Instructions to use sandepaAI/sandepa_ai_coder_435m_small_moe with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sandepaAI/sandepa_ai_coder_435m_small_moe with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="sandepaAI/sandepa_ai_coder_435m_small_moe")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sandepaAI/sandepa_ai_coder_435m_small_moe")
model = AutoModelForCausalLM.from_pretrained("sandepaAI/sandepa_ai_coder_435m_small_moe", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use sandepaAI/sandepa_ai_coder_435m_small_moe 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 sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
# Run inference directly in the terminal:
llama cli -hf sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
# Run inference directly in the terminal:
llama cli -hf sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

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 sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

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 sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

Use Docker

docker model run hf.co/sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

LM Studio
Jan

vLLM

How to use sandepaAI/sandepa_ai_coder_435m_small_moe with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sandepaAI/sandepa_ai_coder_435m_small_moe"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandepaAI/sandepa_ai_coder_435m_small_moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

SGLang

How to use sandepaAI/sandepa_ai_coder_435m_small_moe 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 "sandepaAI/sandepa_ai_coder_435m_small_moe" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandepaAI/sandepa_ai_coder_435m_small_moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "sandepaAI/sandepa_ai_coder_435m_small_moe" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sandepaAI/sandepa_ai_coder_435m_small_moe",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use sandepaAI/sandepa_ai_coder_435m_small_moe with Ollama:
```
ollama run hf.co/sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
```

Unsloth Studio

How to use sandepaAI/sandepa_ai_coder_435m_small_moe 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 sandepaAI/sandepa_ai_coder_435m_small_moe 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 sandepaAI/sandepa_ai_coder_435m_small_moe to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for sandepaAI/sandepa_ai_coder_435m_small_moe to start chatting

Docker Model Runner
How to use sandepaAI/sandepa_ai_coder_435m_small_moe with Docker Model Runner:
```
docker model run hf.co/sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0
```

Lemonade

How to use sandepaAI/sandepa_ai_coder_435m_small_moe with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull sandepaAI/sandepa_ai_coder_435m_small_moe:Q8_0

Run and chat with the model

lemonade run user.sandepa_ai_coder_435m_small_moe-Q8_0

List all available models

lemonade list

Atomic Chat

sandepaAI commited on 7 days ago

Commit

903f1de

verified ·

1 Parent(s): ffa4452

Upload folder using huggingface_hub

Browse files

Files changed (19) hide show

README.md +58 -0
chat_template.jinja +4 -0
checkpoint-250/chat_template.jinja +4 -0
checkpoint-250/config.json +35 -0
checkpoint-250/generation_config.json +12 -0
checkpoint-250/model.safetensors +3 -0
checkpoint-250/optimizer.pt +3 -0
checkpoint-250/rng_state.pth +3 -0
checkpoint-250/scheduler.pt +3 -0
checkpoint-250/tokenizer.json +0 -0
checkpoint-250/tokenizer_config.json +17 -0
checkpoint-250/trainer_state.json +309 -0
checkpoint-250/training_args.bin +3 -0
config.json +35 -0
generation_config.json +12 -0
model.safetensors +3 -0
tokenizer.json +0 -0
tokenizer_config.json +17 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,58 @@

+---
+base_model: sandepaAI/sandepa_ai_coder_small_moe_435m
+library_name: transformers
+model_name: sft_output
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+# Model Card for sft_output
+This model is a fine-tuned version of [sandepaAI/sandepa_ai_coder_small_moe_435m](https://huggingface.co/sandepaAI/sandepa_ai_coder_small_moe_435m).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+## Quick start
+```python
+from transformers import pipeline
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+## Training procedure
+This model was trained with SFT.
+### Framework versions
+- TRL: 1.9.0
+- Transformers: 5.14.1
+- Pytorch: 2.13.0
+- Datasets: 5.0.0
+- Tokenizers: 0.22.2
+## Citations
+Cite TRL as:
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

chat_template.jinja ADDED Viewed

	@@ -0,0 +1,4 @@

+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>
+'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
+'}}{% endif %}

checkpoint-250/chat_template.jinja ADDED Viewed

	@@ -0,0 +1,4 @@

+{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>
+'}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
+'}}{% endif %}

checkpoint-250/config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "eos_token_id": 50256,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "max_position_embeddings": 512,
+  "model_type": "mixtral",
+  "num_attention_heads": 14,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 14,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "pad_token_id": 50256,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50259
+}

checkpoint-250/generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 50256,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

checkpoint-250/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d55062eaf4f00996f29f099a840380f62175671d4ff16ad315fbc87bec95c2
+size 1164043184

checkpoint-250/optimizer.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c85c32db7f004fa9a6c55c31cf717638e0e6ca276de1e9fe809aac3af0a158
+size 2328086987

checkpoint-250/rng_state.pth ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-250/scheduler.pt ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:5b04611bea80597dee677a377375d057cf3fa3437fb4ed8809d4662285b8811b
+size 1465

checkpoint-250/tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

checkpoint-250/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-250/trainer_state.json ADDED Viewed

