Text Generation
Transformers
Safetensors
olmo_hybrid
risc-v
compiled-weights
olmo-hybrid
gated-deltanet
tool-use
Instructions to use jgalego/olmputer-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jgalego/olmputer-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="jgalego/olmputer-tiny")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("jgalego/olmputer-tiny") model = AutoModelForCausalLM.from_pretrained("jgalego/olmputer-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use jgalego/olmputer-tiny with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "jgalego/olmputer-tiny" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "jgalego/olmputer-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/jgalego/olmputer-tiny
- SGLang
How to use jgalego/olmputer-tiny 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 "jgalego/olmputer-tiny" \ --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": "jgalego/olmputer-tiny", "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 "jgalego/olmputer-tiny" \ --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": "jgalego/olmputer-tiny", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use jgalego/olmputer-tiny with Docker Model Runner:
docker model run hf.co/jgalego/olmputer-tiny
Add olmo-tiny
Browse files- chipformer.json +74 -0
- config.json +55 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
chipformer.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"vocab": 230324,
|
| 3 |
+
"pad": 230324,
|
| 4 |
+
"controls": {
|
| 5 |
+
"NT": 230316,
|
| 6 |
+
"ST0": 230317,
|
| 7 |
+
"ST1": 230318,
|
| 8 |
+
"SS0": 230319,
|
| 9 |
+
"SS1": 230320,
|
| 10 |
+
"HALT": 230321,
|
| 11 |
+
"GO": 230322,
|
| 12 |
+
"SC": 230323
|
| 13 |
+
},
|
| 14 |
+
"families": {
|
| 15 |
+
"V": [
|
| 16 |
+
0,
|
| 17 |
+
32768
|
| 18 |
+
],
|
| 19 |
+
"F0": [
|
| 20 |
+
32768,
|
| 21 |
+
32768
|
| 22 |
+
],
|
| 23 |
+
"F1": [
|
| 24 |
+
65536,
|
| 25 |
+
32768
|
| 26 |
+
],
|
| 27 |
+
"F2": [
|
| 28 |
+
98304,
|
| 29 |
+
4
|
| 30 |
+
],
|
| 31 |
+
"J": [
|
| 32 |
+
98308,
|
| 33 |
+
65536
|
| 34 |
+
],
|
| 35 |
+
"R": [
|
| 36 |
+
163844,
|
| 37 |
+
65536
|
| 38 |
+
],
|
| 39 |
+
"BYTE": [
|
| 40 |
+
229380,
|
| 41 |
+
512
|
| 42 |
+
],
|
| 43 |
+
"FLT": [
|
| 44 |
+
229892,
|
| 45 |
+
8
|
| 46 |
+
],
|
| 47 |
+
"HEX": [
|
| 48 |
+
229900,
|
| 49 |
+
16
|
| 50 |
+
],
|
| 51 |
+
"QS": [
|
| 52 |
+
229916,
|
| 53 |
+
16
|
| 54 |
+
],
|
| 55 |
+
"QD": [
|
| 56 |
+
229932,
|
| 57 |
+
128
|
| 58 |
+
],
|
| 59 |
+
"BD": [
|
| 60 |
+
230060,
|
| 61 |
+
256
|
| 62 |
+
]
|
| 63 |
+
},
|
| 64 |
+
"chip_layers": 11,
|
| 65 |
+
"circuit": {
|
| 66 |
+
"layers": 11,
|
| 67 |
+
"dims": 2679,
|
| 68 |
+
"heads": 144,
|
| 69 |
+
"ffn_units": 42014,
|
| 70 |
+
"max_units": 7876,
|
| 71 |
+
"max_heads": 30
|
| 72 |
+
},
|
| 73 |
+
"hidden": 2816
|
| 74 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"OlmoHybridForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 230324,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 230321,
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2816,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 11008,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"linear_attention",
|
| 17 |
+
"linear_attention",
|
| 18 |
+
"linear_attention",
|
| 19 |
+
"linear_attention",
|
| 20 |
+
"linear_attention",
|
| 21 |
+
"linear_attention",
|
| 22 |
+
"linear_attention",
|
| 23 |
+
"linear_attention",
|
| 24 |
+
"linear_attention",
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"full_attention"
|
| 28 |
+
],
|
| 29 |
+
"linear_a_log_max": 16.0,
|
| 30 |
+
"linear_a_log_min": 0.0,
|
| 31 |
+
"linear_allow_neg_eigval": true,
|
| 32 |
+
"linear_conv_kernel_dim": 4,
|
| 33 |
+
"linear_dt_init_floor": 0.0001,
|
| 34 |
+
"linear_dt_max": 0.1,
|
| 35 |
+
"linear_dt_min": 0.001,
|
| 36 |
+
"linear_key_head_dim": 96,
|
| 37 |
+
"linear_num_key_heads": 30,
|
| 38 |
+
"linear_num_value_heads": 30,
|
| 39 |
+
"linear_value_head_dim": 192,
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"model_type": "olmo_hybrid",
|
| 42 |
+
"num_attention_heads": 1,
|
| 43 |
+
"num_hidden_layers": 12,
|
| 44 |
+
"num_key_value_heads": 1,
|
| 45 |
+
"pad_token_id": 230324,
|
| 46 |
+
"rms_norm_eps": 1e-06,
|
| 47 |
+
"rope_parameters": {
|
| 48 |
+
"rope_theta": null,
|
| 49 |
+
"rope_type": "default"
|
| 50 |
+
},
|
| 51 |
+
"tie_word_embeddings": false,
|
| 52 |
+
"transformers_version": "5.19.0",
|
| 53 |
+
"use_cache": true,
|
| 54 |
+
"vocab_size": 230336
|
| 55 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": false,
|
| 3 |
+
"eos_token_id": 230321,
|
| 4 |
+
"pad_token_id": 230324,
|
| 5 |
+
"transformers_version": "5.19.0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11ae8f6e0f92fb27c8a8fb7cb4d46ef1687eb4c3e0518dd7bc9aabdf93a5ccb0
|
| 3 |
+
size 6260116672
|