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
tinymqa1m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
tinymqa1m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
tinymqa1m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
tinymqa1m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
tinymqa1m.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
tinymqa1m.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
tinymqa1m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
tinymqa1m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
tinymqa1m.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
tinymqa1m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
tinymqa1m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
tinymqa1m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
tinymqa1m.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
tinymqa1m.TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text
|
hf/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"dtype": "float32",
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"head_dim": 32,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 128,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 352,
|
| 15 |
+
"max_position_embeddings": 256,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 4,
|
| 19 |
+
"num_hidden_layers": 4,
|
| 20 |
+
"num_key_value_heads": 1,
|
| 21 |
+
"pad_token_id": 2,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_parameters": {
|
| 25 |
+
"rope_theta": 10000.0,
|
| 26 |
+
"rope_type": "default"
|
| 27 |
+
},
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "5.9.0",
|
| 30 |
+
"use_cache": false,
|
| 31 |
+
"vocab_size": 512
|
| 32 |
+
}
|
hf/generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"output_attentions": false,
|
| 6 |
+
"output_hidden_states": false,
|
| 7 |
+
"pad_token_id": 2,
|
| 8 |
+
"transformers_version": "5.9.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
hf/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:febe012ca1183bc353c9e39e48cecb85a5c07cd526f4ab204b8e3cd3b1dcc22a
|
| 3 |
+
size 3351064
|
hf/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
hf/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc157f8b709cc196e4aff7ce859392df25b380f863ecab561922a475d2d8c7d1
|
| 3 |
+
size 247523
|
hf/tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"model_max_length": 256,
|
| 7 |
+
"pad_token": "</s>",
|
| 8 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 9 |
+
"unk_token": "<unk>"
|
| 10 |
+
}
|
tinymqa1m.BF16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:591ce26c11f341168d18ee05a6c5b747b21c7d242623c670204227fe9cc28312
|
| 3 |
+
size 1689632
|
tinymqa1m.F16.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56f1add96e99c3c6f0c629da778dda007fd07ce90ff7912500f687107503e649
|
| 3 |
+
size 1689632
|
tinymqa1m.F32.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:40fb722cb0af9b2296407421ac934534f5a5c5fce51c861804f8ab8e022908df
|
| 3 |
+
size 3360800
|
tinymqa1m.IQ3_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6853fb400e4145ca3ab329de3d2aa1e5691d5ec8c8fa983032802d717f2729b9
|
| 3 |
+
size 523296
|
tinymqa1m.IQ3_XXS.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4de99487e7f77f450b7708fc515e8c97dfb92e5564e4982b5c762fa5eaa08af3
|
| 3 |
+
size 523296
|
tinymqa1m.IQ4_NL.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8e9e534fa1d2d32a39e79519c051d269580154f3da5d66301d78b7afa726a6f
|
| 3 |
+
size 524320
|
tinymqa1m.IQ4_XS.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bbf7afb3dd209db2f47a980483f8b252b717d8ff03d4b950e5470fb612199ab3
|
| 3 |
+
size 524320
|
tinymqa1m.Q2_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83a2ee31b9f6013e4e0b3345abefaeb9a3231437f559e03124497b1191264003
|
| 3 |
+
size 523296
|
tinymqa1m.Q3_K_L.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d4dcc1dbe46a3be10c720659b049c4fdbf940779fb20bbcf1fd48a656d8b9c2
|
| 3 |
+
size 570400
|
tinymqa1m.Q3_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64ba17b923fdd1b68b4988b6995f228e9151cde66455937fb4d3bb081368a61a
|
| 3 |
+
size 554528
|
tinymqa1m.Q3_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48973a1169a3da6bb83557129b96d1820074686dce02e597e0158640d0cd0ba0
|
| 3 |
+
size 521248
|
tinymqa1m.Q4_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb95a6e10f28b76a1dd71c15560dec5a5eee8943f591ef45d11c129786b22cff
|
| 3 |
+
size 521248
|
tinymqa1m.Q4_1.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c0659f97594897f528cbd6cbffc2541be895608e725d44431f4f93b75cb81bc
|
| 3 |
+
size 569376
|
tinymqa1m.Q4_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cddb90c1d6b6fbbfadf031350fa7babca8e4a7accdbedbe738f3683869716287
|
| 3 |
+
size 654368
|
tinymqa1m.Q4_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9d88d0fd1d6650df59266d9d45f1f505c06d9883d4b9281d95186c5ed8c321f
|
| 3 |
+
size 618528
|
tinymqa1m.Q5_K_M.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:105da1fdbcf9118456e8c859a9c79c59a2c1ff8e3301285ac3f7146a762e850e
|
| 3 |
+
size 696352
|
tinymqa1m.Q5_K_S.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc3ae6c72004c91d5a48e0161b349619db82f7c397ff037ed76404f8dffe6524
|
| 3 |
+
size 665632
|
tinymqa1m.Q6_K.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45b472f4c0585e50a7dcdc4ed506b0844f3c5a40db624437ad24be76d201c753
|
| 3 |
+
size 906272
|
tinymqa1m.Q8_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66bd8d5a03589e40e1d0656b90220fd29f699512122af7170c7612c364b7c835
|
| 3 |
+
size 906272
|
tinymqa1m.TQ1_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:771bb8dc6fecc7cd9a084147ce73e2c371a1fc535a34a13c027f85c87294d4a0
|
| 3 |
+
size 529440
|
tinymqa1m.TQ2_0.gguf
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc11758d577ae6a2ebb2600dc9179890fe89d23e8c310858308b12e35a96e427
|
| 3 |
+
size 529440
|