	@@ -0,0 +1,309 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "aux_loss": 2.3257370829582213,
+      "entropy": 3.6007017314434053,
+      "epoch": 0.04,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.9280000000000002e-05,
+      "loss": 3.8956069946289062,
+      "mean_token_accuracy": 0.3586781073361635,
+      "num_tokens": 72397.0,
+      "step": 10
+    },
+    {
+      "aux_loss": 2.3277345478534697,
+      "entropy": 3.6272001445293425,
+      "epoch": 0.08,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.8480000000000003e-05,
+      "loss": 3.896469497680664,
+      "mean_token_accuracy": 0.3564587336033583,
+      "num_tokens": 143657.0,
+      "step": 20
+    },
+    {
+      "aux_loss": 2.323074048757553,
+      "entropy": 3.601874440908432,
+      "epoch": 0.12,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.768e-05,
+      "loss": 3.902561569213867,
+      "mean_token_accuracy": 0.3605616968125105,
+      "num_tokens": 215509.0,
+      "step": 30
+    },
+    {
+      "aux_loss": 2.3261504590511324,
+      "entropy": 3.6270964324474333,
+      "epoch": 0.16,
+      "grad_norm": 1.09375,
+      "learning_rate": 1.688e-05,
+      "loss": 3.8741905212402346,
+      "mean_token_accuracy": 0.3614043775945902,
+      "num_tokens": 288789.0,
+      "step": 40
+    },
+    {
+      "aux_loss": 2.324697870016098,
+      "entropy": 3.5004548013210295,
+      "epoch": 0.2,
+      "grad_norm": 0.99609375,
+      "learning_rate": 1.6080000000000002e-05,
+      "loss": 3.795322799682617,
+      "mean_token_accuracy": 0.37013124153017996,
+      "num_tokens": 361289.0,
+      "step": 50
+    },
+    {
+      "aux_loss": 2.3249743819236754,
+      "entropy": 3.499809369444847,
+      "epoch": 0.24,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.5280000000000003e-05,
+      "loss": 3.755328369140625,
+      "mean_token_accuracy": 0.37386555671691896,
+      "num_tokens": 433139.0,
+      "step": 60
+    },
+    {
+      "aux_loss": 2.324633425474167,
+      "entropy": 3.6745675444602965,
+      "epoch": 0.28,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.448e-05,
+      "loss": 3.902497100830078,
+      "mean_token_accuracy": 0.36646418645977974,
+      "num_tokens": 504919.0,
+      "step": 70
+    },
+    {
+      "aux_loss": 2.3186131000518797,
+      "entropy": 3.470395928621292,
+      "epoch": 0.32,
+      "grad_norm": 0.9921875,
+      "learning_rate": 1.3680000000000003e-05,
+      "loss": 3.723850631713867,
+      "mean_token_accuracy": 0.3796745929867029,
+      "num_tokens": 576593.0,
+      "step": 80
+    },
+    {
+      "aux_loss": 2.3274434208869934,
+      "entropy": 3.6475940525531767,
+      "epoch": 0.36,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.2880000000000002e-05,
+      "loss": 3.898761749267578,
+      "mean_token_accuracy": 0.3605402667075396,
+      "num_tokens": 650395.0,
+      "step": 90
+    },
+    {
+      "aux_loss": 2.3328470826148986,
+      "entropy": 3.5895772576332092,
+      "epoch": 0.4,
+      "grad_norm": 1.125,
+      "learning_rate": 1.2080000000000001e-05,
+      "loss": 3.7831195831298827,
+      "mean_token_accuracy": 0.3730145484209061,
+      "num_tokens": 720132.0,
+      "step": 100
+    },
+    {
+      "aux_loss": 2.331581395864487,
+      "entropy": 3.670157164335251,
+      "epoch": 0.44,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.128e-05,
+      "loss": 3.955718231201172,
+      "mean_token_accuracy": 0.35614234730601313,
+      "num_tokens": 791175.0,
+      "step": 110
+    },
+    {
+      "aux_loss": 2.3278864681720735,
+      "entropy": 3.564240163564682,
+      "epoch": 0.48,
+      "grad_norm": 1.0078125,
+      "learning_rate": 1.0480000000000001e-05,
+      "loss": 3.7921863555908204,
+      "mean_token_accuracy": 0.37363966181874275,
+      "num_tokens": 864007.0,
+      "step": 120
+    },
+    {
+      "aux_loss": 2.333659642934799,
+      "entropy": 3.6451989471912385,
+      "epoch": 0.52,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.68e-06,
+      "loss": 3.894023132324219,
+      "mean_token_accuracy": 0.35798243805766106,
+      "num_tokens": 935475.0,
+      "step": 130
+    },
+    {
+      "aux_loss": 2.3140768826007845,
+      "entropy": 3.50389506816864,
+      "epoch": 0.56,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.880000000000001e-06,
+      "loss": 3.7427852630615233,
+      "mean_token_accuracy": 0.38606042340397834,
+      "num_tokens": 1002776.0,
+      "step": 140
+    },
+    {
+      "aux_loss": 2.323524034023285,
+      "entropy": 3.62218790948391,
+      "epoch": 0.6,
+      "grad_norm": 1.0078125,
+      "learning_rate": 8.08e-06,
+      "loss": 3.8935062408447267,
+      "mean_token_accuracy": 0.36692074611783027,
+      "num_tokens": 1074485.0,
+      "step": 150
+    },
+    {
+      "aux_loss": 2.319421482086182,
+      "entropy": 3.6522460520267486,
+      "epoch": 0.64,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.280000000000001e-06,
+      "loss": 3.938425064086914,
+      "mean_token_accuracy": 0.3640777923166752,
+      "num_tokens": 1148295.0,
+      "step": 160
+    },
+    {
+      "aux_loss": 2.3238328874111174,
+      "entropy": 3.635464870929718,
+      "epoch": 0.68,
+      "grad_norm": 0.9765625,
+      "learning_rate": 6.480000000000001e-06,
+      "loss": 3.839573287963867,
+      "mean_token_accuracy": 0.3715536307543516,
+      "num_tokens": 1220134.0,
+      "step": 170
+    },
+    {
+      "aux_loss": 2.3195456326007844,
+      "entropy": 3.4972031474113465,
+      "epoch": 0.72,
+      "grad_norm": 0.921875,
+      "learning_rate": 5.68e-06,
+      "loss": 3.700027084350586,
+      "mean_token_accuracy": 0.37758239097893237,
+      "num_tokens": 1291904.0,
+      "step": 180
+    },
+    {
+      "aux_loss": 2.331765002012253,
+      "entropy": 3.6483884513378144,
+      "epoch": 0.76,
+      "grad_norm": 0.8984375,
+      "learning_rate": 4.880000000000001e-06,
+      "loss": 3.873792266845703,
+      "mean_token_accuracy": 0.36337695084512234,
+      "num_tokens": 1363374.0,
+      "step": 190
+    },
+    {
+      "aux_loss": 2.3272350072860717,
+      "entropy": 3.674150836467743,
+      "epoch": 0.8,
+      "grad_norm": 0.9609375,
+      "learning_rate": 4.08e-06,
+      "loss": 3.885345458984375,
+      "mean_token_accuracy": 0.3636812623590231,
+      "num_tokens": 1433716.0,
+      "step": 200
+    },
+    {
+      "aux_loss": 2.32773614525795,
+      "entropy": 3.635636830329895,
+      "epoch": 0.84,
+      "grad_norm": 1.0078125,
+      "learning_rate": 3.2800000000000004e-06,
+      "loss": 3.8587207794189453,
+      "mean_token_accuracy": 0.36572874560952184,
+      "num_tokens": 1506681.0,
+      "step": 210
+    },
+    {
+      "aux_loss": 2.325718504190445,
+      "entropy": 3.5308443903923035,
+      "epoch": 0.88,
+      "grad_norm": 0.95703125,
+      "learning_rate": 2.4800000000000004e-06,
+      "loss": 3.72619514465332,
+      "mean_token_accuracy": 0.37508156448602675,
+      "num_tokens": 1575868.0,
+      "step": 220
+    },
+    {
+      "aux_loss": 2.3259211778640747,
+      "entropy": 3.433101177215576,
+      "epoch": 0.92,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 3.593972015380859,
+      "mean_token_accuracy": 0.3888819687068462,
+      "num_tokens": 1648038.0,
+      "step": 230
+    },
+    {
+      "aux_loss": 2.3294626414775848,
+      "entropy": 3.597357761859894,
+      "epoch": 0.96,
+      "grad_norm": 0.9296875,
+      "learning_rate": 8.8e-07,
+      "loss": 3.8016372680664063,
+      "mean_token_accuracy": 0.36985846906900405,
+      "num_tokens": 1720626.0,
+      "step": 240
+    },
+    {
+      "aux_loss": 2.319813519716263,
+      "entropy": 3.5566279590129852,
+      "epoch": 1.0,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8e-08,
+      "loss": 3.757618713378906,
+      "mean_token_accuracy": 0.3740091536194086,
+      "num_tokens": 1788925.0,
+      "step": 250
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6391876233437184.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c53877a785bfe38e0faf9340c1ed796f773a0b617c0db782ffbb188493f5cff7
+size 5713

config.json ADDED Viewed

	@@ -0,0 +1,35 @@

+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "bfloat16",
+  "eos_token_id": 50256,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 1280,
+  "max_position_embeddings": 512,
+  "model_type": "mixtral",
+  "num_attention_heads": 14,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 14,
+  "num_local_experts": 8,
+  "output_router_logits": true,
+  "pad_token_id": 50256,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.14.1",
+  "use_cache": false,
+  "vocab_size": 50259
+}

generation_config.json ADDED Viewed

	@@ -0,0 +1,12 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": [
+    50256
+  ],
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 50256,
+  "transformers_version": "5.14.1",
+  "use_cache": true
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d55062eaf4f00996f29f099a840380f62175671d4ff16ad315fbc87bec95c2
+size 1164043184

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,17 @@

+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c53877a785bfe38e0faf9340c1ed796f773a0b617c0db782ffbb188493f5cff7
+size 5713